data-station-specification.bib

@article{jordan2022selecting,
	title = {Selecting {Privacy}-{Enhancing} {Technologies} for {Managing} {Health} {Data} {Use}},
	volume = {10},
	issn = {2296-2565},
	url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8967420/},
	doi = {10.3389/fpubh.2022.814163},
	abstract = {Privacy protection for health data is more than simply stripping datasets of specific identifiers. Privacy protection increasingly means the application of privacy-enhancing technologies (PETs), also known as privacy engineering. Demands for the application of PETs are not yet met with ease of use or even understanding. This paper provides a scope of the current peer-reviewed evidence regarding the practical use or adoption of various PETs for managing health data privacy. We describe the state of knowledge of PETS for the use and exchange of health data specifically and build a practical perspective on the steps needed to improve the standardization of the application of PETs for diverse uses of health data.},
	urldate = {2023-02-04},
	journal = {Frontiers in Public Health},
	author = {Jordan, Sara and Fontaine, Clara and Hendricks-Sturrup, Rachele},
	month = mar,
	year = {2022},
	pages = {814163},
	file = {PubMed Central Full Text PDF:/Users/dkapitan/Zotero/storage/9Z6PVM72/Jordan et al. - 2022 - Selecting Privacy-Enhancing Technologies for Manag.pdf:application/pdf},
}

@article{dereuver2018digital,
	title = {The {Digital} {Platform}: {A} {Research} {Agenda}},
	volume = {33},
	issn = {0268-3962},
	shorttitle = {The {Digital} {Platform}},
	url = {https://doi.org/10.1057/s41265-016-0033-3},
	doi = {10.1057/s41265-016-0033-3},
	abstract = {As digital platforms are transforming almost every industry today, they are slowly finding their way into the mainstream information systems (ISs) literature. Digital platforms are a challenging research object because of their distributed nature and intertwinement with institutions, markets and technologies. New research challenges arise as a result of the exponentially growing scale of platform innovation, the increasing complexity of platform architectures and the spread of digital platforms to many different industries. This paper develops a research agenda for digital platforms research in IS. We recommend researchers seek to (1) advance conceptual clarity by providing clear definitions that specify the unit of analysis, degree of digitality and the sociotechnical nature of digital platforms; (2) define the proper scoping of digital platform concepts by studying platforms on different architectural levels and in different industry settings; and (3) advance methodological rigour by employing embedded case studies, longitudinal studies, design research, data-driven modelling and visualisation techniques. Considering current developments in the business domain, we suggest six questions for further research: (1) Are platforms here to stay? (2) How should platforms be designed? (3) How do digital platforms transform industries? (4) How can data-driven approaches inform digital platforms research? (5) How should researchers develop theory for digital platforms? and (6) How do digital platforms affect everyday life?},
	language = {en},
	number = {2},
	urldate = {2023-02-15},
	journal = {Journal of Information Technology},
	publisher = {SAGE Publications Ltd},
	author = {de Reuver, Mark and Sørensen, Carsten and Basole, Rahul C.},
	month = jun,
	year = {2018},
	pages = {124--135},
	file = {SAGE PDF Full Text:/Users/dkapitan/Zotero/storage/Z2GNA5YA/de Reuver et al. - 2018 - The Digital Platform A Research Agenda.pdf:application/pdf},
}

@inproceedings{dereuver2022openness,
	address = {New York, NY, USA},
	series = {{DE} '22},
	title = {The openness of data platforms: a research agenda},
	isbn = {978-1-4503-9923-4},
	shorttitle = {The openness of data platforms},
	url = {https://doi.org/10.1145/3565011.3569056},
	doi = {10.1145/3565011.3569056},
	abstract = {Data platforms are the keystone of the data economy. When opened up, data platforms allow data owners, data consumers and third parties to interact. Yet, openness may also harm business and societal interests. Literature on platform openness does not cover data platforms, and data economy scholars rarely study platform openness. Therefore, this paper develops a research agenda on the openness of data platforms. We explore how data platforms differ from conventional digital platforms (e.g., software platforms). From those differentiating characteristics, we identify areas for future work: (1) The specific characteristics of data require reconceptualizing the object of platform openness; (2) New ways in which data platforms can be opened should be conceptualized; (3) As data platforms are tailored to specific industries, platform-to-platform openness should be a novel unit of analysis; (4) Because opening up data platforms create novel risks, new reasons to (not) open up data platforms should be studied.},
	urldate = {2023-02-15},
	booktitle = {Proceedings of the 1st {International} {Workshop} on {Data} {Economy}},
	publisher = {Association for Computing Machinery},
	author = {de Reuver, Mark and Ofe, Hosea and Agahari, Wirawan and Abbas, Antragama Ewa and Zuiderwijk, Anneke},
	month = dec,
	year = {2022},
	keywords = {data ecosystem, data marketplace, data platform, platform openness},
	pages = {34--41},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/CSL6NCAX/de Reuver et al. - 2022 - The openness of data platforms a research agenda.pdf:application/pdf},
}

@inproceedings{choudhury2020personal,
	address = {Singapore},
	series = {Communications in {Computer} and {Information} {Science}},
	title = {Personal {Health} {Train} on {FHIR}: {A} {Privacy} {Preserving} {Federated} {Approach} for {Analyzing} {FAIR} {Data} in {Healthcare}},
	isbn = {978-981-15-6315-7},
	shorttitle = {Personal {Health} {Train} on {FHIR}},
	doi = {10.1007/978-981-15-6315-7_7},
	abstract = {Big data and machine learning applications focus on retrieving data on a central location for analysis. However, healthcare data can be sensitive in nature and as such difficult to share and make use for secondary purposes. Healthcare vendors are restricted to share data without proper consent from the patient. There is a rising awareness among individual patients as well regarding sharing their personal information due to ethical, legal and societal problems. The current data-sharing platforms in healthcare do not sufficiently handle these issues. The rationale of the Personal Health Train (PHT) approach shifts the focus from sharing data to sharing processing/analysis applications and their respective results. A prerequisite of the PHT-infrastructure is that the data is FAIR (findable, accessible, interoperable, reusable). The aim of the paper is to describe a methodology of finding the number of patients diagnosed with hypertension and calculate cohort statistics in a privacy-preserving federated manner. The whole process completes without individual patient data leaving the source. For this, we rely on the Fast Healthcare Interoperability Resources (FHIR) standard.},
	language = {en},
	booktitle = {Machine {Learning}, {Image} {Processing}, {Network} {Security} and {Data} {Sciences}},
	publisher = {Springer},
	author = {Choudhury, Ananya and van Soest, Johan and Nayak, Stuti and Dekker, Andre},
	editor = {Bhattacharjee, Arup and Borgohain, Samir Kr. and Soni, Badal and Verma, Gyanendra and Gao, Xiao-Zhi},
	year = {2020},
	keywords = {FHIR, FAIR, Personal health train},
	pages = {85--95},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/MX4FY5MX/Choudhury et al. - 2020 - Personal Health Train on FHIR A Privacy Preservin.pdf:application/pdf},
}

@article{beyan2020distributed,
	title = {Distributed {Analytics} on {Sensitive} {Medical} {Data}: {The} {Personal} {Health} {Train}},
	volume = {2},
	issn = {2641-435X},
	shorttitle = {Distributed {Analytics} on {Sensitive} {Medical} {Data}},
	url = {https://doi.org/10.1162/dint_a_00032},
	doi = {10.1162/dint_a_00032},
	abstract = {In recent years, as newer technologies have evolved around the healthcare ecosystem, more and more data have been generated. Advanced analytics could power the data collected from numerous sources, both from healthcare institutions, or generated by individuals themselves via apps and devices, and lead to innovations in treatment and diagnosis of diseases; improve the care given to the patient; and empower citizens to participate in the decision-making process regarding their own health and well-being. However, the sensitive nature of the health data prohibits healthcare organizations from sharing the data. The Personal Health Train (PHT) is a novel approach, aiming to establish a distributed data analytics infrastructure enabling the (re)use of distributed healthcare data, while data owners stay in control of their own data. The main principle of the PHT is that data remain in their original location, and analytical tasks visit data sources and execute the tasks. The PHT provides a distributed, flexible approach to use data in a network of participants, incorporating the FAIR principles. It facilitates the responsible use of sensitive and/or personal data by adopting international principles and regulations. This paper presents the concepts and main components of the PHT and demonstrates how it complies with FAIR principles.},
	number = {1-2},
	urldate = {2023-02-16},
	journal = {Data Intelligence},
	author = {Beyan, Oya and Choudhury, Ananya and van Soest, Johan and Kohlbacher, Oliver and Zimmermann, Lukas and Stenzhorn, Holger and Karim, Md. Rezaul and Dumontier, Michel and Decker, Stefan and da Silva Santos, Luiz Olavo Bonino and Dekker, Andre},
	month = jan,
	year = {2020},
	pages = {96--107},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/SGX995AZ/Beyan et al. - 2020 - Distributed Analytics on Sensitive Medical Data T.pdf:application/pdf},
}

@article{rieke2020future,
	title = {The future of digital health with federated learning},
	volume = {3},
	copyright = {2020 The Author(s)},
	issn = {2398-6352},
	url = {https://www.nature.com/articles/s41746-020-00323-1},
	doi = {10.1038/s41746-020-00323-1},
	abstract = {Data-driven machine learning (ML) has emerged as a promising approach for building accurate and robust statistical models from medical data, which is collected in huge volumes by modern healthcare systems. Existing medical data is not fully exploited by ML primarily because it sits in data silos and privacy concerns restrict access to this data. However, without access to sufficient data, ML will be prevented from reaching its full potential and, ultimately, from making the transition from research to clinical practice. This paper considers key factors contributing to this issue, explores how federated learning (FL) may provide a solution for the future of digital health and highlights the challenges and considerations that need to be addressed.},
	language = {en},
	number = {1},
	urldate = {2023-04-23},
	journal = {npj Digital Medicine},
	publisher = {Nature Publishing Group},
	author = {Rieke, Nicola and Hancox, Jonny and Li, Wenqi and Milletarì, Fausto and Roth, Holger R. and Albarqouni, Shadi and Bakas, Spyridon and Galtier, Mathieu N. and Landman, Bennett A. and Maier-Hein, Klaus and Ourselin, Sébastien and Sheller, Micah and Summers, Ronald M. and Trask, Andrew and Xu, Daguang and Baust, Maximilian and Cardoso, M. Jorge},
	month = sep,
	year = {2020},
	note = {Number: 1},
	keywords = {Medical research, Medical imaging},
	pages = {1--7},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/DJI9BHQP/Rieke et al. - 2020 - The future of digital health with federated learni.pdf:application/pdf},
}

@article{mehl2021who,
	title = {{WHO} {SMART} guidelines: optimising country-level use of guideline recommendations in the digital age},
	volume = {3},
	issn = {2589-7500},
	shorttitle = {{WHO} {SMART} guidelines},
	url = {https://www.thelancet.com/journals/landig/article/PIIS2589-7500(21)00038-8/fulltext},
	doi = {10.1016/S2589-7500(21)00038-8},
	language = {English},
	number = {4},
	urldate = {2023-06-21},
	journal = {The Lancet Digital Health},
	publisher = {Elsevier},
	author = {Mehl, Garrett and Tunçalp, Özge and Ratanaprayul, Natschja and Tamrat, Tigest and Barreix, María and Lowrance, David and Bartolomeos, Kidist and Say, Lale and Kostanjsek, Nenad and Jakob, Robert and Grove, John and Mariano, Bernardo and Swaminathan, Soumya},
	month = apr,
	year = {2021},
	pages = {e213--e216},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/ZQH6V9GJ/Mehl et al. - 2021 - WHO SMART guidelines optimising country-level use.pdf:application/pdf},
}

@article{prainsack2023beyond,
	title = {Beyond {Individual} {Rights}: {How} {Data} {Solidarity} {Gives} {People} {Meaningful} {Control} over {Data}},
	volume = {23},
	issn = {1526-5161, 1536-0075},
	shorttitle = {Beyond {Individual} {Rights}},
	url = {https://www.tandfonline.com/doi/full/10.1080/15265161.2023.2256267},
	doi = {10.1080/15265161.2023.2256267},
	language = {en},
	number = {11},
	urldate = {2023-11-11},
	journal = {The American Journal of Bioethics},
	author = {Prainsack, Barbara and El-Sayed, Seliem},
	month = nov,
	year = {2023},
	pages = {36--39},
	file = {prainsack2023beyond.pdf:/Users/dkapitan/Zotero/storage/T542DFXH/prainsack2023beyond.pdf:application/pdf},
}

@article{pedreira2023composable,
	title = {The {Composable} {Data} {Management} {System} {Manifesto}},
	volume = {16},
	issn = {2150-8097},
	url = {https://dl.acm.org/doi/10.14778/3603581.3603604},
	doi = {10.14778/3603581.3603604},
	abstract = {The requirement for specialization in data management systems has evolved faster than our software development practices. After decades of organic growth, this situation has created a siloed landscape composed of hundreds of products developed and maintained as monoliths, with limited reuse between systems. This fragmentation has resulted in developers often reinventing the wheel, increased maintenance costs, and slowed down innovation. It has also affected the end users, who are often required to learn the idiosyncrasies of dozens of incompatible SQL and non-SQL API dialects, and settle for systems with incomplete functionality and inconsistent semantics. In this vision paper, considering the recent popularity of open source projects aimed at standardizing different aspects of the data stack, we advocate for a paradigm shift in how data management systems are designed. We believe that by decomposing these into a modular stack of reusable components, development can be streamlined while creating a more consistent experience for users. Towards that goal, we describe the state-ofthe-art, principal open source technologies, and highlight open questions and areas where additional research is needed. We hope this work will foster collaboration, motivate further research, and promote a more composable future for data management.},
	language = {en},
	number = {10},
	urldate = {2023-12-27},
	journal = {Proceedings of the VLDB Endowment},
	author = {Pedreira, Pedro and Erling, Orri and Karanasos, Konstantinos and Schneider, Scott and McKinney, Wes and Valluri, Satya R and Zait, Mohamed and Nadeau, Jacques},
	month = jun,
	year = {2023},
	pages = {2679--2685},
	file = {Pedreira et al. - 2023 - The Composable Data Management System Manifesto.pdf:/Users/dkapitan/Zotero/storage/SVVTZQSR/Pedreira et al. - 2023 - The Composable Data Management System Manifesto.pdf:application/pdf},
}

@article{hai2023data,
	title = {Data {Lakes}: {A} {Survey} of {Functions} and {Systems}},
	volume = {35},
	issn = {1558-2191},
	shorttitle = {Data {Lakes}},
	url = {https://ieeexplore.ieee.org/abstract/document/10107808},
	doi = {10.1109/TKDE.2023.3270101},
	abstract = {Data lakes are becoming increasingly prevalent for Big Data management and data analytics. In contrast to traditional ‘schema-on-write’ approaches such as data warehouses, data lakes are repositories storing raw data in its original formats and providing a common access interface. Despite the strong interest raised from both academia and industry, there is a large body of ambiguity regarding the definition, functions and available technologies for data lakes. A complete, coherent picture of data lake challenges and solutions is still missing. This survey reviews the development, architectures, and systems of data lakes. We provide a comprehensive overview of research questions for designing and building data lakes. We classify the existing approaches and systems based on their provided functions for data lakes, which makes this survey a useful technical reference for designing, implementing and deploying data lakes. We hope that the thorough comparison of existing solutions and the discussion of open research challenges in this survey will motivate the future development of data lake research and practice.},
	number = {12},
	urldate = {2024-01-11},
	journal = {IEEE Transactions on Knowledge and Data Engineering},
	author = {Hai, Rihan and Koutras, Christos and Quix, Christoph and Jarke, Matthias},
	month = dec,
	year = {2023},
	note = {Conference Name: IEEE Transactions on Knowledge and Data Engineering},
	pages = {12571--12590},
	file = {IEEE Xplore Full Text PDF:/Users/dkapitan/Zotero/storage/R87AQA44/Hai et al. - 2023 - Data Lakes A Survey of Functions and Systems.pdf:application/pdf},
}

@incollection{curry2021reference,
	address = {Cham},
	title = {A {Reference} {Model} for {Big} {Data} {Technologies}},
	isbn = {978-3-030-68176-0},
	url = {https://doi.org/10.1007/978-3-030-68176-0_6},
	doi = {10.1007/978-3-030-68176-0_6},
	abstract = {The Big Data Value (BDV) Reference Model has been developed with input from technical experts and stakeholders along the whole big data value chain. The BDV Reference Model may serve as a common reference framework to locate big data technologies on the overall IT stack. It addresses the main technical concerns and aspects to be considered for big data value systems. The BDV Reference Model enables the mapping of existing and future data technologies within a common framework. Within this chapter, we detail the reference model in more detail and show how it can be used to manage a portfolio of research and innovation projects.},
	language = {en},
	urldate = {2024-01-11},
	booktitle = {The {Elements} of {Big} {Data} {Value}: {Foundations} of the {Research} and {Innovation} {Ecosystem}},
	publisher = {Springer International Publishing},
	author = {Curry, Edward and Metzger, Andreas and Berre, Arne J. and Monzón, Andrés and Boggio-Marzet, Alessandra},
	editor = {Curry, Edward and Metzger, Andreas and Zillner, Sonja and Pazzaglia, Jean-Christophe and García Robles, Ana},
	year = {2021},
	keywords = {Data management, Data protection, Data processing, Reference model, Big data technologies, Data analysis, Data visualisation},
	pages = {127--151},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/3HMH2BE9/Curry et al. - 2021 - A Reference Model for Big Data Technologies.pdf:application/pdf},
}

@misc{mazumdar2023data,
	title = {The {Data} {Lakehouse}: {Data} {Warehousing} and {More}},
	shorttitle = {The {Data} {Lakehouse}},
	url = {http://arxiv.org/abs/2310.08697},
	abstract = {Relational Database Management Systems designed for Online Analytical Processing (RDBMS-OLAP) have been foundational to democratizing data and enabling analytical use cases such as business intelligence and reporting for many years. However, RDBMS-OLAP systems present some well-known challenges. They are primarily optimized only for relational workloads, lead to proliferation of data copies which can become unmanageable, and since the data is stored in proprietary formats, it can lead to vendor lock-in, restricting access to engines, tools, and capabilities beyond what the vendor offers. As the demand for data-driven decision making surges, the need for a more robust data architecture to address these challenges becomes ever more critical. Cloud data lakes have addressed some of the shortcomings of RDBMS-OLAP systems, but they present their own set of challenges. More recently, organizations have often followed a two-tier architectural approach to take advantage of both these platforms, leveraging both cloud data lakes and RDBMS-OLAP systems. However, this approach brings additional challenges, complexities, and overhead. This paper discusses how a data lakehouse, a new architectural approach, achieves the same benefits of an RDBMS-OLAP and cloud data lake combined, while also providing additional advantages. We take today's data warehousing and break it down into implementation independent components, capabilities, and practices. We then take these aspects and show how a lakehouse architecture satisfies them. Then, we go a step further and discuss what additional capabilities and benefits a lakehouse architecture provides over an RDBMS-OLAP.},
	urldate = {2024-01-11},
	publisher = {arXiv},
	author = {Mazumdar, Dipankar and Hughes, Jason and Onofre, J. B.},
	month = oct,
	year = {2023},
	note = {arXiv:2310.08697 [cs]},
	keywords = {Computer Science - Databases},
	file = {arXiv.org Snapshot:/Users/dkapitan/Zotero/storage/AIKBHRKJ/2310.html:text/html;Full Text PDF:/Users/dkapitan/Zotero/storage/IV9Y5T4V/Mazumdar et al. - 2023 - The Data Lakehouse Data Warehousing and More.pdf:application/pdf},
}

@misc{openhie,
	title = {{OpenHIE} {Framework} v5.2-en},
	url = {https://ohie.org/},
	abstract = {OpenHIE is a community of individuals who strive to develop health information exchanges that improve patient care, health, and so much more.},
	language = {en-US},
	urldate = {2024-08-27},
	month = aug,
	year = {2024},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/55NPDMZ3/ohie.org.html:text/html},
}

@article{scheibner2021revolutionizing,
	title = {Revolutionizing {Medical} {Data} {Sharing} {Using} {Advanced} {Privacy}-{Enhancing} {Technologies}: {Technical}, {Legal}, and {Ethical} {Synthesis}},
	volume = {23},
	shorttitle = {Revolutionizing {Medical} {Data} {Sharing} {Using} {Advanced} {Privacy}-{Enhancing} {Technologies}},
	url = {https://www.jmir.org/2021/2/e25120},
	doi = {10.2196/25120},
	abstract = {Multisite medical data sharing is critical in modern clinical practice and medical research. The challenge is to conduct data sharing that preserves individual privacy and data utility. The shortcomings of traditional privacy-enhancing technologies mean that institutions rely upon bespoke data sharing contracts. The lengthy process and administration induced by these contracts increases the inefficiency of data sharing and may disincentivize important clinical treatment and medical research. 
This paper provides a synthesis between 2 novel advanced privacy-enhancing technologies—homomorphic encryption and secure multiparty computation (defined together as multiparty homomorphic encryption). These privacy-enhancing technologies provide a mathematical guarantee of privacy, with multiparty homomorphic encryption providing a performance advantage over separately using homomorphic encryption or secure multiparty computation. We argue multiparty homomorphic encryption fulfills legal requirements for medical data sharing under the European Union’s General Data Protection Regulation which has set a global benchmark for data protection. Specifically, the data processed and shared using multiparty homomorphic encryption can be considered anonymized data. We explain how multiparty homomorphic encryption can reduce the reliance upon customized contractual measures between institutions. The proposed approach can accelerate the pace of medical research while offering additional incentives for health care and research institutes to employ common data interoperability standards.},
	language = {EN},
	number = {2},
	urldate = {2024-02-05},
	journal = {Journal of Medical Internet Research},
	publisher = {JMIR Publications Inc., Toronto, Canada},
	author = {Scheibner, James and Raisaro, Jean Louis and Troncoso-Pastoriza, Juan Ramón and Ienca, Marcello and Fellay, Jacques and Vayena, Effy and Hubaux, Jean-Pierre},
	month = feb,
	year = {2021},
	note = {Company: Journal of Medical Internet Research
Distributor: Journal of Medical Internet Research
Institution: Journal of Medical Internet Research
Label: Journal of Medical Internet Research},
	pages = {e25120},
	file = {Full Text:/Users/dkapitan/Zotero/storage/TDJ64DAV/Scheibner et al. - 2021 - Revolutionizing Medical Data Sharing Using Advance.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/QNV7X8TJ/e25120.html:text/html},
}

@article{venable2016feds,
	title = {{FEDS}: a {Framework} for {Evaluation} in {Design} {Science} {Research}},
	volume = {25},
	issn = {1476-9344},
	shorttitle = {{FEDS}},
	url = {https://doi.org/10.1057/ejis.2014.36},
	doi = {10.1057/ejis.2014.36},
	abstract = {Evaluation of design artefacts and design theories is a key activity in Design Science Research (DSR), as it provides feedback for further development and (if done correctly) assures the rigour of the research. However, the extant DSR literature provides insufficient guidance on evaluation to enable Design Science Researchers to effectively design and incorporate evaluation activities into a DSR project that can achieve DSR goals and objectives. To address this research gap, this research paper develops, explicates, and provides evidence for the utility of a Framework for Evaluation in Design Science (FEDS) together with a process to guide design science researchers in developing a strategy for evaluating the artefacts they develop within a DSR project. A FEDS strategy considers why, when, how, and what to evaluate. FEDS includes a two-dimensional characterisation of DSR evaluation episodes (particular evaluations), with one dimension being the functional purpose of the evaluation (formative or summative) and the other dimension being the paradigm of the evaluation (artificial or naturalistic). The FEDS evaluation design process is comprised of four steps: (1) explicate the goals of the evaluation, (2) choose the evaluation strategy or strategies, (3) determine the properties to evaluate, and (4) design the individual evaluation episode(s). The paper illustrates the framework with two examples and provides evidence of its utility via a naturalistic, summative evaluation through its use on an actual DSR project.},
	language = {en},
	number = {1},
	urldate = {2024-02-07},
	journal = {European Journal of Information Systems},
	author = {Venable, John and Pries-Heje, Jan and Baskerville, Richard},
	month = jan,
	year = {2016},
	keywords = {research methodology, artefact evaluation, Design Science Research, information systems evaluation, research design, utility evaluation},
	pages = {77--89},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/C42M7QGN/Venable et al. - 2016 - FEDS a Framework for Evaluation in Design Science.pdf:application/pdf},
}

@article{mehl2023fullstac,
	title = {A full-{STAC} remedy for global digital health transformation: open standards, technologies, architectures and content},
	volume = {1},
	issn = {2754-4591},
	shorttitle = {A full-{STAC} remedy for global digital health transformation},
	url = {https://doi.org/10.1093/oodh/oqad018},
	doi = {10.1093/oodh/oqad018},
	abstract = {The global digital health ecosystem is project-centric: point solutions are developed for vertical health programs and financed through vertical funding allocations. This results in data fragmentation and technology lock-in, compromising health care delivery. A convergence of trends enabled by interoperability and digital governance makes possible a shift towards person-focused health. Together, open Standards, open Technologies, open Architectures and open Content represent a next-generation ‘full-STAC’ remedy for digital health transformation. Local developers and implementers can avoid reinventing the wheel, and instead build digital tools suited to local needs—where data travels with an individual over time, evidence-based practice is easily integrated, and insights are gleaned from harmonized data. This is the culmination of the vision endorsed by 194 WHO Member States in the Global Strategy on Digital Health 2020 to 2025.},
	urldate = {2024-02-09},
	journal = {Oxford Open Digital Health},
	author = {Mehl, Garrett L and Seneviratne, Martin G and Berg, Matt L and Bidani, Suhel and Distler, Rebecca L and Gorgens, Marelize and Kallander, Karin E and Labrique, Alain B and Landry, Mark S and Leitner, Carl and Lubell-Doughtie, Peter B and Marcelo, Alvin D and Matias, Yossi and Nelson, Jennifer and Nguyen, Von and Nsengimana, Jean Philbert and Orton, Maeghan and Otzoy Garcia, Daniel R and Oyaole, Daniel R and Ratanaprayul, Natschja and Roth, Susann and Schaefer, Merrick P and Settle, Dykki and Tang, Jing and Tien-Wahser, Barakissa and Wanyee, Steven and Hersch, Fred},
	month = jan,
	year = {2023},
	pages = {oqad018},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/4D3EIB6H/Mehl et al. - 2023 - A full-STAC remedy for global digital health trans.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/9ILKUCUU/7475299.html:text/html},
}

@article{cascini2024health,
	title = {Health data sharing attitudes towards primary and secondary use of data: a systematic review},
	volume = {71},
	issn = {2589-5370},
	shorttitle = {Health data sharing attitudes towards primary and secondary use of data},
	url = {https://www.sciencedirect.com/science/article/pii/S2589537024001305},
	doi = {10.1016/j.eclinm.2024.102551},
	abstract = {Background
To receive the best care, people share their health data (HD) with their health practitioners (known as sharing HD for primary purposes). However, during the past two decades, sharing for other (i.e., secondary) purposes has become of great importance in numerous fields, including public health, personalized medicine, research, and development. We aimed to conduct the first comprehensive overview of all studies that investigated people's HD sharing attitudes—along with associated barriers/motivators and significant influencing factors—for all data types and across both primary and secondary uses.
Methods
We searched PubMed, MEDLINE, PsycINFO, Web of Science, EMBASE, and CINAHL for relevant studies published in English between database inception and February 28, 2023, using a predefined set of keywords. Studies were included, regardless of their design, if they reported outcomes related to attitudes towards sharing HD. We extracted key data from the included studies, including the type of HD involved and findings related to: HD sharing attitudes (either in general or depending on type of data/user); barriers/motivators/benefits/concerns of the study participants; and sociodemographic and other variables that could impact HD sharing behaviour. The qualitative synthesis was conducted by dividing the studies according to the data type (resulting in five subgroups) as well as the purpose the data sharing was focused on (primary, secondary or both). The Newcastle–Ottawa Scale (NOS) was used to assess the quality of non-randomised studies. This work was registered with PROSPERO, CRD42023413822.
Findings
Of 2109 studies identified through our search, 116 were included in the qualitative synthesis, yielding a total of 228,501 participants and various types of HD represented: person-generated HD (n = 17 studies and 10,771 participants), personal HD in general (n = 69 studies and 117,054 participants), Biobank data (n = 7 studies and 27,073 participants), genomic data (n = 13 studies and 54,716 participants), and miscellaneous data (n = 10 studies and 18,887 participants). The majority of studies had a moderate level of quality (83 [71.6\%] of 116 studies), but varying levels of quality were observed across the included studies. Overall, studies suggest that sharing intentions for primary purposes were observed to be high regardless of data type, and it was higher than sharing intentions for secondary purposes. Sharing for secondary purposes yielded variable findings, where both the highest and the lowest intention rates were observed in the case of studies that explored sharing biobank data (98\% and 10\%, respectively). Several influencing factors on sharing intentions were identified, such as the type of data recipient, data, consent. Further, concerns related to data sharing that were found to be mutual for all data types included privacy, security, and data access/control, while the perceived benefits included those related to improvements in healthcare. Findings regarding attitudes towards sharing varied significantly across sociodemographic factors and depended on data type and type of use. In most cases, these findings were derived from single studies and therefore warrant confirmations from additional studies.
Interpretation
Sharing health data is a complex issue that is influenced by various factors (the type of health data, the intended use, the data recipient, among others) and these insights could be used to overcome barriers, address people's concerns, and focus on spreading awareness about the data sharing process and benefits.
Funding
None.},
	urldate = {2024-03-21},
	journal = {eClinicalMedicine},
	author = {Cascini, Fidelia and Pantovic, Ana and Al-Ajlouni, Yazan A. and Puleo, Valeria and De Maio, Lucia and Ricciardi, Walter},
	month = may,
	year = {2024},
	keywords = {Data sharing, Biobank, Genomic data, Person-generated data, Personal health data, Secondary use},
	pages = {102551},
	file = {cascini2024health.pdf:/Users/dkapitan/Zotero/storage/VILMTDEP/cascini2024health.pdf:application/pdf;ScienceDirect Snapshot:/Users/dkapitan/Zotero/storage/2CFANZZK/S2589537024001305.html:text/html},
}

@article{abbas2021business,
	title = {Business {Data} {Sharing} through {Data} {Marketplaces}: {A} {Systematic} {Literature} {Review}},
	shorttitle = {Business {Data} {Sharing} through {Data} {Marketplaces}},
	url = {https://aisel.aisnet.org/bled2021/13},
	journal = {BLED 2021 Proceedings},
	author = {Abbas, Antragama Ewa and Agahari, Wirawan and Ven, Montijn van de and Zuiderwijk, Anneke and Reuver, Mark de},
	month = jan,
	year = {2021},
	file = {"Business Data Sharing through Data Marketplaces\: A Systematic Literatu" by Antragama Ewa Abbas, Wirawan Agahari et al.:/Users/dkapitan/Zotero/storage/NS4TWGF4/13.html:text/html},
}

@article{sein2011action,
	title = {Action {Design} {Research}},
	volume = {35},
	doi = {10.2307/23043488},
	abstract = {Design research (DR) positions information technology artifacts at the core of the Information Systems discipline. However, dominant DR thinking takes a technological view of the IT artifact, paying scant attention to its shaping by the organizational context. Consequently, existing DR methods focus on building the artifact and relegate evaluation to a subsequent and separate phase. They value technological rigor at the cost of organizational relevance, and fail to recognize that the artifact emerges from interaction with the organizational context even when its initial design is guided by the researchers' intent. We propose action design research (ADR) as a new DR method to address this problem. ADR reflects the premise that IT artifacts are ensembles shaped by the organizational context during development and use. The method conceptualizes the research process as containing the inseparable and inherently interwoven activities of building the IT artifact, intervening in the organization, and evaluating it concurrently. The essay describes the stages of ADR and associated principles that encapsulate its underlying beliefs and values. We illustrate ADR through a case of competence management at Volvo IT.},
	journal = {MIS Quarterly},
	author = {Sein, Maung and Henfridsson, Ola and Purao, Sandeep and Rossi, Matti and Lindgren, Rikard},
	month = mar,
	year = {2011},
	pages = {37--56},
	file = {Sein-ActionDesignResearch-2011:/Users/dkapitan/Zotero/storage/GUUY9RV9/Sein-ActionDesignResearch-2011.pdf:application/pdf},
}

@article{gruendner2022architecture,
	title = {The {Architecture} of a {Feasibility} {Query} {Portal} for {Distributed} {COVID}-19 {Fast} {Healthcare} {Interoperability} {Resources} ({FHIR}) {Patient} {Data} {Repositories}: {Design} and {Implementation} {Study}},
	volume = {10},
	copyright = {This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published JMIR Medical Informatics, is properly cited. The complete bibliographic information, a link to the original publication on https://medinform.jmir.org/, as well as this copyright and license information must be included.},
	shorttitle = {The {Architecture} of a {Feasibility} {Query} {Portal} for {Distributed} {COVID}-19 {Fast} {Healthcare} {Interoperability} {Resources} ({FHIR}) {Patient} {Data} {Repositories}},
	url = {https://medinform.jmir.org/2022/5/e36709},
	doi = {10.2196/36709},
	abstract = {Background: An essential step in any medical research project after identifying the research question is to determine if there are sufficient patients available for a study and where to find them. Pursuing digital feasibility queries on available patient data registries has proven to be an excellent way of reusing existing real-world data sources. To support multicentric research, these feasibility queries should be designed and implemented to run across multiple sites and securely access local data. Working across hospitals usually involves working with different data formats and vocabularies. Recently, the Fast Healthcare Interoperability Resources (FHIR) standard was developed by Health Level Seven to address this concern and describe patient data in a standardized format. The Medical Informatics Initiative in Germany has committed to this standard and created data integration centers, which convert existing data into the FHIR format at each hospital. This partially solves the interoperability problem; however, a distributed feasibility query platform for the FHIR standard is still missing.
Objective: This study described the design and implementation of the components involved in creating a cross-hospital feasibility query platform for researchers based on FHIR resources. This effort was part of a large COVID-19 data exchange platform and was designed to be scalable for a broad range of patient data.
Methods: We analyzed and designed the abstract components necessary for a distributed feasibility query. This included a user interface for creating the query, backend with an ontology and terminology service, middleware for query distribution, and FHIR feasibility query execution service.
Results: We implemented the components described in the Methods section. The resulting solution was distributed to 33 German university hospitals. The functionality of the comprehensive network infrastructure was demonstrated using a test data set based on the German Corona Consensus Data Set. A performance test using specifically created synthetic data revealed the applicability of our solution to data sets containing millions of FHIR resources. The solution can be easily deployed across hospitals and supports feasibility queries, combining multiple inclusion and exclusion criteria using standard Health Level Seven query languages such as Clinical Quality Language and FHIR Search. Developing a platform based on multiple microservices allowed us to create an extendable platform and support multiple Health Level Seven query languages and middleware components to allow integration with future directions of the Medical Informatics Initiative.
Conclusions: We designed and implemented a feasibility platform for distributed feasibility queries, which works directly on FHIR-formatted data and distributed it across 33 university hospitals in Germany. We showed that developing a feasibility platform directly on the FHIR standard is feasible.},
	language = {EN},
	number = {5},
	urldate = {2024-05-27},
	journal = {JMIR Medical Informatics},
	publisher = {JMIR Publications Inc., Toronto, Canada},
	author = {Gruendner, Julian and Deppenwiese, Noemi and Folz, Michael and Köhler, Thomas and Kroll, Björn and Prokosch, Hans-Ulrich and Rosenau, Lorenz and Rühle, Mathias and Scheidl, Marc-Anton and Schüttler, Christina and Sedlmayr, Brita and Twrdik, Alexander and Kiel, Alexander and Majeed, Raphael W.},
	month = may,
	year = {2022},
	note = {Company: JMIR Medical Informatics
Distributor: JMIR Medical Informatics
Institution: JMIR Medical Informatics
Label: JMIR Medical Informatics},
	pages = {e36709},
	file = {Full Text:/Users/dkapitan/Zotero/storage/JWTLQ68A/Gruendner et al. - 2022 - The Architecture of a Feasibility Query Portal for.pdf:application/pdf},
}

@article{bergman2022business,
	title = {Business model archetypes for data marketplaces in the automotive industry},
	volume = {32},
	issn = {1422-8890},
	url = {https://doi.org/10.1007/s12525-022-00547-x},
	doi = {10.1007/s12525-022-00547-x},
	abstract = {Policymakers and analysts are heavily promoting data marketplaces to foster data trading between companies. Existing business model literature covers individually owned, multilateral data marketplaces. However, these particular types of data marketplaces hardly reach commercial exploitation. This paper develops business model archetypes for the full array of data marketplace types, ranging from private to independent ownership and from a hierarchical to a market orientation. Through exploratory interviews and case analyses, we create a business model taxonomy. Patterns in our taxonomy reveal four business model archetypes. We find that privately-owned data marketplaces with hierarchical orientation apply the aggregating data marketplace archetype. Consortium-owned data marketplaces apply the archetypes of aggregating data marketplace with additional brokering service and consulting data marketplace. Independently owned data marketplaces with market orientation apply the facilitating data marketplace archetype. Our results provide a basis for configurational theory that explains the performance of data marketplace business models. Our results also provide a basis for specifying boundary conditions for theory on data marketplace business models, as, for instance, the importance of network effects differs strongly between the archetypes.},
	language = {en},
	number = {2},
	urldate = {2024-05-27},
	journal = {Electronic Markets},
	author = {Bergman, Rômy and Abbas, Antragama Ewa and Jung, Sven and Werker, Claudia and de Reuver, Mark},
	month = jun,
	year = {2022},
	keywords = {L10, L22, L86, L89, Z00},
	pages = {747--765},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/ID3JBSXD/Bergman et al. - 2022 - Business model archetypes for data marketplaces in.pdf:application/pdf},
}

@article{demast2022analytical,
	title = {Analytical {Problem} {Solving} {Based} on {Causal}, {Correlational} and {Deductive} {Models}},
	issn = {0003-1305},
	url = {https://doi.org/10.1080/00031305.2021.2023633},
	doi = {10.1080/00031305.2021.2023633},
	journal = {The American Statistician},
	publisher = {Taylor \& Francis},
	author = {de Mast, Jeroen and Steiner, Stefan H. and Nuijten, Wim P. M. and Kapitan, Daniel},
	month = jan,
	year = {2022},
	keywords = {Machine learning, Business analytics, Causal inference, Operations research, Predictive modeling, Prescriptive analytics, Problem solving},
	pages = {1--11},
	file = {00031305.2021:/Users/dkapitan/Zotero/storage/QKE3R3BT/00031305.2021.html:text/html;de Mast et al. - 2022 - Analytical Problem Solving Based on Causal, Correl.pdf:/Users/dkapitan/Zotero/storage/WBL5J2BZ/de Mast et al. - 2022 - Analytical Problem Solving Based on Causal, Correl.pdf:application/pdf;de Mast et al. - 2022 - Analytical Problem Solving Based on Causal, Correl.pdf:/Users/dkapitan/Zotero/storage/TSQD6J5V/de Mast et al. - 2022 - Analytical Problem Solving Based on Causal, Correl.pdf:application/pdf},
}

@article{teo2024federateda,
	title = {Federated machine learning in healthcare: {A} systematic review on clinical applications and technical architecture},
	volume = {5},
	issn = {26663791},
	shorttitle = {Federated machine learning in healthcare},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2666379124000429},
	doi = {10.1016/j.xcrm.2024.101419},
	abstract = {Federated learning (FL) is a distributed machine learning framework that is gaining traction in view of increasing health data privacy protection needs. By conducting a systematic review of FL applications in healthcare, we identify relevant articles in scientific, engineering, and medical journals in English up to August 31st, 2023. Out of a total of 22,693 articles under review, 612 articles are included in the final analysis. The majority of articles are proof-of-concepts studies, and only 5.2\% are studies with real-life application of FL. Radiology and internal medicine are the most common specialties involved in FL. FL is robust to a variety of machine learning models and data types, with neural networks and medical imaging being the most common, respectively. We highlight the need to address the barriers to clinical translation and to assess its realworld impact in this new digital data-driven healthcare scene.},
	language = {en},
	number = {2},
	urldate = {2024-06-03},
	journal = {Cell Reports Medicine},
	author = {Teo, Zhen Ling and Jin, Liyuan and Liu, Nan and Li, Siqi and Miao, Di and Zhang, Xiaoman and Ng, Wei Yan and Tan, Ting Fang and Lee, Deborah Meixuan and Chua, Kai Jie and Heng, John and Liu, Yong and Goh, Rick Siow Mong and Ting, Daniel Shu Wei},
	month = feb,
	year = {2024},
	pages = {101419},
	file = {Teo et al. - 2024 - Federated machine learning in healthcare A system.pdf:/Users/dkapitan/Zotero/storage/84BC73II/Teo et al. - 2024 - Federated machine learning in healthcare A system.pdf:application/pdf},
}

@article{agahari2022it,
	title = {It is not (only) about privacy: {How} multi-party computation redefines control, trust, and risk in data sharing},
	issn = {1422-8890},
	shorttitle = {It is not (only) about privacy},
	url = {https://doi.org/10.1007/s12525-022-00572-w},
	doi = {10.1007/s12525-022-00572-w},
	abstract = {Firms are often reluctant to share data because of mistrust, concerns over control, and other risks. Multi-party computation (MPC) is a new technique to compute meaningful insights without having to transfer data. This paper investigates if MPC affects known antecedents for data sharing decisions: control, trust, and risks. Through 23 qualitative interviews in the automotive industry, we find that MPC (1) enables new ways of technology-based control, (2) reduces the need for inter-organizational trust, and (3) prevents losing competitive advantage due to data leakage. However, MPC also creates the need to trust technology and introduces new risks of data misuse. These impacts arise if firms perceive benefits from sharing data, have high organizational readiness, and perceive data as non-sensitive. Our findings show that known antecedents of data sharing should be specified differently with MPC in place. Furthermore, we suggest reframing MPC as a data collaboration technology beyond enhancing privacy.},
	language = {en},
	urldate = {2022-08-01},
	journal = {Electronic Markets},
	author = {Agahari, Wirawan and Ofe, Hosea and de Reuver, Mark},
	month = jul,
	year = {2022},
	keywords = {L86, Control, Data sharing, Multi-party computation, Privacy-enhancing technology, Risk, Trust},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/UEAXXGDX/Agahari et al. - 2022 - It is not (only) about privacy How multi-party co.pdf:application/pdf},
}

@misc{federatedb,
	title = {A federated architecture for information management {\textbar} {ACM} {Transactions} on {Information} {Systems}},
	url = {https://dl-acm-org.dianus.libr.tue.nl/doi/abs/10.1145/4229.4233},
	urldate = {2024-05-11},
	file = {A federated architecture for information management | ACM Transactions on Information Systems:/Users/dkapitan/Zotero/storage/WW7Q7XHC/4229.html:text/html},
}

@article{busse1999federated,
	title = {Federated {Information} {Systems}: {Concepts}, {Terminology} and {Architectures}},
	abstract = {We are currently witnessing the emerging of a new generation of software systems: Federated information systems. Their main characteristic is that they are constructed as an integrating layer over existing legacy applications and databases. They can be broadly classified in three dimensions: the degree of autonomy they allow in integrated components, the degree of heterogeneity between components they can cope with, and whether or not they support distribution. Whereas the communication and interoperation problem has come into a stage of applicable solutions over the past decade, semantic data integration has not become similarly clear.},
	language = {en},
	author = {Busse, Susanne and Kutsche, Ralf-Detlef and Leser, Ulf and Weber, Herbert},
	year = {1999},
	file = {Busse et al. - 1999 - Federated Information Systems Concepts, Terminolo.pdf:/Users/dkapitan/Zotero/storage/BP4Z3V7K/Busse et al. - 1999 - Federated Information Systems Concepts, Terminolo.pdf:application/pdf},
}

@misc{konecny2016federated,
	title = {Federated {Optimization}: {Distributed} {Machine} {Learning} for {On}-{Device} {Intelligence}},
	shorttitle = {Federated {Optimization}},
	url = {http://arxiv.org/abs/1610.02527},
	doi = {10.48550/arXiv.1610.02527},
	abstract = {We introduce a new and increasingly relevant setting for distributed optimization in machine learning, where the data defining the optimization are unevenly distributed over an extremely large number of nodes. The goal is to train a high-quality centralized model. We refer to this setting as Federated Optimization. In this setting, communication efficiency is of the utmost importance and minimizing the number of rounds of communication is the principal goal. A motivating example arises when we keep the training data locally on users' mobile devices instead of logging it to a data center for training. In federated optimziation, the devices are used as compute nodes performing computation on their local data in order to update a global model. We suppose that we have extremely large number of devices in the network --- as many as the number of users of a given service, each of which has only a tiny fraction of the total data available. In particular, we expect the number of data points available locally to be much smaller than the number of devices. Additionally, since different users generate data with different patterns, it is reasonable to assume that no device has a representative sample of the overall distribution. We show that existing algorithms are not suitable for this setting, and propose a new algorithm which shows encouraging experimental results for sparse convex problems. This work also sets a path for future research needed in the context of {\textbackslash}federated optimization.},
	urldate = {2024-05-12},
	publisher = {arXiv},
	author = {Konečný, Jakub and McMahan, H. Brendan and Ramage, Daniel and Richtárik, Peter},
	month = oct,
	year = {2016},
	note = {arXiv:1610.02527 [cs]
version: 1},
	keywords = {Computer Science - Machine Learning},
	file = {arXiv Fulltext PDF:/Users/dkapitan/Zotero/storage/Z7TITNAI/Konečný et al. - 2016 - Federated Optimization Distributed Machine Learni.pdf:application/pdf;arXiv.org Snapshot:/Users/dkapitan/Zotero/storage/A77M3B4W/1610.html:text/html},
}

@article{pillutla2022robust,
	title = {Robust {Aggregation} for {Federated} {Learning}},
	volume = {70},
	issn = {1053-587X, 1941-0476},
	url = {http://arxiv.org/abs/1912.13445},
	doi = {10.1109/TSP.2022.3153135},
	abstract = {Federated learning is the centralized training of statistical models from decentralized data on mobile devices while preserving the privacy of each device. We present a robust aggregation approach to make federated learning robust to settings when a fraction of the devices may be sending corrupted updates to the server. The approach relies on a robust aggregation oracle based on the geometric median, which returns a robust aggregate using a constant number of iterations of a regular non-robust averaging oracle. The robust aggregation oracle is privacy-preserving, similar to the non-robust secure average oracle it builds upon. We establish its convergence for least squares estimation of additive models. We provide experimental results with linear models and deep networks for three tasks in computer vision and natural language processing. The robust aggregation approach is agnostic to the level of corruption; it outperforms the classical aggregation approach in terms of robustness when the level of corruption is high, while being competitive in the regime of low corruption. Two variants, a faster one with one-step robust aggregation and another one with on-device personalization, round off the paper.},
	language = {en},
	urldate = {2024-05-13},
	journal = {IEEE Transactions on Signal Processing},
	author = {Pillutla, Krishna and Kakade, Sham M. and Harchaoui, Zaid},
	year = {2022},
	note = {arXiv:1912.13445 [cs, stat]},
	keywords = {Computer Science - Machine Learning, Statistics - Machine Learning, Computer Science - Cryptography and Security},
	pages = {1142--1154},
	file = {Pillutla et al. - 2022 - Robust Aggregation for Federated Learning.pdf:/Users/dkapitan/Zotero/storage/HUXQ7Z9V/Pillutla et al. - 2022 - Robust Aggregation for Federated Learning.pdf:application/pdf},
}

@article{jahnke2024federated,
	title = {Federated data catalogs for data sharing - towards design principles},
	url = {https://aisel.aisnet.org/ecis2024/track23_designresearch/track23_designresearch/10},
	journal = {ECIS 2024 Proceedings},
	author = {Jahnke, Nils and Spiekermann, Markus and Möller, Frederik},
	month = jun,
	year = {2024},
	file = {AIS Electronic Library (AISeL) - ECIS 2024 Proceedings\: FEDERATED DATA CATALOGS FOR DATA SHARING – TOWARDS DESIGN PRINCIPLES:/Users/dkapitan/Zotero/storage/F6HHTGEN/10.html:text/html},
}

@article{sheth1990federated,
	title = {Federated database systems for managing distributed, heterogeneous, and autonomous databases},
	volume = {22},
	issn = {0360-0300, 1557-7341},
	url = {https://dl.acm.org/doi/10.1145/96602.96604},
	doi = {10.1145/96602.96604},
	abstract = {A federated database system (FDBS) is a collection of cooperating database systems that are autonomous and possibly heterogeneous. In this paper, we define a reference architecture for distributed database management systems from system and schema viewpoints and show how various FDBS architectures can be developed. We then define a methodology for developing one of the popular architectures of an FDBS. Finally, we discuss critical issues related to developing and operating an FDBS.},
	language = {en},
	number = {3},
	urldate = {2024-05-13},
	journal = {ACM Computing Surveys},
	author = {Sheth, Amit P. and Larson, James A.},
	month = sep,
	year = {1990},
	pages = {183--236},
	file = {Available Version (via Google Scholar):/Users/dkapitan/Zotero/storage/C8VUQ6CY/Sheth and Larson - 1990 - Federated database systems for managing distribute.pdf:application/pdf},
}

@article{nargesian2019data,
	title = {Data lake management: challenges and opportunities},
	volume = {12},
	issn = {2150-8097},
	shorttitle = {Data lake management},
	url = {https://dl.acm.org/doi/10.14778/3352063.3352116},
	doi = {10.14778/3352063.3352116},
	abstract = {The ubiquity of data lakes has created fascinating new challenges for data management research. In this tutorial, we review the state-of-the-art in data management for data lakes. We consider how data lakes are introducing new problems including dataset discovery and how they are changing the requirements for classic problems including data extraction, data cleaning, data integration, data versioning, and metadata management.},
	language = {en},
	number = {12},
	urldate = {2024-05-13},
	journal = {Proceedings of the VLDB Endowment},
	author = {Nargesian, Fatemeh and Zhu, Erkang and Miller, Renée J. and Pu, Ken Q. and Arocena, Patricia C.},
	month = aug,
	year = {2019},
	pages = {1986--1989},
	file = {Available Version (via Google Scholar):/Users/dkapitan/Zotero/storage/NRHA4TPV/Nargesian et al. - 2019 - Data lake management challenges and opportunities.pdf:application/pdf},
}

@incollection{sheth1999changing,
	address = {Boston, MA},
	title = {Changing {Focus} on {Interoperability} in {Information} {Systems}:{From} {System}, {Syntax}, {Structure} to {Semantics}},
	isbn = {978-1-4613-7363-6 978-1-4615-5189-8},
	shorttitle = {Changing {Focus} on {Interoperability} in {Information} {Systems}},
	url = {http://link.springer.com/10.1007/978-1-4615-5189-8_2},
	doi = {10.1007/978-1-4615-5189-8_2},
	urldate = {2024-05-13},
	booktitle = {Interoperating {Geographic} {Information} {Systems}},
	publisher = {Springer US},
	author = {Sheth, Amit P.},
	editor = {Goodchild, Michael and Egenhofer, Max and Fegeas, Robin and Kottman, Cliff},
	year = {1999},
	pages = {5--29},
	file = {Available Version (via Google Scholar):/Users/dkapitan/Zotero/storage/4376HL56/Sheth - 1999 - Changing Focus on Interoperability in Information .pdf:application/pdf},
}

@article{mahon2024federated,
	title = {A federated learning system for precision oncology in {Europe}: {DigiONE}},
	volume = {30},
	issn = {1078-8956, 1546-170X},
	shorttitle = {A federated learning system for precision oncology in {Europe}},
	url = {https://www.nature.com/articles/s41591-023-02715-8},
	doi = {10.1038/s41591-023-02715-8},
	language = {en},
	number = {2},
	urldate = {2024-05-27},
	journal = {Nature Medicine},
	author = {Mahon, Piers and Chatzitheofilou, Ismini and Dekker, Andre and Fernández, Xosé and Hall, Geoff and Helland, Aslaug and Traverso, Alberto and Van Marcke, Cedric and Vehreschild, Janne and Ciliberto, Gennaro and Tonon, Giovanni},
	month = feb,
	year = {2024},
	pages = {334--337},
	file = {Mahon et al. - 2024 - A federated learning system for precision oncology.pdf:/Users/dkapitan/Zotero/storage/DR3TJKV6/Mahon et al. - 2024 - A federated learning system for precision oncology.pdf:application/pdf},
}

@article{agahari2022rethinking,
	title = {Rethinking consumers' data sharing decisions with the emergence of multi-party computation: {An} experimental design for evaluation},
	shorttitle = {Rethinking consumers' data sharing decisions with the emergence of multi-party computation},
	url = {https://repository.tudelft.nl/islandora/object/uuid%3A624e946c-7a14-468e-8b48-f6d2cd7f16c4},
	abstract = {Consumers are increasingly reluctant to share their personal data with businesses due to mounting concerns over privacy and control. Emerging privacy-enhancing technologies like multi-party computation (MPC), which allows generating insights while consumers retain data control, are challenging the current understanding of why consumers share their data. In this research-in-progress paper, we develop and evaluate an instrument and experimental design to investigate the impact of MPC on consumers’ willingness to share data and its antecedents. Preliminary analysis from a pre-study (N=300) indicates a good fit for our model. Also, MPC enhances consumers’ control and trust while reducing privacy concerns and risk, ultimately increasing data sharing willingness. The findings suggest that privacy-enhancing technologies significantly affect both the willingness to share data itself and its typical antecedents. The next step will conduct a large-scale online experiment using the developed instruments to evaluate further the impact of MPC on consumers’ willingness to share data.},
	language = {en},
	urldate = {2024-06-05},
	journal = {30th European Conference on Information Systems (ECIS 2022)},
	publisher = {Association of the Information Systems (AIS)},
	author = {Agahari, W. and de Reuver, Mark},
	year = {2022},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/QQVNV9TN/Agahari and de Reuver - 2022 - Rethinking consumers' data sharing decisions with .pdf:application/pdf},
}

@phdthesis{agahari2023multiparty,
	type = {Dissertation ({TU} {Delft})},
	title = {Multi-{Party} {Computation} as a {Privacy}-{Enhancing} {Technology}: {Implications} for {Data} {Sharing} by {Businesses} and {Consumers}},
	isbn = {978-94-6384-480-2},
	shorttitle = {Multi-{Party} {Computation} as a {Privacy}-{Enhancing} {Technology}},
	abstract = {Data sharing through data marketplaces, which rely on a Trusted Third Party (TTP), can benefit businesses and society. However, many companies and consumers are increasingly reluctant to share data due to mounting concerns over data control and privacy. Emerging privacy-enhancing technologies (PETs) like Multi-Party Computation (MPC), which enables joint computation to generate insights while keeping the input data private, could address data sharing barriers due to its differences with the traditional data sharing approach relying on a TTP. Thus, MPC could challenge the current understanding of why and how businesses and consumers share data. Nevertheless, whether businesses and consumers would be more willing to share data with MPC in place is unclear, as less attention is given to the socio-technical implications of MPC on data sharing decisions in data marketplaces and its antecedents. This research aimed to theorize the socio-technical implications of MPC on sharing through data marketplaces, by investigating how MPC potentially impacts data sharing antecedents by businesses and individuals. We do so through a mixed-method research design focusing on the automotive industry. Based on interviews with 15 MPC experts, which were structured using a Unified Business Model framework, we explored value propositions enabled by MPC use in data marketplaces. These value propositions allow MPC to potentially impact control, privacy, trust, and risks as antecedents of data sharing decisions in data marketplaces. Subsequently, we interviewed 23 automotive industry experts to investigate the potential impact of MPC use in data marketplaces on control, trust, and risks as antecedents of business data sharing. We then conducted an experiment via an online crowdsourcing platform with 1457 participants to investigate the potential impact of MPC use in data marketplaces on control, privacy, trust, and risks as antecedents of consumer data sharing. In this way, we contribute to the socio-technical understanding of MPC beyond technical perspectives. At the same time, we also demonstrate the relevance of MPC to practitioners by pointing out key aspects that should be considered while exploring the possibility of implementing MPC. Furthermore, this research provides a foundation for future studies on understanding the socio-technical implications of MPC on data sharing decisions.},
	author = {Agahari, W.},
	year = {2023},
	doi = {10.4233/uuid:83e0a9bc-f429-479a-ac2b-8a42e6da63f1},
	keywords = {data sharing, automotive industry, data marketplaces, mixed-method research, Multi-Party Computation, privacy-enhancing technologies},
}

@article{sun2021systematic,
	title = {A systematic review on privacy-preserving distributed data mining},
	volume = {4},
	issn = {2451-8484},
	url = {https://content.iospress.com/articles/data-science/ds210036},
	doi = {10.3233/DS-210036},
	abstract = {Combining and analysing sensitive data from multiple sources offers considerable potential for knowledge discovery. However, there are a number of issues that pose problems for such analyses, including technical barriers, privacy restrictions, securi},
	language = {en},
	number = {2},
	urldate = {2024-06-10},
	journal = {Data Science},
	publisher = {IOS Press},
	author = {Sun, Chang and Ippel, Lianne and Dekker, Andre and Dumontier, Michel and van Soest, Johan},
	month = jan,
	year = {2021},
	pages = {121--150},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/KSWLZZ5I/Sun et al. - 2021 - A systematic review on privacy-preserving distribu.pdf:application/pdf},
}

@article{kaheman2020sindypi,
	title = {{SINDy}-{PI}: a robust algorithm for parallel implicit sparse identification of nonlinear dynamics},
	volume = {476},
	shorttitle = {{SINDy}-{PI}},
	url = {https://royalsocietypublishing.org/doi/10.1098/rspa.2020.0279},
	doi = {10.1098/rspa.2020.0279},
	abstract = {Accurately modelling the nonlinear dynamics of a system from measurement data is a challenging yet vital topic. The sparse identification of nonlinear dynamics (SINDy) algorithm is one approach to discover dynamical systems models from data. Although extensions have been developed to identify implicit dynamics, or dynamics described by rational functions, these extensions are extremely sensitive to noise. In this work, we develop SINDy-PI (parallel, implicit), a robust variant of the SINDy algorithm to identify implicit dynamics and rational nonlinearities. The SINDy-PI framework includes multiple optimization algorithms and a principled approach to model selection. We demonstrate the ability of this algorithm to learn implicit ordinary and partial differential equations and conservation laws from limited and noisy data. In particular, we show that the proposed approach is several orders of magnitude more noise robust than previous approaches, and may be used to identify a class of ODE and PDE dynamics that were previously unattainable with SINDy, including for the double pendulum dynamics and simplified model for the Belousov–Zhabotinsky (BZ) reaction.},
	number = {2242},
	urldate = {2022-11-07},
	journal = {Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences},
	publisher = {Royal Society},
	author = {Kaheman, Kadierdan and Kutz, J. Nathan and Brunton, Steven L.},
	month = oct,
	year = {2020},
	keywords = {optimization, model selection, rational differential equations, system identification},
	pages = {20200279},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/GIPCGV4J/Kaheman et al. - 2020 - SINDy-PI a robust algorithm for parallel implicit.pdf:application/pdf},
}

@article{ottofederated,
	title = {A {Federated} {Infrastructure} for {European} {Data} {Spaces}},
	url = {https://cacm.acm.org/magazines/2022/4/259403-a-federated-infrastructure-for-european-data-spaces/fulltext},
	abstract = {The Gaia-X project, with more than 300 members, aims at a federated data architecture that comprises not only data and smart services, but also cloud infrastructure services.},
	language = {en},
	urldate = {2022-11-04},
	author = {Otto, Boris},
	file = {PDF:/Users/dkapitan/Zotero/storage/Z2EIQNRJ/Otto - A Federated Infrastructure for European Data Spaces.pdf:application/pdf},
}

@misc{privacy,
	title = {Privacy {Is} {Hard} and {Seven} {Other} {Myths}},
	url = {https://mitpress.mit.edu/9780262045827/},
	urldate = {2022-11-03},
}

@article{hoepman2018privacy,
	title = {Privacy {Design} {Strategies}},
	abstract = {Limit as much as possible the detail in which personal data is processed. Hide Protect personal data, or make it unlinkable or unobservable. Make sure it does not become public or known.},
	language = {en},
	author = {Hoepman, Jaap-Henk},
	year = {2018},
	pages = {30},
	file = {Hoepman - This work is licensed under a Creative Commons Att.pdf:/Users/dkapitan/Zotero/storage/PBL9NFW4/Hoepman - This work is licensed under a Creative Commons Att.pdf:application/pdf;hoepman2018pds-boekje.pdf:/Users/dkapitan/Zotero/storage/GEGAW3LB/hoepman2018pds-boekje.pdf:application/pdf},
}

@article{abspoel2021secure,
	title = {Secure training of decision trees with continuous attributes},
	volume = {2021},
	issn = {2299-0984},
	url = {https://petsymposium.org/popets/2021/popets-2021-0010.php},
	doi = {10.2478/popets-2021-0010},
	abstract = {We apply multiparty computation (MPC) techniques to show, given a database that is secret-shared among multiple mutually distrustful parties, how the parties may obliviously construct a decision tree based on the secret data. We consider data with continuous attributes (i.e., coming from a large domain), and develop a secure version of a learning algorithm similar to the C4.5 or CART algorithms. Previous MPC-based work only focused on decision tree learning with discrete attributes (De Hoogh et al. 2014). Our starting point is to apply an existing generic MPC protocol to a standard decision tree learning algorithm, which we then optimize in several ways. We exploit the fact that even if we allow the data to have continuous values, which a priori might require fixed or floating point representations, the output of the tree learning algorithm only depends on the relative ordering of the data. By obliviously sorting the data we reduce the number of comparisons needed per node to O(N log2 N ) from the naive O(N 2), where N is the number of training records in the dataset, thus making the algorithm feasible for larger datasets. This does however introduce a problem when duplicate values occur in the dataset, but we manage to overcome this problem with a relatively cheap subprotocol. We show a procedure to convert a sorting network into a permutation network of smaller complexity, resulting in a round complexity of O(log N ) per layer in the tree. We implement our algorithm in the MP-SPDZ framework and benchmark our implementation for both passive and active three-party computation using arithmetic modulo 264. We apply our implementation to a large scale medical dataset of ≈ 290 000 rows using random forests, and thus demonstrate practical feasibility of using MPC for privacy-preserving machine learning based on decision trees for large datasets.},
	language = {en},
	number = {1},
	urldate = {2022-10-21},
	journal = {Proceedings on Privacy Enhancing Technologies},
	author = {Abspoel, Mark and Escudero, Daniel and Volgushev, Nikolaj},
	month = jan,
	year = {2021},
	pages = {167--187},
	file = {Abspoel et al. - 2021 - Secure training of decision trees with continuous .pdf:/Users/dkapitan/Zotero/storage/8PEDIV8X/Abspoel et al. - 2021 - Secure training of decision trees with continuous .pdf:application/pdf},
}

@article{sweeneyKANONYMITYMODELPROTECTING2002,
	title = {K-{ANONYMITY}: {A} {MODEL} {FOR} {PROTECTING} {PRIVACY}},
	volume = {10},
	issn = {0218-4885},
	shorttitle = {K-{ANONYMITY}},
	doi = {10.1142/S0218488502001648},
	abstract = {Consider a data holder, such as a hospital or a bank, that has a privately held collection of person-specific, field structured data. Suppose the data holder wants to share a version of the data with researchers. How can a data holder release a version of its private data with scientific guarantees that the individuals who are the subjects of the data cannot be re-identified while the data remain practically useful? The solution provided in this paper includes a formal protection model named k-anonymity and a set of accompanying policies for deployment. A release provides k-anonymity protection if the information for each person contained in the release cannot be distinguished from at least k-1 individuals whose information also appears in the release. This paper also examines re-identification attacks that can be realized on releases that adhere to k-anonymity unless accompanying policies are respected. The k-anonymity protection model is important because it forms the basis on which the real-world systems known as Datafly, 𝜇-Argus and k-Similar provide guarantees of privacy protection.},
	number = {05},
	urldate = {2020-04-23},
	journal = {International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems},
	publisher = {World Scientific Publishing Co.},
	author = {Sweeney, Latanya},
	month = oct,
	year = {2002},
	pages = {557--570},
	file = {S0218488502001648:/Users/dkapitan/Zotero/storage/N4GK6C3N/S0218488502001648.html:text/html;Sweeney - 2002 - k-ANONYMITY A MODEL FOR PROTECTING PRIVACY:/Users/dkapitan/Zotero/storage/6V42KUJZ/Sweeney - 2002 - k-ANONYMITY A MODEL FOR PROTECTING PRIVACY.pdf:application/pdf},
}

@article{joshi2022federated,
	title = {Federated {Learning} for {Healthcare} {Domain} - {Pipeline}, {Applications} and {Challenges}},
	volume = {3},
	issn = {2691-1957},
	url = {https://dl.acm.org/doi/10.1145/3533708},
	doi = {10.1145/3533708},
	abstract = {Federated learning is the process of developing machine learning models over datasets distributed across data centers such as hospitals, clinical research labs, and mobile devices while preventing data leakage. This survey examines previous research and studies on federated learning in the healthcare sector across a range of use cases and applications. Our survey shows what challenges, methods, and applications a practitioner should be aware of in the topic of federated learning. This paper aims to lay out existing research and list the possibilities of federated learning for healthcare industries.},
	number = {4},
	urldate = {2023-04-20},
	journal = {ACM Transactions on Computing for Healthcare},
	author = {Joshi, Madhura and Pal, Ankit and Sankarasubbu, Malaikannan},
	month = nov,
	year = {2022},
	keywords = {GDPR, transfer learning, Federated learning},
	pages = {40:1--40:36},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/J5BTYABM/Joshi et al. - 2022 - Federated Learning for Healthcare Domain - Pipelin.pdf:application/pdf},
}

@article{heimbigner1985federated,
	title = {A federated architecture for information management},
	volume = {3},
	issn = {1046-8188},
	url = {https://dl.acm.org/doi/10.1145/4229.4233},
	doi = {10.1145/4229.4233},
	abstract = {An approach to the coordinated sharing and interchange of computerized information is described emphasizing partial, controlled sharing among autonomous databases. Office information systems provide a particularly appropriate context for this type of information sharing and exchange. A federated database architecture is described in which a collection of independent database systems are united into a loosely coupled federation in order to share and exchange information. A federation consists of components (of which there may be any number) and a single federal dictionary. The components represent individual users, applications, workstations, or other components in an office information system. The federal dictionary is a specialized component that maintains the topology of the federation and oversees the entry of new components. Each component in the federation controls its interactions with other components by means of an export schema and an import schema. The export schema specifies the information that a component will share with other components, while the import schema specifies the nonlocal information that a component wishes to manipulate. The federated architecture provides mechanisms for sharing data, for sharing transactions (via message types) for combining information from several components, and for coordinating activities among autonomous components (via negotiation). A prototype implementation of the federated database mechanism is currently operational on an experimental basis.},
	number = {3},
	urldate = {2023-04-23},
	journal = {ACM Transactions on Information Systems},
	author = {Heimbigner, Dennis and McLeod, Dennis},
	month = jul,
	year = {1985},
	pages = {253--278},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/L3BBRJUP/Heimbigner and McLeod - 1985 - A federated architecture for information managemen.pdf:application/pdf},
}

@article{elkordy2023federated,
	title = {Federated {Analytics}: {A} {Survey}},
	volume = {12},
	issn = {2048-7703},
	shorttitle = {Federated {Analytics}},
	url = {http://www.nowpublishers.com/article/Details/SIP-2022-0063},
	doi = {10.1561/116.00000063},
	abstract = {Federated analytics (FA) is a privacy-preserving framework for computing data analytics over multiple remote parties (e.g., mobile devices) or silo-ed institutional entities (e.g., hospitals, banks) without sharing the data among parties. Motivated by the practical use cases of federated analytics, we follow a systematic discussion on federated analytics in this article. In particular, we discuss the unique characteristics of federated analytics and how it differs from federated learning. We also explore a wide range of FA queries and discuss various existing solutions and potential use case applications for different FA queries.},
	language = {en},
	number = {1},
	urldate = {2023-05-07},
	journal = {APSIPA Transactions on Signal and Information Processing},
	author = {Elkordy, Ahmed Roushdy and Ezzeldin, Yahya H. and Han, Shanshan and Sharma, Shantanu and He, Chaoyang and Mehrotra, Sharad and Avestimehr, Salman},
	year = {2023},
	file = {Elkordy et al. - 2023 - Federated Analytics A Survey.pdf:/Users/dkapitan/Zotero/storage/RT8R68NY/Elkordy et al. - 2023 - Federated Analytics A Survey.pdf:application/pdf},
}

@article{gu2022systematic,
	title = {A systematic overview of data federation systems},
	volume = {15},
	issn = {1570-0844},
	url = {https://content.iospress.com/articles/semantic-web/sw223201},
	doi = {10.3233/SW-223201},
	abstract = {Data federation addresses the problem of uniformly accessing multiple, possibly heterogeneous data sources, by mapping them into a unified schema, such as an RDF(S)/OWL ontology or a relational schema, and by supporting the execution of queries, like},
	language = {en},
	number = {1},
	urldate = {2024-05-27},
	journal = {Semantic Web},
	publisher = {IOS Press},
	author = {Gu, Zhenzhen and Corcoglioniti, Francesco and Lanti, Davide and Mosca, Alessandro and Xiao, Guohui and Xiong, Jing and Calvanese, Diego},
	month = dec,
	year = {2022},
	pages = {107--165},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/8FWFTGCM/Gu et al. - 2024 - A systematic overview of data federation systems.pdf:application/pdf},
}

@article{schultes2023fair,
	title = {The {FAIR} hourglass: {A} framework for {FAIR} implementation},
	volume = {1},
	issn = {2949799X},
	shorttitle = {The {FAIR} hourglass},
	url = {https://www.medra.org/servlet/aliasResolver?alias=iospress&doi=10.3233/FC-221514},
	doi = {10.3233/FC-221514},
	abstract = {The FAIR Hourglass provides a framework to organize two general phases of FAIR implementation: FAIRification (top) and FAIR Orchestration (bottom). The center of the hourglass represents the use of widely agreed-upon open, minimal standards ensuring machine-actionability.},
	language = {en},
	number = {1},
	urldate = {2023-04-04},
	journal = {FAIR Connect},
	author = {Schultes, Erik},
	editor = {Magagna, Barbara},
	month = jan,
	year = {2023},
	pages = {13--17},
	file = {Schultes - 2023 - The FAIR hourglass A framework for FAIR implement.pdf:/Users/dkapitan/Zotero/storage/C79VBWCR/Schultes - 2023 - The FAIR hourglass A framework for FAIR implement.pdf:application/pdf},
}

@article{nikayin2013collective,
	title = {Collective action for a common service platform for independent living services},
	volume = {82},
	issn = {13865056},
	doi = {10.1016/j.ijmedinf.2013.06.013},
	abstract = {Objective: The paper aims to explain how and why organizations, providing assistive devices and related web services for elderly independent living services, might be willing to collaborate and to share their resources and data on a common service platform. Method: A theoretical framework from literature on collective action theory, platform and business ecosystem concepts was developed to explain what factors influence interorganizational collective action for a common service platform. The framework was tested in a case study of collaborative platform project for independent living services in Finland. Semi-structured interviews with the project managers and the decision makers of involved organizations were the primary source of data collection. Result: Strikingly, interdependency among the organizations was not found to be important for collaboration in this case. Instead, we found that a central organization can play an important role in initiating, facilitating and encouraging collaboration among different parties. Moreover, we found more willingness for collaboration when the platform is aimed to be open to third-parties to complement the platform with additional services. Conclusions: Strategies of the platform leader and openness of the platform towards third parties are the most important drivers for collective action between organizations offering independent living services. Establishing common service platforms for independent living services requires explicit attention to these inter-organizational issues.},
	language = {english},
	number = {10},
	journal = {International Journal of Medical Informatics},
	author = {Nikayin, Fatemeh and De Reuver, Mark and Itälä, Timo},
	month = oct,
	year = {2013},
	pages = {922--939},
}

@article{karippacheril2013servinga,
	title = {Serving the poor: {Multisided} mobile service platforms, openness, competition, collaboration and the struggle for leadership},
	volume = {37},
	issn = {0308-5961},
	shorttitle = {Serving the poor},
	doi = {10.1016/j.telpol.2012.06.001},
	abstract = {Four billion people at the base of the economic pyramid live on incomes below \$3000 a year in local purchasing power, and more often than not, lack consistent access to services, such as water, healthcare, banking or agricultural know-how. Rapid advances in mobile technology offer the potential to mediate access to essential services. Through this research, the answers to the following question were explored: will mobile service platforms bridge the gap between service providers and people living at the base of the pyramid in developing countries? Anchored in interviews with 31 experts in the field of mobile and ICT, qualitative analysis starting from platform leadership to explain the role of mobile service platforms is presented: how operator, device and service provider centric platforms compete, collaborate and open up (or not) for delivering scalable services to the poor. Based on the analysis in this paper, it is portended that although operator centric platforms are in pole position, device centric platform providers, being astute innovators, are positioned to close the lead by presenting alternatives to bridge the gap in developing countries. This paper frames the current debate on M4D through the lens of platform theory, and aims to provide guidance to policy makers to improve access to services for the poor.},
	language = {english},
	number = {1},
	journal = {Telecommunications Policy},
	author = {Karippacheril, Tina George and Nikayin, Fatemeh and de Reuver, Mark and Bouwman, Harry},
	month = feb,
	year = {2013},
	keywords = {ICT4D, M4D, Mobile, Platform leadership, Poverty, Telecommunications},
	pages = {24--34},
}

@article{beck2019hourglass,
	title = {On the hourglass model},
	volume = {62},
	issn = {0001-0782, 1557-7317},
	doi = {10.1145/3274770},
	abstract = {Used in the design of the Internet and Unix, the layered services of the hourglass model have enabled viral adoption and deployment scalability.},
	language = {english},
	number = {7},
	journal = {Communications of the ACM},
	author = {Beck, Micah},
	month = jun,
	year = {2019},
	pages = {48--57},
	file = {Beck - 2019 - On the hourglass model:/Users/dkapitan/Zotero/storage/NKGQZL5V/Beck - 2019 - On the hourglass model.pdf:application/pdf},
}

@article{baran1964distributed,
	title = {On {Distributed} {Communications} {Networks}},
	volume = {12},
	issn = {1558-2647},
	url = {https://ieeexplore.ieee.org/abstract/document/1088883},
	doi = {10.1109/TCOM.1964.1088883},
	abstract = {This paper briefly reviews the distributed communication network concept in which each station is connected to all adjacent stations rather than to a few switching points, as in a centralized system. The payoff for a distributed configuration in terms of survivability in the cases of enemy attack directed against nodes, links or combinations of nodes and links is demonstrated. A comparison is made between diversity of assignment and perfect switching in distributed networks, and the feasibility of using low-cost unreliable communication links, even links so unreliable as to be unusable in present type networks, to form highly reliable networks is discussed. The requirements for a future all-digital data distributed network which provides common user service for a wide range of users having different requirements is considered. The use of a standard format message block permits building relatively simple switching mechanisms using an adaptive store-and-forward routing policy to handle all forms of digital data including digital voice. This network rapidly responds to changes in the network status. Recent history of measured network traffic is used to modify path selection. Simulation results are shown to indicate that highly efficient routing can be performed by local control without the necessity for any central, and therefore vulnerable, control point.},
	number = {1},
	urldate = {2024-08-12},
	journal = {IEEE Transactions on Communications Systems},
	author = {Baran, P.},
	month = mar,
	year = {1964},
	note = {Conference Name: IEEE Transactions on Communications Systems},
	keywords = {Information systems, Buildings, Centralized control, Communication networks, Communication switching, Communication system control, History, Network synthesis, Routing, Telecommunication network reliability},
	pages = {1--9},
	file = {IEEE Xplore Full Text PDF:/Users/dkapitan/Zotero/storage/GXJYF89Z/Baran - 1964 - On Distributed Communications Networks.pdf:application/pdf},
}

@inproceedings{mcmahan2017communication,
	title = {Communication-{Efficient} {Learning} of {Deep} {Networks} from {Decentralized} {Data}},
	url = {https://proceedings.mlr.press/v54/mcmahan17a.html},
	abstract = {Modern mobile devices have access to a wealth of data suitable for learning models, which in turn can greatly improve the user experience on the device. For example, language models can improve speech recognition and text entry, and image models can automatically select good photos. However, this rich data is often privacy sensitive, large in quantity, or both, which may preclude logging to the data center and training there using conventional approaches. We advocate an alternative that leaves the training data distributed on the mobile devices, and learns a shared model by aggregating locally-computed updates. We term this decentralized approach Federated Learning. We present a practical method for the federated learning of deep networks based on iterative model averaging, and conduct an extensive empirical evaluation, considering five different model architectures and four datasets. These experiments demonstrate the approach is robust to the unbalanced and non-IID data distributions that are a defining characteristic of this setting. Communication costs are the principal constraint, and we show a reduction in required communication rounds by 10-100x as compared to synchronized stochastic gradient descent.},
	language = {en},
	urldate = {2024-08-25},
	booktitle = {Proceedings of the 20th {International} {Conference} on {Artificial} {Intelligence} and {Statistics}},
	publisher = {PMLR},
	author = {McMahan, Brendan and Moore, Eider and Ramage, Daniel and Hampson, Seth and Arcas, Blaise Aguera y},
	month = apr,
	year = {2017},
	pages = {1273--1282},
	file = {PDF:/Users/dkapitan/Zotero/storage/BVMJRDYZ/McMahan et al. - 2017 - Communication-Efficient Learning of Deep Networks from Decentralized Data.pdf:application/pdf},
}

@article{estrin2010health,
	title = {Health care delivery. {Open} {mHealth} architecture: an engine for health care innovation},
	volume = {330},
	issn = {1095-9203},
	shorttitle = {Health care delivery. {Open} {mHealth} architecture},
	doi = {10.1126/science.1196187},
	language = {eng},
	number = {6005},
	journal = {Science (New York, N.Y.)},
	author = {Estrin, Deborah and Sim, Ida},
	month = nov,
	year = {2010},
	keywords = {Humans, Medical Informatics, Telemedicine, Software, Internet, Delivery of Health Care, Cell Phone},
	pages = {759--760},
	file = {Estrin and Sim - 2010 - Health care delivery. Open mHealth architecture a.pdf:/Users/dkapitan/Zotero/storage/9CHH5MAQ/Estrin and Sim - 2010 - Health care delivery. Open mHealth architecture a.pdf:application/pdf},
}

@article{jordan2015machine,
	title = {Machine learning: {Trends}, perspectives, and prospects},
	volume = {349},
	shorttitle = {Machine learning},
	url = {https://www.science.org/doi/full/10.1126/science.aaa8415},
	doi = {10.1126/science.aaa8415},
	abstract = {Machine learning addresses the question of how to build computers that improve automatically through experience. It is one of today’s most rapidly growing technical fields, lying at the intersection of computer science and statistics, and at the core of artificial intelligence and data science. Recent progress in machine learning has been driven both by the development of new learning algorithms and theory and by the ongoing explosion in the availability of online data and low-cost computation. The adoption of data-intensive machine-learning methods can be found throughout science, technology and commerce, leading to more evidence-based decision-making across many walks of life, including health care, manufacturing, education, financial modeling, policing, and marketing.},
	number = {6245},
	urldate = {2024-09-12},
	journal = {Science},
	publisher = {American Association for the Advancement of Science},
	author = {Jordan, M. I. and Mitchell, T. M.},
	month = jul,
	year = {2015},
	pages = {255--260},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/W6JFUK5V/Jordan and Mitchell - 2015 - Machine learning Trends, perspectives, and prospe.pdf:application/pdf},
}

@article{moncada-torres2021vantage6,
	title = {{VANTAGE6}: an open source {priVAcy} {preserviNg} {federaTed} {leArninG} {infrastructurE} for {Secure} {Insight} {eXchange}},
	volume = {2020},
	issn = {1942-597X},
	shorttitle = {{VANTAGE6}},
	url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8075508/},
	abstract = {Answering many of the research questions in the field of cancer informatics requires incorporating and centralizing data that are hosted by different parties. Federated Learning (FL) has emerged as a new approach in which a global model can be generated without disclosing private patient data by keeping them at their original location. Flexible, user-friendly, and robust infrastructures are crucial for bringing FL solutions to the day-to-day work of the cancer epidemiologist. In this paper, we present an open source priVAcy preserviNg federaTed leArninG infrastructurE for Secure Insight eXchange, VANTAGE6. We provide a detailed description of its conceptual design, modular architecture, and components. We also show a few examples where VANTAGE6 has been successfully used in research on observational cancer data. Developing and deploying technology to support federated analyses – such as VANTAGE6 – will pave the way for the adoption and mainstream practice of this new approach for analyzing decentralized data.},
	urldate = {2024-09-21},
	journal = {AMIA Annual Symposium Proceedings},
	author = {Moncada-Torres, Arturo and Martin, Frank and Sieswerda, Melle and Van Soest, Johan and Geleijnse, Gijs},
	month = jan,
	year = {2021},
	pages = {870--877},
	file = {PubMed Central Full Text PDF:/Users/dkapitan/Zotero/storage/IBF6X9ZZ/Moncada-Torres et al. - 2021 - VANTAGE6 an open source priVAcy preserviNg federa.pdf:application/pdf},
}

@article{tsafnat2024converge,
	title = {Converge or {Collide}? {Making} {Sense} of a {Plethora} of {Open} {Data} {Standards} in {Health} {Care}},
	volume = {26},
	shorttitle = {Converge or {Collide}?},
	url = {https://www.jmir.org/2024/1/e55779},
	doi = {10.2196/55779},
	abstract = {Practitioners of digital health are familiar with disjointed data environments that often inhibit effective communication among different elements of the ecosystem. This fragmentation leads in turn to issues such as inconsistencies in services versus payments, wastage, and notably, care delivered being less than best-practice. Despite the long-standing recognition of interoperable data as a potential solution, efforts in achieving interoperability have been disjointed and inconsistent, resulting in numerous incompatible standards, despite the widespread agreement that fewer standards would enhance interoperability. This paper introduces a framework for understanding health care data needs, discussing the challenges and opportunities of open data standards in the field. It emphasizes the necessity of acknowledging diverse data standards, each catering to specific viewpoints and needs, while proposing a categorization of health care data into three domains, each with its distinct characteristics and challenges, along with outlining overarching design requirements applicable to all domains and specific requirements unique to each domain.},
	language = {EN},
	number = {1},
	urldate = {2024-09-21},
	journal = {Journal of Medical Internet Research},
	publisher = {JMIR Publications Inc., Toronto, Canada},
	author = {Tsafnat, Guy and Dunscombe, Rachel and Gabriel, Davera and Grieve, Grahame and Reich, Christian},
	month = apr,
	year = {2024},
	note = {Company: Journal of Medical Internet Research
Distributor: Journal of Medical Internet Research
Institution: Journal of Medical Internet Research
Label: Journal of Medical Internet Research},
	pages = {e55779},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/HCRU7DUV/e55779.html:text/html},
}

@misc{composable,
	title = {The {Composable} {Codex}},
	url = {https://voltrondata.com/codex.html},
	abstract = {The Composable Codex covers the trends, tools, and standards enabling composable data systems. Discover open data standards making composability possible and how they foster system interoperability and acceleration.},
	language = {en},
	urldate = {2024-10-16},
	journal = {Voltron Data},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/K89H8AWL/codex.html:text/html},
}

@misc{zhang2023secure,
	title = {Secure and {Private} {Healthcare} {Analytics}: {A} {Feasibility} {Study} of {Federated} {Deep} {Learning} with {Personal} {Health} {Train}},
	shorttitle = {Secure and {Private} {Healthcare} {Analytics}},
	url = {https://www.researchsquare.com/article/rs-3158418/v1},
	doi = {10.21203/rs.3.rs-3158418/v1},
	abstract = {Objective In this article, we aim to present a new open-source Federated Learning infrastructure by conducting several proof-of-concept experiments. We seek to prove the reliability of the infrastructure to develop global models without sharing private patient data.Materials and Methods We applied the Personal Health Train (PHT) principles using the Vantage6 software to train a neural network to classify head and neck cancer patients\’ distant metastasis using federated learning algorithms in a privacy preserving manner. Head and neck cancer patient data from four cohorts were assigned to two data stations. During each training iteration, model weights were averaged and sent back to central node.Results We compared the area under the receiver operating characteristic curves (AUCs) and model weights between the centralized and federated learning scenarios. The results showed that our federated infrastructure was able to achieve similar predicting power as in the centralized case. Different federated learning model weights aggregation methods were tested. The experiment results showed that federated learning models reached best performance when we aggregate model weights per epoch.Discussion and Conclusion PHT and FAIR data principles can efficiently calculate quality indicators in a privacy-preserving federated approach and the work can be scaled up both nationally and internationally. Despite this, application of the methodology was largely hampered by ELSI issues. However, the lessons learned from this study can provide other hospitals and researchers to adapt to the process easily and take effective measures in building quality of care infrastructures.},
	urldate = {2024-10-24},
	publisher = {Research Square},
	author = {Zhang, Chong and Choudhury, Ananya and Volmer, Leroy and Soest, Johan and Bermejo, Inigo and Dekker, Andre and Gomes, Aiara Lobo and Wee, Leonard},
	month = jul,
	year = {2023},
	note = {ISSN: 2693-5015},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/QSIP8H5B/Zhang et al. - 2023 - Secure and Private Healthcare Analytics A Feasibility Study of Federated Deep Learning with Persona.pdf:application/pdf},
}

@article{gentner2023data,
	title = {Data {Lakes} in {Healthcare}: {Applications} and {Benefits} from the {Perspective} of {Data} {Sources} and {Players}},
	volume = {225},
	issn = {18770509},
	shorttitle = {Data {Lakes} in {Healthcare}},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S1877050923012760},
	doi = {10.1016/j.procs.2023.10.118},
	abstract = {As the amount of available data in healthcare has increased significantly and only 20\% of electronic health record data are in a structured format, data lakes have become a common solution for managing heterogeneous data in the healthcare domain. Nowadays, these are utilized far below their capabilities in medical research. Since previous reviews only partly address data lakes in the healthcare domain, a systematic literature review on this topic is missing. Therefore, this paper provides an overview of applications in the healthcare domain that benefit from data lakes. We review the literature and structure it according to data sources and players, and we identify applications and future research needs of data lakes in the healthcare domain. Overall, it turned out that all players could benefit from the capabilities of data lakes. We found that data lakes are currently not broadly implemented in the field, and the viewpoint of hospital operators and healthcare insurers seems to be an underresearched topic compared to the other players.},
	language = {en},
	urldate = {2024-12-02},
	journal = {Procedia Computer Science},
	author = {Gentner, Tobias and Neitzel, Timon and Schulze, Jacob and Gerschner, Felix and Theissler, Andreas},
	year = {2023},
	pages = {1302--1311},
	file = {PDF:/Users/dkapitan/Zotero/storage/55AX3GRC/Gentner et al. - 2023 - Data Lakes in Healthcare Applications and Benefits from the Perspective of Data Sources and Players.pdf:application/pdf},
}

@article{mancohealer,
	title = {{HEALER}: {A} {Data} {Lake} {Architecture} for {Healthcare}},
	abstract = {With the growth of the Internet of Things and the rapid progress of social networks, everything appears to generate data. The ever-increasing number of connected devices is accompanied by a growth of the volume of data, produced at an ever-increasing rate, and this massive flow includes data types that are difficult to process using standard database techniques. One of the most critical scenarios is healthcare, whose activities need to store and manage a variety of data types – reports written in natural language, medical images, genomic data and waveforms of vital signs – which do not have a well-defined structure. In order to benefit from this large amount of complex data, Data Lakes have recently emerged as a solution to grant central storage and flexible analysis for all types of data. However, there is no Data Lake architecture that fits all the possible scenarios, since the architecture depends heavily on the application domain and, so far, there are no Data Lake architectures that support the specific needs of the healthcare domain. This work proposes HEALER: a Data Lake architecture that effectively performs data ingestion, data storage, and data access with the aim of providing a single central repository for efficient storage of different types of healthcare data. The architecture also enables the analysis and querying of the data, which can be loaded into the Data Lake regardless of their format and type. To verify the effectiveness of the architecture, a proof-of-concept of HEALER has been developed, that allows ingestion of various data, performs waveforms processing to make them more interpretable to researchers and analysts, grants access to the saved data and allows the analysis of natural language reports. Finally we studied the performance of the system in each of its main phases: ingestion, processing, data access and analysis. The results lead us to some important considerations to be taken into account when using and configuring the system components.},
	language = {en},
	author = {Manco, Carlo and Dolci, Tommaso and Azzalini, Fabio and Barbierato, Enrico and Gribaudo, Marco and Tanca, Letizia},
	file = {PDF:/Users/dkapitan/Zotero/storage/TWCJ2CUD/Manco et al. - HEALER A Data Lake Architecture for Healthcare.pdf:application/pdf},
}

@misc{verheul2016polymorphic,
	title = {Polymorphic {Encryption} and {Pseudonymisation} for {Personalised} {Healthcare}},
	url = {https://eprint.iacr.org/2016/411},
	abstract = {Polymorphic encryption and Pseudonymisation, abbreviated as PEP, form
a novel approach for the management of sensitive personal data,
especially in health care. Traditional encryption is rather rigid:
once encrypted, only one key can be used to decrypt the data. This
rigidity is becoming an every greater problem in the context of big
data analytics, where different parties who wish to investigate part
of an encrypted data set all need the one key for decryption.

Polymorphic encryption is a new cryptographic technique that solves
these problems. Together with the associated technique of polymorphic
pseudonymisation new security and privacy guarantees can be given
which are essential in areas such as (personalised) healthcare,
medical data collection via self-measurement apps, and more generally
in privacy-friendly identity management and data analytics.

The key ideas of polymorphic encryption are:
1. Directly after generation, data can be encrypted in a
`polymorphic' manner and stored at a (cloud) storage facility in
such a way that the storage provider cannot get access. Crucially,
there is no need to a priori fix who gets to see the data, so that
the data can immediately be protected.

For instance a PEP-enabled self-measurement device will store all its
measurement data in polymorphically encrypted form in a back-end data
base.

2. Later on it can be decided who can decrypt the data. This
decision will be made on the basis of a policy, in which the data
subject should play a key role.

The user of the PEP-enabled device can, for instance, decide that
doctors \$X,Y,Z\$ may at some stage decrypt to use the data in their
diagnosis, or medical researcher groups \$A, B, C\$ may use it for their
investigations, or third parties \$U,V,W\$ may use it for additional
services, etc.

3. This `tweaking' of the encrypted data to make it decryptable by
a specific party can be done in a blind manner. It will have to be
done by a trusted party who knows how to tweak the ciphertext for
whom.

This PEP technology can provide the necessary security and privacy
infrastructure for big data analytics. People can entrust their data
in polymorphically encrypted form, and each time decide later to make
(parts of) it available (decryptable) for specific parties, for
specific analysis purposes. In this way users remain in control, and
can monitor which of their data is used where by whom for which
purposes.

The polymorphic encryption infrastructure can be supplemented with a
pseudonymisation infrastructure which is also polymorphic, and
guarantees that each individual will automatically have different
pseudonyms at different parties and can only be de-pseudonymised by
participants (like medical doctors) who know the original identity.

This white paper provides an introduction to Polymorphic Encryption
and Pseudonymisation (PEP), at different levels of abstraction,
focusing on health care as application area. It contains a general
description of PEP, explaining the basic functionality for laymen,
supplemented by a clarification of the legal framework provided by the
upcoming General Data Protection Regulation (GDPR) of the European
Union. The paper also contains a more advanced, mathematically
oriented description of PEP, including the underlying cryptographic
primitives, key and pseudonym managment, interaction protocols,
etc. This second part is aimed at readers with a background in
computer security and cryptography. The cryptographic basis for PEP is
ElGamal public key encryption, which is well-known since the mid
1980s. It is the way in which this encryption is used --- with
re-randomisation, re-keying and re-shuffling --- that is new.

The PEP framework is currently elaborated into an open design and open
source (prototype) implementation at Radboud University in Nijmegen,
The Netherlands. The technology will be used and tested in a real-life
medical research project at the Radboud University Medical Center.},
	urldate = {2024-12-30},
	author = {Verheul, Eric and Jacobs, Bart and Meijer, Carlo and Hildebrandt, Mireille and Ruiter, Joeri de},
	year = {2016},
	note = {Publication info: Preprint.},
	keywords = {healthcare, ElGamal, implementation, pseudonymisation, public key encryption},
}

@article{liao2024fair,
	title = {{FAIR} {Data} {Cube}, a {FAIR} data infrastructure for integrated multi-omics data analysis},
	volume = {15},
	issn = {2041-1480},
	url = {https://jbiomedsem.biomedcentral.com/articles/10.1186/s13326-024-00321-2},
	doi = {10.1186/s13326-024-00321-2},
	abstract = {Motivation We are witnessing an enormous growth in the amount of molecular profiling (-omics) data. The integration of multi-omics data is challenging. Moreover, human multi-omics data may be privacy-sensitive and can be misused to de-anonymize and (re-)identify individuals. Hence, most biomedical data is kept in secure and protected silos. Therefore, it remains a challenge to re-use these data without infringing the privacy of the individuals from which the data were derived. Federated analysis of Findable, Accessible, Interoperable, and Reusable (FAIR) data is a privacypreserving solution to make optimal use of these multi-omics data and transform them into actionable knowledge. Results The Netherlands X-omics Initiative is a National Roadmap Large-Scale Research Infrastructure aiming for efficient integration of data generated within X-omics and external datasets. To facilitate this, we developed the FAIR Data Cube (FDCube), which adopts and applies the FAIR principles and helps researchers to create FAIR data and metadata, to facilitate re-use of their data, and to make their data analysis workflows transparent, and in the meantime ensure data security and privacy.},
	language = {en},
	number = {1},
	urldate = {2025-01-04},
	journal = {Journal of Biomedical Semantics},
	author = {Liao, Xiaofeng and Ederveen, Thomas H.A. and Niehues, Anna and de Visser, Casper and Huang, Junda and Badmus, Firdaws and Doornbos, Cenna and Orlova, Yuliia and Kulkarni, Purva and van der Velde, K. Joeri and Swertz, Morris A. and Brandt, Martin and van Gool, Alain J. and ’T Hoen, Peter A. C.},
	month = dec,
	year = {2024},
	pages = {20},
	file = {PDF:/Users/dkapitan/Zotero/storage/SWMD5FTR/Liao et al. - 2024 - FAIR Data Cube, a FAIR data infrastructure for integrated multi-omics data analysis.pdf:application/pdf},
}

@misc{knodel2024how,
	title = {How {To} {Think} {About} {End}-{To}-{End} {Encryption} and {AI}: {Training}, {Processing}, {Disclosure}, and {Consent}},
	shorttitle = {How {To} {Think} {About} {End}-{To}-{End} {Encryption} and {AI}},
	url = {https://eprint.iacr.org/2024/2086},
	abstract = {End-to-end encryption (E2EE) has become the gold standard for securing communications, bringing strong confidentiality and privacy guarantees to billions of users worldwide. However, the current push towards widespread integration of artificial intelligence (AI) models, including in E2EE systems, raises some serious security concerns.

This work performs a critical examination of the (in)compatibility of AI models and E2EE applications. We explore this on two fronts: (1) the integration of AI “assistants” within E2EE applications, and (2) the use of E2EE data for training AI models. 
We analyze the potential security implications of each, and identify conflicts with the security guarantees of E2EE. Then, we analyze legal implications of integrating AI models in E2EE applications, given how AI integration can undermine the confidentiality that E2EE promises. Finally, we offer a list of detailed recommendations based on our technical and legal analyses, including: technical design choices that must be prioritized to uphold E2EE security; how service providers must accurately represent E2EE security; and best practices for the default behavior of AI features and for requesting user consent. We hope this paper catalyzes an informed conversation on the tensions that arise between the brisk deployment of AI and the security offered by E2EE, and guides the responsible development of new AI features.},
	urldate = {2025-01-04},
	author = {Knodel, Mallory and Fábrega, Andrés and Ferrari, Daniella and Leiken, Jacob and Hou, Betty Li and Yen, Derek and Alfaro, Sam de and Cho, Kyunghyun and Park, Sunoo},
	year = {2024},
	note = {Publication info: Preprint.},
	keywords = {Artificial Intelligence, Secure messaging},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/NYK9L4BR/Knodel et al. - 2024 - How To Think About End-To-End Encryption and AI Training, Processing, Disclosure, and Consent.pdf:application/pdf},
}

@techreport{vangool2018eenheid,
	title = {Eenheid van {Taal} in de {Nederlandse} zorg : {Van} eenduidige informatie-uitwisseling tot hulpmiddel voor betere zorg},
	shorttitle = {Eenheid van {Taal} in de {Nederlandse} zorg},
	url = {https://rivm.openrepository.com/handle/10029/622206},
	doi = {10.21945/RIVM-2018-0081},
	language = {nl},
	urldate = {2025-01-15},
	institution = {RIVM},
	author = {van Gool, CH and Volkert, PA and Savelkoul, M},
	year = {2018},
	file = {PDF:/Users/dkapitan/Zotero/storage/55HDPCS2/van Gool et al. - 2018 - Eenheid van Taal in de Nederlandse zorg  Van eenduidige informatie-uitwisseling tot hulpmiddel voor.pdf:application/pdf},
}

@article{schmidt2024mappinga,
	title = {Mapping the regulatory landscape for artificial intelligence in health within the {European} {Union}},
	volume = {7},
	copyright = {2024 The Author(s)},
	issn = {2398-6352},
	url = {https://www.nature.com/articles/s41746-024-01221-6},
	doi = {10.1038/s41746-024-01221-6},
	abstract = {Regulatory frameworks for artificial intelligence (AI) are needed to mitigate risks while ensuring the ethical, secure, and effective implementation of AI technology in healthcare and population health. In this article, we present a synthesis of 141 binding policies applicable to AI in healthcare and population health in the EU and 10 European countries. The EU AI Act sets the overall regulatory framework for AI, while other legislations set social, health, and human rights standards, address the safety of technologies and the implementation of innovation, and ensure the protection and safe use of data. Regulation specifically pertaining to AI is still nascent and scarce, though a combination of data, technology, innovation, and health and human rights policy has already formed a baseline regulatory framework for AI in health. Future work should explore specific regulatory challenges, especially with respect to AI medical devices, data protection, and data enablement.},
	language = {en},
	number = {1},
	urldate = {2025-01-18},
	journal = {npj Digital Medicine},
	publisher = {Nature Publishing Group},
	author = {Schmidt, Jelena and Schutte, Nienke M. and Buttigieg, Stefan and Novillo-Ortiz, David and Sutherland, Eric and Anderson, Michael and de Witte, Bart and Peolsson, Michael and Unim, Brigid and Pavlova, Milena and Stern, Ariel Dora and Mossialos, Elias and van Kessel, Robin},
	month = aug,
	year = {2024},
	keywords = {Health policy, Public health, Law, Information technology},
	pages = {1--9},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/8QTTM7QB/Schmidt et al. - 2024 - Mapping the regulatory landscape for artificial intelligence in health within the European Union.pdf:application/pdf},
}

@techreport{mxi2024ai,
	title = {{AI} {Monitor} {Ziekenhuizen} 2024},
	url = {https://mxi.nl/uploads/files/publication/ai-monitor-2024.pdf},
	language = {nl},
	institution = {M\&I Partners},
	author = {Gude, Wouter and van Eekeren, Patrick and Vasseur, Jordan},
	year = {2024},
	file = {PDF:/Users/dkapitan/Zotero/storage/XUI9A4M3/Zeist - 2024 - AI Monitor Ziekenhuizen 2024.pdf:application/pdf},
}

@misc{homepage,
	title = {Homepage - {Leidraad}-ai},
	url = {https://guideline-ai-healthcare.com/},
	abstract = {Waardevolle AI Hoe beoordeel je voorspellende artificiële intelligentie (AI) algoritmen voor gezondheid en zorg op kwaliteit en effectiviteit? De Leidraad kwaliteit AI in de zorg geeft u een overzicht van de belangrijkste eisen en aanbevelingen per fase, van ontwikkeling tot implementatie. Lees meer berichten over de leidraad op datavoorgezondheid.nl Vragen/opmerkingen? Deze kunt u delen via},
	language = {en},
	urldate = {2025-01-20},
	journal = {Leidraad-ai -},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/QKXMWPDW/guideline-ai-healthcare.com.html:text/html},
}

@misc{smart-guidelines-webpage,
	title = {{SMART} {Guidelines}},
	url = {https://www.who.int/teams/digital-health-and-innovation/smart-guidelines},
	abstract = {As a landmark effort to accelerating the digitization of global public health resources, digitalizing the countries increasingly invest in digital technologies for health, WHO  need to build support for digital health across its core functions. To date, there is no documentation of procedures for systematically translating WHO’s recommendations into digital health systems in a software-neutral manner.},
	language = {en},
	urldate = {2025-01-20},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/2VTW64HD/smart-guidelines.html:text/html},
}

@misc{2023ai,
	title = {{AI} in medical care: {A} map for clinical practice and patient protection},
	shorttitle = {{AI} in medical care},
	url = {https://www.medicaleconomics.com/view/ai-in-medical-care-a-map-for-clinical-practice-and-patient-protection},
	abstract = {Artificial intelligence (AI) has seen an exponential increase in the already rising interest within the medical field since the introduction of ChatGPT in November 2022.},
	language = {en},
	urldate = {2025-01-20},
	journal = {MedicalEconomics},
	month = jun,
	year = {2023},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/PD3KR9RU/ai-in-medical-care-a-map-for-clinical-practice-and-patient-protection.html:text/html},
}

@article{artificial,
	title = {Artificial {Intelligence} in {Health}},
	language = {en},
	file = {PDF:/Users/dkapitan/Zotero/storage/N8VMKG7K/Artificial Intelligence in Health.pdf:application/pdf},
}

@article{ali2023systematic,
	title = {A systematic literature review of artificial intelligence in the healthcare sector: {Benefits}, challenges, methodologies, and functionalities},
	volume = {8},
	issn = {2444-569X},
	shorttitle = {A systematic literature review of artificial intelligence in the healthcare sector},
	url = {https://www.sciencedirect.com/science/article/pii/S2444569X2300029X},
	doi = {10.1016/j.jik.2023.100333},
	abstract = {Administrative and medical processes of the healthcare organizations are rapidly changing because of the use of artificial intelligence (AI) systems. This change demonstrates the critical impact of AI at multiple activities, particularly in medical processes related to early detection and diagnosis. Previous studies suggest that AI can raise the quality of services in the healthcare industry. AI-based technologies have reported to improve human life quality, making life easier, safer and more productive. This study presents a systematic review of academic articles on the application of AI in the healthcare sector. The review initially considered 1,988 academic articles from major scholarly databases. After a careful review, the list was filtered down to 180 articles for full analysis to present a classification framework based on four dimensions: AI-enabled healthcare benefits, challenges, methodologies, and functionalities. It was identified that AI continues to significantly outperform humans in terms of accuracy, efficiency and timely execution of medical and related administrative processes. Benefits for patients’ map directly to the relevant AI functionalities in the categories of diagnosis, treatment, consultation and health monitoring for self-management of chronic conditions. Implications for future research directions are identified in the areas of value-added healthcare services for medical decision-making, security and privacy for patient data, health monitoring features, and creative IT service delivery models using AI.},
	number = {1},
	urldate = {2025-01-20},
	journal = {Journal of Innovation \& Knowledge},
	author = {Ali, Omar and Abdelbaki, Wiem and Shrestha, Anup and Elbasi, Ersin and Alryalat, Mohammad Abdallah Ali and Dwivedi, Yogesh K},
	month = jan,
	year = {2023},
	keywords = {Artificial intelligence, Healthcare, Systematic literature review, Technology benefits, Technology challenges},
	pages = {100333},
	file = {Full Text:/Users/dkapitan/Zotero/storage/K7HWLDES/Ali et al. - 2023 - A systematic literature review of artificial intelligence in the healthcare sector Benefits, challe.pdf:application/pdf;ScienceDirect Snapshot:/Users/dkapitan/Zotero/storage/Y8IHINYK/S2444569X2300029X.html:text/html},
}

@article{gbadegeshin2022overcominga,
	title = {Overcoming the {Valley} of {Death}: {A} {New} {Model} for {High} {Technology} {Startups}},
	volume = {4},
	issn = {26661888},
	shorttitle = {Overcoming the {Valley} of {Death}},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2666188822000119},
	doi = {10.1016/j.sftr.2022.100077},
	abstract = {The Valley of Death (VoD) reflects a series of challenges facing technology-based companies during their early development stages. Extant literature highlights the need for startups to equip themselves with the tools and resources to manage this turbulent transition. However, the existing frameworks propounded by fellow scholars and practitioners regarding VoD are fragmented, each covering only a few issues in the chasm. Thus, the current article proposes a new and comprehensive model for high technology-based startups. The new model emerged from an in-depth review of 128 scholarly materials and empirical data collected from 30 startups (from artificial intelligence, virtual and augmented realities, internet of things, medical, and cleantech industrial sectors). The model was piloted in three pre-startups. The model adds on the existing VoD frameworks to provide a holistic baseline for future research in this field by presenting different challenges underlying the pre-establishment years of a company while addressing courses of action needed to overcome this perilous transition.},
	language = {en},
	urldate = {2025-01-21},
	journal = {Sustainable Futures},
	author = {Gbadegeshin, Saheed A. and Natsheh, Anas Al and Ghafel, Kawtar and Mohammed, Omar and Koskela, Ashten and Rimpiläinen, Antti and Tikkanen, Joonas and Kuoppala, Antti},
	year = {2022},
	pages = {100077},
	file = {PDF:/Users/dkapitan/Zotero/storage/5ZTEG4R2/Gbadegeshin et al. - 2022 - Overcoming the Valley of Death A New Model for High Technology Startups.pdf:application/pdf},
}

@techreport{un2023pet-guide,
	title = {The {PET} {Guide}},
	url = {https://unstats.un.org/bigdata/task-teams/privacy/guide/},
	urldate = {2025-01-22},
	institution = {United Nations},
	author = {United Nations Committee of Experts on Big Data {and} Data Science for Official Statistics},
	year = {2023},
	file = {PDF:/Users/dkapitan/Zotero/storage/AJP3R3G3/UN Guide on Privacy-Enhancing Technologies for Official Statistics  Task Team on Privacy Enhancing.pdf:application/pdf;UN Guide on Privacy-Enhancing Technologies for Official Statistics // Task Team on Privacy Enhancing Techniques — UN-CEBD:/Users/dkapitan/Zotero/storage/CE6FUTIB/guide.html:text/html},
}

@book{curry2021elements,
	address = {Cham},
	title = {The {Elements} of {Big} {Data} {Value}: {Foundations} of the {Research} and {Innovation} {Ecosystem}},
	copyright = {https://creativecommons.org/licenses/by/4.0},
	isbn = {978-3-030-68175-3 978-3-030-68176-0},
	shorttitle = {The {Elements} of {Big} {Data} {Value}},
	url = {https://link.springer.com/10.1007/978-3-030-68176-0},
	doi = {10.1007/978-3-030-68176-0},
	language = {en},
	urldate = {2025-01-23},
	publisher = {Springer International Publishing},
	editor = {Curry, Edward and Metzger, Andreas and Zillner, Sonja and Pazzaglia, Jean-Christophe and García Robles, Ana},
	year = {2021},
	file = {PDF:/Users/dkapitan/Zotero/storage/LN9HQFQR/Curry et al. - 2021 - The Elements of Big Data Value Foundations of the Research and Innovation Ecosystem.pdf:application/pdf},
}

@misc{2024ai,
	title = {The {AI} {Factory}: {What} {It} {Is} \& {Its} {Key} {Components} {\textbar} {HBS} {Online}},
	shorttitle = {The {AI} {Factory}},
	url = {https://online.hbs.edu/blog/post/ai-factory},
	abstract = {In the digital age, you must understand the AI factory and how it can help you implement AI technologies into business operations.},
	language = {en},
	urldate = {2025-01-24},
	journal = {Business Insights Blog},
	month = sep,
	year = {2024},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/XEYJ3WE6/ai-factory.html:text/html},
}

@misc{aia,
	title = {{AI} {Factories} {\textbar} {Shaping} {Europe}’s digital future},
	url = {https://digital-strategy.ec.europa.eu/en/policies/ai-factories},
	language = {en},
	urldate = {2025-01-24},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/ZP55BPVM/ai-factories.html:text/html},
}

@misc{2024european,
	title = {The {European} {High} {Performance} {Computing} {Joint} {Undertaking} {\textbar} {Shaping} {Europe}’s digital future},
	url = {https://digital-strategy.ec.europa.eu/en/policies/high-performance-computing-joint-undertaking},
	language = {en},
	urldate = {2025-01-24},
	month = dec,
	year = {2024},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/8L3WPBF5/high-performance-computing-joint-undertaking.html:text/html},
}

@misc{2024homepage,
	title = {Homepage - {EuroHPC} {JU}},
	url = {https://eurohpc-ju.europa.eu/index_en},
	abstract = {The European High Performance Computing Joint Undertaking (EuroHPC JU) is a joint initiative between the EU, European countries and private partners to develop a World Class Supercomputing Ecosystem in Europe.},
	language = {en},
	urldate = {2025-01-24},
	month = dec,
	year = {2024},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/UENNPC2T/index_en.html:text/html},
}

@techreport{tarkowski2025data,
	title = {Data {Governance} in {Open} {Source} {AI}},
	language = {en},
	institution = {Open Future Foundation},
	author = {Tarkowski, Alek},
	month = jan,
	year = {2025},
	file = {PDF:/Users/dkapitan/Zotero/storage/X8XDXHKI/Tarkowski - Data Governance in Open Source AI.pdf:application/pdf},
}

@article{boylesecond,
	title = {{THE} {SECOND} {ENCLOSURE} {MOVEMENT} {AND} {THE} {CONSTRUCTION} {OF} {THE} {PUBLIC} {DOMAIN}},
	language = {en},
	author = {Boyle, James},
	file = {PDF:/Users/dkapitan/Zotero/storage/3EY7YA9R/Boyle - THE SECOND ENCLOSURE MOVEMENT AND THE CONSTRUCTION OF THE PUBLIC DOMAIN.pdf:application/pdf},
}

@misc{choosing,
	title = {Choosing {Between} {Microsoft} {Fabric} and {Databricks}: {A} {Guide} for {Your} {Data} {Analytics} {Needs}},
	shorttitle = {Choosing {Between} {Microsoft} {Fabric} and {Databricks}},
	url = {https://www.element61.be/en/resource/choosing-between-microsoft-fabric-and-databricks-guide-your-data-analytics-needs},
	abstract = {Feeling torn between Microsoft Fabric and Databricks for data analytics? You're not alone! Let us guide you through their features, functionalities, and benefits to help you make the right choice for your organization.},
	language = {en},
	urldate = {2025-01-28},
	journal = {element61},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/QYJW8CWA/choosing-between-microsoft-fabric-and-databricks-guide-your-data-analytics-needs.html:text/html},
}

@misc{tagliabue2023building,
	title = {Building a serverless {Data} {Lakehouse} from spare parts},
	url = {http://arxiv.org/abs/2308.05368},
	doi = {10.48550/arXiv.2308.05368},
	abstract = {The recently proposed Data Lakehouse architecture is built on open file formats, performance, and first-class support for data transformation, BI and data science: while the vision stresses the importance of lowering the barrier for data work, existing implementations often struggle to live up to user expectations. At Bauplan, we decided to build a new serverless platform to fulfill the Lakehouse vision. Since building from scratch is a challenge unfit for a startup, we started by re-using (sometimes unconventionally) existing projects, and then investing in improving the areas that would give us the highest marginal gains for the developer experience. In this work, we review user experience, high-level architecture and tooling decisions, and conclude by sharing plans for future development.},
	urldate = {2025-01-29},
	publisher = {arXiv},
	author = {Tagliabue, Jacopo and Greco, Ciro and Bigon, Luca},
	month = aug,
	year = {2023},
	note = {arXiv:2308.05368 [cs]},
	keywords = {Computer Science - Databases, Computer Science - Software Engineering, Computer Science - Distributed, Parallel, and Cluster Computing},
	file = {Preprint PDF:/Users/dkapitan/Zotero/storage/HH33FNWB/Tagliabue et al. - 2023 - Building a serverless Data Lakehouse from spare parts.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/QMGVJ8H9/2308.html:text/html},
}

@incollection{pohjonen2022norway,
	title = {Norway, {Sweden}, and {Finland} as forerunners in open ecosystems and {openEHR}},
	isbn = {978-0-12-823413-6},
	url = {https://www.sciencedirect.com/science/article/pii/B9780128234136000112},
	doi = {10.1016/B978-0-12-823413-6.00011-2},
	abstract = {Norway, Sweden, and Finland may be considered as forerunners in adopting openEHR and moving towards open ecosystems. Cross-organisational data sharing, or data exchange, has historically been the objective in all Nordic countries. The needs to share data finally resulted in national document-based data sharing infrastructures in all Nordic countries. Document-based sharing is, however, somewhat limited, and the need for complementary structured sharing has started to emerge. openEHR projects typically start as data exchange projects and gradually develop into a modular EHR. In the Nordics, however, the dominant EHR market leaders chose openEHR as their own data model and started to modernise their solutions as their own internal decision. This is not necessarily the approach taken in other countries. The Nordic experience shows that in order to build a true ecosystem, it is important to increase awareness amongst all stakeholders. A monolithic solution may seem lucrative unless there is sufficient understanding of the benefits of modularity and openEHR.},
	urldate = {2025-02-05},
	booktitle = {Roadmap to {Successful} {Digital} {Health} {Ecosystems}},
	publisher = {Academic Press},
	author = {Pohjonen, Hanna},
	editor = {Hovenga, Evelyn and Grain, Heather},
	month = jan,
	year = {2022},
	keywords = {Data sharing, EHR, openEHR, Data exchange, Modular, Nordic, Open ecosystem},
	pages = {457--471},
	file = {ScienceDirect Full Text PDF:/Users/dkapitan/Zotero/storage/UQT5YXBQ/Pohjonen - 2022 - Chapter 20 - Norway, Sweden, and Finland as forerunners in open ecosystems and openEHR.pdf:application/pdf;ScienceDirect Snapshot:/Users/dkapitan/Zotero/storage/UTVGDW2T/B9780128234136000112.html:text/html},
}

@inproceedings{akhtar2024croissant,
	address = {Santiago AA Chile},
	title = {Croissant: {A} {Metadata} {Format} for {ML}-{Ready} {Datasets}},
	isbn = {979-8-4007-0611-0},
	shorttitle = {Croissant},
	url = {https://dl.acm.org/doi/10.1145/3650203.3663326},
	doi = {10.1145/3650203.3663326},
	abstract = {Data is a critical resource for Machine Learning (ML), yet working with data remains a key friction point. This paper introduces Croissant, a metadata format for datasets that simplifies how data is used by ML tools and frameworks. Croissant makes datasets more discoverable, portable and interoperable, thereby addressing significant challenges in ML data management and responsible AI. Croissant is already supported by several popular dataset repositories, spanning hundreds of thousands of datasets, ready to be loaded into the most popular ML frameworks.},
	language = {en},
	urldate = {2025-02-14},
	booktitle = {Proceedings of the {Eighth} {Workshop} on {Data} {Management} for {End}-to-{End} {Machine} {Learning}},
	publisher = {ACM},
	author = {Akhtar, Mubashara and Benjelloun, Omar and Conforti, Costanza and Gijsbers, Pieter and Giner-Miguelez, Joan and Jain, Nitisha and Kuchnik, Michael and Lhoest, Quentin and Marcenac, Pierre and Maskey, Manil and Mattson, Peter and Oala, Luis and Ruyssen, Pierre and Shinde, Rajat and Simperl, Elena and Thomas, Goeffry and Tykhonov, Slava and Vanschoren, Joaquin and Van Der Velde, Jos and Vogler, Steffen and Wu, Carole-Jean},
	month = jun,
	year = {2024},
	pages = {1--6},
	file = {PDF:/Users/dkapitan/Zotero/storage/7265AEDQ/Akhtar et al. - 2024 - Croissant A Metadata Format for ML-Ready Datasets.pdf:application/pdf},
}

@article{dasilvasantos2023fair,
	title = {{FAIR} {Data} {Point}: {A} {FAIR}-{Oriented} {Approach} for {Metadata} {Publication}},
	volume = {5},
	issn = {2641-435X},
	shorttitle = {{FAIR} {Data} {Point}},
	url = {https://doi.org/10.1162/dint_a_00160},
	doi = {10.1162/dint_a_00160},
	abstract = {Metadata, data about other digital objects, play an important role in FAIR with a direct relation to all FAIR principles. In this paper we present and discuss the FAIR Data Point (FDP), a software architecture aiming to define a common approach to publish semantically-rich and machine-actionable metadata according to the FAIR principles. We present the core components and features of the FDP, its approach to metadata provision, the criteria to evaluate whether an application adheres to the FDP specifications and the service to register, index and allow users to search for metadata content of available FDPs.},
	number = {1},
	urldate = {2025-02-16},
	journal = {Data Intelligence},
	author = {da Silva Santos, Luiz Olavo Bonino and Burger, Kees and Kaliyaperumal, Rajaram and Wilkinson, Mark D.},
	month = mar,
	year = {2023},
	pages = {163--183},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/Y34RNYYM/da Silva Santos et al. - 2023 - FAIR Data Point A FAIR-Oriented Approach for Metadata Publication.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/8P3WD4GA/FAIR-Data-Point-A-FAIR-Oriented-Approach-for.html:text/html},
}

@article{braun2025how,
	title = {How predictive medicine leads to solidarity gaps in health},
	volume = {8},
	copyright = {2025 The Author(s)},
	issn = {2398-6352},
	url = {https://www.nature.com/articles/s41746-025-01497-2},
	doi = {10.1038/s41746-025-01497-2},
	abstract = {The current shift in healthcare towards AI-driven P4 medicine challenges practices of solidarity, with implications for EU health policy.},
	language = {en},
	number = {1},
	urldate = {2025-02-20},
	journal = {npj Digital Medicine},
	publisher = {Nature Publishing Group},
	author = {Braun, Matthias},
	month = feb,
	year = {2025},
	keywords = {Ethics, Society},
	pages = {1--3},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/6EYGUDFY/Braun - 2025 - How predictive medicine leads to solidarity gaps in health.pdf:application/pdf},
}

@article{chustecki2024benefits,
	title = {Benefits and {Risks} of {AI} in {Health} {Care}: {Narrative} {Review}},
	volume = {13},
	copyright = {Unless stated otherwise, all articles are open-access distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work ("first published in the interactive Journal of Medical Research...") is properly cited with original URL and bibliographic citation information. The complete bibliographic information, a link to the original publication on http://www.i-jmr.org/, as well as this copyright and license information must be included.},
	shorttitle = {Benefits and {Risks} of {AI} in {Health} {Care}},
	url = {https://www.i-jmr.org/2024/1/e53616},
	doi = {10.2196/53616},
	abstract = {Background: The integration of artificial intelligence (AI) into health care has the potential to transform the industry, but it also raises ethical, regulatory, and safety concerns. This review paper provides an in-depth examination of the benefits and risks associated with AI in health care, with a focus on issues like biases, transparency, data privacy, and safety.
Objective: This study aims to evaluate the advantages and drawbacks of incorporating AI in health care. This assessment centers on the potential biases in AI algorithms, transparency challenges, data privacy issues, and safety risks in health care settings.
Methods: Studies included in this review were selected based on their relevance to AI applications in health care, focusing on ethical, regulatory, and safety considerations. Inclusion criteria encompassed peer-reviewed articles, reviews, and relevant research papers published in English. Exclusion criteria included non–peer-reviewed articles, editorials, and studies not directly related to AI in health care. A comprehensive literature search was conducted across 8 databases: OVID MEDLINE, OVID Embase, OVID PsycINFO, EBSCO CINAHL Plus with Full Text, ProQuest Sociological Abstracts, ProQuest Philosopher’s Index, ProQuest Advanced Technologies \& Aerospace, and Wiley Cochrane Library. The search was last updated on June 23, 2023. Results were synthesized using qualitative methods to identify key themes and findings related to the benefits and risks of AI in health care.
Results: The literature search yielded 8796 articles. After removing duplicates and applying the inclusion and exclusion criteria, 44 studies were included in the qualitative synthesis. This review highlights the significant promise that AI holds in health care, such as enhancing health care delivery by providing more accurate diagnoses, personalized treatment plans, and efficient resource allocation. However, persistent concerns remain, including biases ingrained in AI algorithms, a lack of transparency in decision-making, potential compromises of patient data privacy, and safety risks associated with AI implementation in clinical settings.
Conclusions: In conclusion, while AI presents the opportunity for a health care revolution, it is imperative to address the ethical, regulatory, and safety challenges linked to its integration. Proactive measures are required to ensure that AI technologies are developed and deployed responsibly, striking a balance between innovation and the safeguarding of patient well-being.},
	language = {EN},
	number = {1},
	urldate = {2025-02-20},
	journal = {Interactive Journal of Medical Research},
	publisher = {JMIR Publications Inc., Toronto, Canada},
	author = {Chustecki, Margaret},
	month = nov,
	year = {2024},
	note = {Company: Interactive Journal of Medical Research
Distributor: Interactive Journal of Medical Research
Institution: Interactive Journal of Medical Research
Label: Interactive Journal of Medical Research},
	pages = {e53616},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/YVN9K8XG/e53616.html:text/html},
}

@article{li2025evolution,
	title = {Evolution of {Artificial} {Intelligence} in {Medical} {Education} {From} 2000 to 2024: {Bibliometric} {Analysis}},
	volume = {14},
	copyright = {Unless stated otherwise, all articles are open-access distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work ("first published in the interactive Journal of Medical Research...") is properly cited with original URL and bibliographic citation information. The complete bibliographic information, a link to the original publication on http://www.i-jmr.org/, as well as this copyright and license information must be included.},
	shorttitle = {Evolution of {Artificial} {Intelligence} in {Medical} {Education} {From} 2000 to 2024},
	url = {https://www.i-jmr.org/2025/1/e63775},
	doi = {10.2196/63775},
	abstract = {Background: Incorporating artificial intelligence (AI) into medical education has gained significant attention for its potential to enhance teaching and learning outcomes. However, it lacks a comprehensive study depicting the academic performance and status of AI in the medical education domain.
Objective: This study aims to analyze the social patterns, productive contributors, knowledge structure, and clusters since the 21st century.
Methods: Documents were retrieved from the Web of Science Core Collection database from 2000 to 2024. VOSviewer, Incites, and Citespace were used to analyze the bibliometric metrics, which were categorized by country, institution, authors, journals, and keywords. The variables analyzed encompassed counts, citations, H-index, impact factor, and collaboration metrics.
Results: Altogether, 7534 publications were initially retrieved and 2775 were included for analysis. The annual count and citation of papers exhibited exponential trends since 2018. The United States emerged as the lead contributor due to its high productivity and recognition levels. Stanford University, Johns Hopkins University, National University of Singapore, Mayo Clinic, University of Arizona, and University of Toronto were representative institutions in their respective fields. Cureus, JMIR Medical Education, Medical Teacher, and BMC Medical Education ranked as the top four most productive journals. The resulting heat map highlighted several high-frequency keywords, including performance, education, AI, and model. The citation burst time of terms revealed that AI technologies shifted from imaging processing (2000), augmented reality (2013), and virtual reality (2016) to decision-making (2020) and model (2021). Keywords such as mortality and robotic surgery persisted into 2023, suggesting the ongoing recognition and interest in these areas.
Conclusions: This study provides valuable insights and guidance for researchers who are interested in educational technology, as well as recommendations for pioneering institutions and journal submissions. Along with the rapid growth of AI, medical education is expected to gain much more benefits.},
	language = {EN},
	number = {1},
	urldate = {2025-02-25},
	journal = {Interactive Journal of Medical Research},
	publisher = {JMIR Publications Inc., Toronto, Canada},
	author = {Li, Rui and Wu, Tong},
	month = jan,
	year = {2025},
	note = {Company: Interactive Journal of Medical Research
Distributor: Interactive Journal of Medical Research
Institution: Interactive Journal of Medical Research
Label: Interactive Journal of Medical Research},
	pages = {e63775},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/TY4E8WQN/e63775.html:text/html},
}

@article{bajric2023building,
	title = {Building a {Sustainable} {Ecosystem} for {eHealth} in {Slovenia}: {Opportunities}, {Challenges}, and {Strategies}},
	volume = {9},
	issn = {2055-2076},
	shorttitle = {Building a {Sustainable} {Ecosystem} for {eHealth} in {Slovenia}},
	url = {https://doi.org/10.1177/20552076231205743},
	doi = {10.1177/20552076231205743},
	abstract = {The pandemic COVID-19 has shown us how important it is for medical teams to have access to all patient data, to be able to implement appropriate guidelines, and to adapt as easily as possible to new challenges. This paper explores the implementation of an open platform within Slovenia’s healthcare backbone and identifies requisite elements for bolstering a national healthcare ecosystem. A gap analysis between the Slovenian open platform and Apperta’s specifications has revealed discrepancies. Through addressing this gap and examining backbone challenges, a preliminary list of success factors has been identified. These insights not only inform the establishment of a resilient national healthcare ecosystem but also contribute to a broader comprehension and execution of digital transformation within healthcare systems.},
	language = {en},
	urldate = {2025-02-25},
	journal = {DIGITAL HEALTH},
	publisher = {SAGE Publications Ltd},
	author = {Bajrić, Samed},
	month = jan,
	year = {2023},
	pages = {20552076231205743},
	file = {SAGE PDF Full Text:/Users/dkapitan/Zotero/storage/LFPB7KZM/Bajrić - 2023 - Building a Sustainable Ecosystem for eHealth in Slovenia Opportunities, Challenges, and Strategies.pdf:application/pdf},
}

@article{nguyen2024preserving,
	title = {Preserving {Privacy} and {Security} in {Federated} {Learning}},
	volume = {32},
	issn = {1558-2566},
	url = {https://ieeexplore.ieee.org/abstract/document/10230990?casa_token=zDfZVLOccjEAAAAA:0j-V9O7Y4L36ELDLhYvO_8AKBb_p2GvVgChFfwoVialkWULXR4LDNA3XQA_aSIHwWCo4pVY-ag},
	doi = {10.1109/TNET.2023.3302016},
	abstract = {Federated learning is known to be vulnerable to both security and privacy issues. Existing research has focused either on preventing poisoning attacks from users or on concealing the local model updates from the server, but not both. However, integrating these two lines of research remains a crucial challenge since they often conflict with one another with respect to the threat model. In this work, we develop a principle framework that offers both privacy guarantees for users and detection against poisoning attacks from them. With a new threat model that includes both an honest-but-curious server and malicious users, we first propose a secure aggregation protocol using homomorphic encryption for the server to combine local model updates in a private manner. Then, a zero-knowledge proof protocol is leveraged to shift the task of detecting attacks in the local models from the server to the users. The key observation here is that the server no longer needs access to the local models for attack detection. Therefore, our framework enables the central server to identify poisoned model updates without violating the privacy guarantees of secure aggregation.},
	number = {1},
	urldate = {2025-02-26},
	journal = {IEEE/ACM Transactions on Networking},
	author = {Nguyen, Truc and Thai, My T.},
	month = feb,
	year = {2024},
	note = {Conference Name: IEEE/ACM Transactions on Networking},
	keywords = {Privacy, Protocols, Security, Computational modeling, Training, Servers, Federated learning, homomorphic encryption, model poisoning, zero-knowledge proof},
	pages = {833--843},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/3LXNYXIL/Nguyen and Thai - 2024 - Preserving Privacy and Security in Federated Learning.pdf:application/pdf;IEEE Xplore Abstract Record:/Users/dkapitan/Zotero/storage/NU95CMZW/10230990.html:text/html},
}

@article{mosterd2021context,
	title = {Context dependent trade-offs around platform-to-platform openness: {The} case of the {Internet} of {Things}},
	volume = {108},
	issn = {0166-4972},
	shorttitle = {Context dependent trade-offs around platform-to-platform openness},
	url = {https://www.sciencedirect.com/science/article/pii/S0166497221001127},
	doi = {10.1016/j.technovation.2021.102331},
	abstract = {As digital platforms are dominating the digital economy, complex ecologies of platforms are emerging. While the openness of digital platforms is an important theme in platform studies, the openness between platforms has hardly been studied. This paper explores factors that affect decisions by platform owners to open their platforms to other platforms. The focus is on Internet-of-Things platforms for automotive and healthcare applications. According to the findings, platform owners make trade-offs on whether to open up on a case-by-case basis. We identify a complex array of factors relating to direct benefits and costs (e.g., revenues from selling platform data), indirect benefits (e.g., attractiveness of the focal platform to users) as well as strategic consideration (e.g., improving bargaining power towards other actors). How businesses make trade-offs on these factors depends on market-level context (e.g., maturity of the market and standards) and organizational context (e.g., strategic focus and business objectives). Our findings provide a basis for future studies on the openness between platforms, which will become increasingly important as platforms proliferate in every layer of the digital industry.},
	urldate = {2025-02-27},
	journal = {Technovation},
	author = {Mosterd, Lars and Sobota, Vladimir C. M. and van de Kaa, Geerten and Ding, Aaron Yi and de Reuver, Mark},
	month = dec,
	year = {2021},
	keywords = {Digital platforms, Internet-of-Things, Platform openness},
	pages = {102331},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/J5ERE7WZ/Mosterd et al. - 2021 - Context dependent trade-offs around platform-to-platform openness The case of the Internet of Thing.pdf:application/pdf;ScienceDirect Snapshot:/Users/dkapitan/Zotero/storage/HMQKGZDE/S0166497221001127.html:text/html},
}

@article{demello2022semantica,
	title = {Semantic interoperability in health records standards: a systematic literature review},
	volume = {12},
	issn = {2190-7188},
	shorttitle = {Semantic interoperability in health records standards},
	url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8791650/},
	doi = {10.1007/s12553-022-00639-w},
	abstract = {The integration and exchange of information among health organizations and system providers are currently regarded as a challenge. Each organization usually has an internal ecosystem and a proprietary way to store electronic health records of the patient’s history. Recent research explores the advantages of an integrated ecosystem by exchanging information between the different inpatient care actors. Many efforts seek quality in health care, economy, and sustainability in process management. Some examples are reducing medical errors, disease control and monitoring, individualized patient care, and avoiding duplicate and fragmented entries in the electronic medical record. Likewise, some studies showed technologies to achieve this goal effectively and efficiently, with the ability to interoperate data, allowing the interpretation and use of health information. To that end, semantic interoperability aims to share data among all the sectors in the organization, clinicians, nurses, lab, the entire hospital. Therefore, avoiding data silos and keep data regardless of vendors, to exchange the information across organizational boundaries. This study presents a comprehensive systematic literature review of semantic interoperability in electronic health records. We searched seven databases of articles published between 2010 to September 2020. We showed the most chosen scenarios, technologies, and tools employed to solve interoperability problems, and we propose a taxonomy around semantic interoperability in health records. Also, we presented the main approaches to solve the exchange problem of legacy and heterogeneous data across healthcare organizations.},
	number = {2},
	urldate = {2025-03-07},
	journal = {Health and Technology},
	author = {de Mello, Blanda Helena and Rigo, Sandro José and da Costa, Cristiano André and da Rosa Righi, Rodrigo and Donida, Bruna and Bez, Marta Rosecler and Schunke, Luana Carina},
	year = {2022},
	pages = {255--272},
	file = {PubMed Central Full Text PDF:/Users/dkapitan/Zotero/storage/XK35IJIG/de Mello et al. - 2022 - Semantic interoperability in health records standards a systematic literature review.pdf:application/pdf},
}

@article{zhang2024crossstandard,
	title = {Cross-{Standard} {Health} {Data} {Harmonization} using {Semantics} of {Data} {Elements}},
	volume = {11},
	copyright = {2024 The Author(s)},
	issn = {2052-4463},
	url = {https://www.nature.com/articles/s41597-024-04168-1},
	doi = {10.1038/s41597-024-04168-1},
	abstract = {Faced with heterogeneity of healthcare data, we propose a novel approach for harmonizing data elements (i.e., attributes) across health data standards. This approach focuses on the implicit concept that is represented by a data element. The process includes the following steps: identifying concepts, clustering similar concepts and constructing mappings between the clusters using the Simple Standard for Sharing Ontological Mappings (SSSOM) and Resource Description Framework (RDF), and enabling the creation of reusable mappings. As proof-of-concept, we applied the approach to five common health data standards - HL7 FHIR, OMOP, CDISC, Phenopackets, and openEHR, across four domains, such as demographics and diagnoses, and nine topics within those domains, such as gender and vital status. These domains and topics are selected to represent the broader range of topics in the health field. For each topic, data elements were found in the health data standards after a thorough search, resulting in the analysis of 64 data elements, identification of their underlying concepts, and development of mappings. Three use cases were implemented to demonstrate the role of data element concepts in data harmonization and data querying at varying levels of granularity. The approach helps overcome the limitations of context-dependent mappings and provides valuable insight for mapping practice within the health domain.},
	language = {en},
	number = {1},
	urldate = {2025-03-07},
	journal = {Scientific Data},
	publisher = {Nature Publishing Group},
	author = {Zhang, Shuxin and Cornet, Ronald and Benis, Nirupama},
	month = dec,
	year = {2024},
	keywords = {Databases, Standards, Data integration},
	pages = {1407},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/VWK3SH33/Zhang et al. - 2024 - Cross-Standard Health Data Harmonization using Semantics of Data Elements.pdf:application/pdf},
}

@article{vorisek2024interoperability,
	title = {Towards an {Interoperability} {Landscape} for a {National} {Research} {Data} {Infrastructure} for {Personal} {Health} {Data}},
	volume = {11},
	copyright = {2024 The Author(s)},
	issn = {2052-4463},
	url = {https://www.nature.com/articles/s41597-024-03615-3},
	doi = {10.1038/s41597-024-03615-3},
	abstract = {The German initiative “National Research Data Infrastructure for Personal Health Data” (NFDI4Health) focuses on research data management in health research. It aims to foster and develop harmonized informatics standards for public health, epidemiological studies, and clinical trials, facilitating access to relevant data and metadata standards. This publication lists syntactic and semantic data standards of potential use for NFDI4Health and beyond, based on interdisciplinary meetings and workshops, mappings of study questionnaires and the NFDI4Health metadata schema, and literature search. Included are 7 syntactic, 32 semantic and 9 combined syntactic and semantic standards. In addition, 101 ISO Standards from ISO/TC 215 Health Informatics and ISO/TC 276 Biotechnology could be identified as being potentially relevant. The work emphasizes the utilization of standards for epidemiological and health research data ensuring interoperability as well as the compatibility to NFDI4Health, its use cases, and to (inter-)national efforts within these sectors. The goal is to foster collaborative and inter-sectoral work in health research and initiate a debate around the potential of using common standards.},
	language = {en},
	number = {1},
	urldate = {2025-03-08},
	journal = {Scientific Data},
	publisher = {Nature Publishing Group},
	author = {Vorisek, Carina Nina and Klopfenstein, Sophie Anne Inès and Löbe, Matthias and Schmidt, Carsten Oliver and Mayer, Paula Josephine and Golebiewski, Martin and Thun, Sylvia},
	month = jul,
	year = {2024},
	keywords = {Epidemiology, Public health},
	pages = {772},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/KFECN9A7/Vorisek et al. - 2024 - Towards an Interoperability Landscape for a National Research Data Infrastructure for Personal Healt.pdf:application/pdf},
}

@article{milne2022concentric,
	title = {A concentric circles view of health data relations facilitates understanding of sociotechnical challenges for learning health systems and the role of federated data networks},
	volume = {5},
	issn = {2624-909X},
	url = {https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2022.945739/full},
	doi = {10.3389/fdata.2022.945739},
	abstract = {{\textless}p{\textgreater}The ability to use clinical and research data at scale is central to hopes for data-driven medicine. However, in using such data researchers often encounter hurdles–both technical, such as differing data security requirements, and social, such as the terms of informed consent, legal requirements and patient and public trust. Federated or distributed data networks have been proposed and adopted in response to these hurdles. However, to date there has been little consideration of how FDNs respond to both technical and social constraints on data use. In this Perspective we propose an approach to thinking about data in terms that make it easier to navigate the health data space and understand the value of differing approaches to data collection, storage and sharing. We set out a {\textless}italic{\textgreater}socio-technical{\textless}/italic{\textgreater} model of data systems that we call the “Concentric Circles View” (CCV) of data-relationships. The aim is to enable a consistent understanding of the fit between the local relationships within which data are produced and the extended socio-technical systems that enable their use. The paper suggests this model can help understand and tackle challenges associated with the use of real-world data in the health setting. We use the model to understand not only how but {\textless}italic{\textgreater}why{\textless}/italic{\textgreater} federated networks may be well placed to address emerging issues and adapt to the evolving needs of health research for patient benefit. We conclude that the CCV provides a useful model with broader application in mapping, understanding, and tackling the major challenges associated with using real world data in the health setting.{\textless}/p{\textgreater}},
	language = {English},
	urldate = {2025-03-11},
	journal = {Frontiers in Big Data},
	publisher = {Frontiers},
	author = {Milne, Richard and Sheehan, Mark and Barnes, Brendan and Kapper, Janek and Lea, Nathan and N'Dow, James and Singh, Gurparkash and Martín-Uranga, Amelia and Hughes, Nigel},
	month = sep,
	year = {2022},
	keywords = {Consent, Ethics, Data, Distributed data access, Federated data access},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/EGIDJMR8/Milne et al. - 2022 - A concentric circles view of health data relations facilitates understanding of sociotechnical chall.pdf:application/pdf},
}

@article{sheller2020federated,
	title = {Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data},
	volume = {10},
	copyright = {2020 The Author(s)},
	issn = {2045-2322},
	shorttitle = {Federated learning in medicine},
	url = {https://www.nature.com/articles/s41598-020-69250-1},
	doi = {10.1038/s41598-020-69250-1},
	abstract = {Several studies underscore the potential of deep learning in identifying complex patterns, leading to diagnostic and prognostic biomarkers. Identifying sufficiently large and diverse datasets, required for training, is a significant challenge in medicine and can rarely be found in individual institutions. Multi-institutional collaborations based on centrally-shared patient data face privacy and ownership challenges. Federated learning is a novel paradigm for data-private multi-institutional collaborations, where model-learning leverages all available data without sharing data between institutions, by distributing the model-training to the data-owners and aggregating their results. We show that federated learning among 10 institutions results in models reaching 99\% of the model quality achieved with centralized data, and evaluate generalizability on data from institutions outside the federation. We further investigate the effects of data distribution across collaborating institutions on model quality and learning patterns, indicating that increased access to data through data private multi-institutional collaborations can benefit model quality more than the errors introduced by the collaborative method. Finally, we compare with other collaborative-learning approaches demonstrating the superiority of federated learning, and discuss practical implementation considerations. Clinical adoption of federated learning is expected to lead to models trained on datasets of unprecedented size, hence have a catalytic impact towards precision/personalized medicine.},
	language = {en},
	number = {1},
	urldate = {2025-03-12},
	journal = {Scientific Reports},
	publisher = {Nature Publishing Group},
	author = {Sheller, Micah J. and Edwards, Brandon and Reina, G. Anthony and Martin, Jason and Pati, Sarthak and Kotrotsou, Aikaterini and Milchenko, Mikhail and Xu, Weilin and Marcus, Daniel and Colen, Rivka R. and Bakas, Spyridon},
	month = jul,
	year = {2020},
	keywords = {Health care, Medical imaging, Computational science, Biomedical engineering, Scientific data, Brain imaging, Cancer, CNS cancer},
	pages = {12598},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/C2UB2PZW/Sheller et al. - 2020 - Federated learning in medicine facilitating multi-institutional collaborations without sharing pati.pdf:application/pdf},
}

@article{guerin2021osiris,
	title = {{OSIRIS}: {A} {Minimum} {Data} {Set} for {Data} {Sharing} and {Interoperability} in {Oncology}},
	shorttitle = {{OSIRIS}},
	url = {https://ascopubs.org/doi/10.1200/CCI.20.00094},
	doi = {10.1200/CCI.20.00094},
	abstract = {PurposeMany institutions throughout the world have launched precision medicine initiatives in oncology, and a large amount of clinical and genomic data is being produced. Although there have been attempts at data sharing with the community, initiatives are still limited. In this context, a French task force composed of Integrated Cancer Research Sites (SIRICs), comprehensive cancer centers from the Unicancer network (one of Europe's largest cancer research organization), and university hospitals launched an initiative to improve and accelerate retrospective and prospective clinical and genomic data sharing in oncology.Materials and MethodsFor 5 years, the OSIRIS group has worked on structuring data and identifying technical solutions for collecting and sharing them. The group used a multidisciplinary approach that included weekly scientific and technical meetings over several months to foster a national consensus on a minimal data set.ResultsThe resulting OSIRIS set and event-based data model, which is able to capture the disease course, was built with 67 clinical and 65 omics items. The group made it compatible with the HL7 Fast Healthcare Interoperability Resources (FHIR) format to maximize interoperability. The OSIRIS set was reviewed, approved by a National Plan Strategic Committee, and freely released to the community. A proof-of-concept study was carried out to put the OSIRIS set and Common Data Model into practice using a cohort of 300 patients.ConclusionUsing a national and bottom-up approach, the OSIRIS group has defined a model including a minimal set of clinical and genomic data that can be used to accelerate data sharing produced in oncology. The model relies on clear and formally defined terminologies and, as such, may also benefit the larger international community.},
	number = {5},
	urldate = {2025-03-12},
	journal = {JCO Clinical Cancer Informatics},
	publisher = {Wolters Kluwer},
	author = {Guérin, Julien and Laizet, Yec'han and Le Texier, Vincent and Chanas, Laetitia and Rance, Bastien and Koeppel, Florence and Lion, François and Gourgou, Sophie and Martin, Anne-Laure and Tejeda, Manuel and Toulmonde, Maud and Cox, Stéphanie and Hess, Elisabeth and Rousseau-Tsangaris, Marina and Jouhet, Vianney and Saintigny, Pierre},
	month = mar,
	year = {2021},
	pages = {256--265},
	file = {Full Text:/Users/dkapitan/Zotero/storage/73Z7ZZ58/Guérin et al. - 2021 - OSIRIS A Minimum Data Set for Data Sharing and Interoperability in Oncology.pdf:application/pdf},
}

@article{riedel2024comparative,
	title = {Comparative analysis of open-source federated learning frameworks - a literature-based survey and review},
	volume = {15},
	issn = {1868-808X},
	url = {https://doi.org/10.1007/s13042-024-02234-z},
	doi = {10.1007/s13042-024-02234-z},
	abstract = {While Federated Learning (FL) provides a privacy-preserving approach to analyze sensitive data without centralizing training data, the field lacks an detailed comparison of emerging open-source FL frameworks. Furthermore, there is currently no standardized, weighted evaluation scheme for a fair comparison of FL frameworks that would support the selection of a suitable FL framework. This study addresses these research gaps by conducting a comparative analysis of 15 individual open-source FL frameworks filtered by two selection criteria, using the literature review methodology proposed by Webster and Watson. These framework candidates are compared using a novel scoring schema with 15 qualitative and quantitative evaluation criteria, focusing on features, interoperability, and user friendliness. The evaluation results show that the FL framework Flower outperforms its peers with an overall score of 84.75\%, while Fedlearner lags behind with a total score of 24.75\%. The proposed comparison suite offers valuable initial guidance for practitioners and researchers in selecting an FL framework for the design and development of FL-driven systems. In addition, the FL framework comparison suite is designed to be adaptable and extendable accommodating the inclusion of new FL frameworks and evolving requirements.},
	language = {en},
	number = {11},
	urldate = {2025-03-12},
	journal = {International Journal of Machine Learning and Cybernetics},
	author = {Riedel, Pascal and Schick, Lukas and von Schwerin, Reinhold and Reichert, Manfred and Schaudt, Daniel and Hafner, Alexander},
	month = nov,
	year = {2024},
	keywords = {Privacy, Machine learning, Artificial Intelligence, Open source, Federated learning, Framework comparison},
	pages = {5257--5278},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/UQ59Z4XJ/Riedel et al. - 2024 - Comparative analysis of open-source federated learning frameworks - a literature-based survey and re.pdf:application/pdf},
}

@article{abouzaid2025building,
	title = {Building a modern data platform based on the data lakehouse architecture and cloud-native ecosystem},
	volume = {7},
	issn = {3004-9261},
	url = {https://doi.org/10.1007/s42452-025-06545-w},
	doi = {10.1007/s42452-025-06545-w},
	abstract = {In today’s Big Data world, organisations can gain a competitive edge by adopting data-driven decision-making. However, a modern data platform that is portable, resilient, and efficient is required to manage organisations’ data and support their growth. Furthermore, the change in the data management architectures has been accompanied by changes in storage formats, particularly open standard formats like Apache Hudi, Apache Iceberg, and Delta Lake. With many alternatives, organisations are unclear on how to combine these into an effective platform. Our work investigates capabilities provided by Kubernetes and other Cloud-Native software, using DataOps methodologies to build a generic data platform that follows the Data Lakehouse architecture. We define the data platform specification, architecture, and core components to build a proof of concept system. Moreover, we provide a clear implementation methodology by developing the core of the proposed platform, which are infrastructure (Kubernetes), ingestion and transport (Argo Workflows), storage (MinIO), and finally, query and processing (Dremio). We then conducted performance benchmarks using an industry-standard benchmark suite to compare cold/warm start scenarios and assess Dremio’s caching capabilities, demonstrating a 12\% median enhancement of query duration with caching.},
	language = {en},
	number = {3},
	urldate = {2025-03-16},
	journal = {Discover Applied Sciences},
	author = {AbouZaid, Ahmed and Barclay, Peter J. and Chrysoulas, Christos and Pitropakis, Nikolaos},
	month = feb,
	year = {2025},
	keywords = {Big Data, Artificial Intelligence, Data Lakehouse, Cloud-Native, DataOps, Kubernetes},
	pages = {166},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/DMLA553M/AbouZaid et al. - 2025 - Building a modern data platform based on the data lakehouse architecture and cloud-native ecosystem.pdf:application/pdf},
}

@article{schneider2024lakehouse,
	title = {The {Lakehouse}: {State} of the {Art} on {Concepts} and {Technologies}},
	volume = {5},
	issn = {2661-8907},
	shorttitle = {The {Lakehouse}},
	url = {https://doi.org/10.1007/s42979-024-02737-0},
	doi = {10.1007/s42979-024-02737-0},
	abstract = {In the context of data analytics, so-called lakehouses refer to novel variants of data platforms that attempt to combine characteristics of data warehouses and data lakes. In this way, lakehouses promise to simplify enterprise analytics architectures, which often suffer from high operational costs, slow analytical processes and further shortcomings resulting from data replication. However, different views and notions on the lakehouse paradigm exist, which are commonly driven by individual technologies and varying analytical use cases. Therefore, it remains unclear what challenges lakehouses address, how they can be characterized and which technologies can be leveraged to implement them. This paper addresses these issues by providing an extensive overview of concepts and technologies that are related to the lakehouse paradigm and by outlining lakehouses as a distinct architectural approach for data platforms. Concepts and technologies from literature with regard to lakehouses are discussed, based on which a conceptual foundation for lakehouses is established. In addition, several popular technologies are evaluated regarding their suitability for the building of lakehouses. All findings are supported and demonstrated with the help of a representative analytics scenario. Typical challenges of conventional data platforms are identified, a new, sharper definition for lakehouses is proposed and technical requirements for lakehouses are derived. As part of an evaluation, these requirements are applied to several popular technologies, of which frameworks for data lakes turn out to be particularly helpful for the construction of lakehouses. Our work provides an overview of the state of the art and a conceptual foundation for the lakehouse paradigm, which can support future research.},
	language = {en},
	number = {5},
	urldate = {2025-03-16},
	journal = {SN Computer Science},
	author = {Schneider, Jan and Gröger, Christoph and Lutsch, Arnold and Schwarz, Holger and Mitschang, Bernhard},
	month = apr,
	year = {2024},
	keywords = {Data analytics, Data lake, Data lakehouse, Data platform},
	pages = {449},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/PKXBJ9LC/Schneider et al. - 2024 - The Lakehouse State of the Art on Concepts and Technologies.pdf:application/pdf},
}

@article{harby2025data,
	title = {Data {Lakehouse}: {A} survey and experimental study},
	volume = {127},
	issn = {03064379},
	shorttitle = {Data {Lakehouse}},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0306437924001182},
	doi = {10.1016/j.is.2024.102460},
	abstract = {Efficient big data management is a dire necessity to manage the exponential growth in data generated by digital information systems to produce usable knowledge. Structured databases, data lakes, and warehouses have each provided a solution with varying degrees of success. However, a new and superior solution, the data Lakehouse, has emerged to extract actionable insights from unstructured data ingested from distributed sources. By combining the strengths of data warehouses and data lakes, the data Lakehouse can process and merge data quickly while ingesting and storing high-speed unstructured data with post-storage transformation and analytics capabilities. The Lakehouse architecture offers the necessary features for optimal functionality and has gained significant attention in the big data management research community. In this paper, we compare data lake, warehouse, and lakehouse systems, highlight their strengths and shortcomings, identify the desired features to handle the evolving challenges in big data management and analysis and propose an advanced data Lakehouse architecture. We also demonstrate the performance of three state-of-the-art data management systems namely HDFS data lake, Hive data warehouse, and Delta lakehouse in managing data for analytical query responses through an experimental study.},
	language = {en},
	urldate = {2025-03-16},
	journal = {Information Systems},
	author = {Harby, Ahmed A. and Zulkernine, Farhana},
	month = jan,
	year = {2025},
	pages = {102460},
	file = {PDF:/Users/dkapitan/Zotero/storage/YG5UJM8Z/Harby and Zulkernine - 2025 - Data Lakehouse A survey and experimental study.pdf:application/pdf},
}

@article{leroux2017achieving,
	title = {Towards achieving semantic interoperability of clinical study data with {FHIR}},
	volume = {8},
	issn = {2041-1480},
	url = {http://jbiomedsem.biomedcentral.com/articles/10.1186/s13326-017-0148-7},
	doi = {10.1186/s13326-017-0148-7},
	abstract = {Background: Observational clinical studies play a pivotal role in advancing medical knowledge and patient healthcare. To lessen the prohibitive costs of conducting these studies and support evidence-based medicine, results emanating from these studies need to be shared and compared to one another. Current approaches for clinical study management have limitations that prohibit the effective sharing of clinical research data.
Methods: The objective of this paper is to present a proposal for a clinical study architecture to not only facilitate the communication of clinical study data but also its context so that the data that is being communicated can be unambiguously understood at the receiving end. Our approach is two-fold. First we outline our methodology to map clinical data from Clinical Data Interchange Standards Consortium Operational Data Model (ODM) to the Fast Healthcare Interoperable Resource (FHIR) and outline the strengths and weaknesses of this approach. Next, we propose two FHIR-based models, to capture the metadata and data from the clinical study, that not only facilitate the syntactic but also semantic interoperability of clinical study data.
Conclusions: This work shows that our proposed FHIR resources provide a good fit to semantically enrich the ODM data. By exploiting the rich information model in FHIR, we can organise clinical data in a manner that preserves its organisation but captures its context. Our implementations demonstrate that FHIR can natively manage clinical data. Furthermore, by providing links at several levels, it improves the traversal and querying of the data. The intended benefits of this approach is more efficient and effective data exchange that ultimately will allow clinicians to switch their focus back to decision-making and evidence-based medicines.},
	language = {en},
	number = {1},
	urldate = {2025-03-24},
	journal = {Journal of Biomedical Semantics},
	author = {Leroux, Hugo and Metke-Jimenez, Alejandro and Lawley, Michael J.},
	month = dec,
	year = {2017},
	pages = {41},
	file = {PDF:/Users/dkapitan/Zotero/storage/336XH4TF/Leroux et al. - 2017 - Towards achieving semantic interoperability of clinical study data with FHIR.pdf:application/pdf},
}

@article{vandervlist2024big,
	title = {Big {AI}: {Cloud} infrastructure dependence and the industrialisation of artificial intelligence},
	volume = {11},
	issn = {2053-9517},
	shorttitle = {Big {AI}},
	url = {https://doi.org/10.1177/20539517241232630},
	doi = {10.1177/20539517241232630},
	abstract = {Critical scholars contend that ‘There is no AI without Big Tech’. This study delves into the substantial role played by major technology conglomerates, including Amazon, Microsoft, and Google (Alphabet), in the ‘industrialisation of artificial intelligence’. This concept encapsulates the shift of AI technologies from the research and development stage to practical, real-world applications across diverse industry sectors, resulting in new dependencies and associated investments. We employ the term ‘Big AI’ to encapsulate the structural convergence of AI and Big Tech, characterised by the profound interdependence of AI with the infrastructure, resources, and investments of these major technology companies. Using a ‘technographic’ approach, our study scrutinises the infrastructural support and investments of Big Tech in the AI sector, focussing on corporate partnerships, acquisitions, and financial investments. Additionally, we conduct a detailed examination of the complete spectrum of cloud platform products and services offered by Amazon, Microsoft, and Google. We demonstrate that AI is not merely an abstract idea but an actual technology stack encompassing infrastructure, models, applications, and an ecosystem of applications and companies relying on this stack. Significantly, these tech giants have seamlessly integrated all three components of the stack into their cloud offerings. Furthermore, they have developed industry-focussed solutions and marketplaces aimed at attracting third-party developers and businesses, fostering the growth of a broader AI ecosystem. This analysis underscores the intricate interdependence between AI and cloud infrastructure, emphasising the industry-specific aspects of cloud AI.},
	language = {EN},
	number = {1},
	urldate = {2025-03-28},
	journal = {Big Data \& Society},
	publisher = {SAGE Publications Ltd},
	author = {van der Vlist, Fernando and Helmond, Anne and Ferrari, Fabian},
	month = mar,
	year = {2024},
	pages = {20539517241232630},
	file = {SAGE PDF Full Text:/Users/dkapitan/Zotero/storage/QGSP68CJ/van der Vlist et al. - 2024 - Big AI Cloud infrastructure dependence and the industrialisation of artificial intelligence.pdf:application/pdf},
}

@article{vandervlist2021how,
	title = {How partners mediate platform power: {Mapping} business and data partnerships in the social media ecosystem},
	volume = {8},
	issn = {2053-9517},
	shorttitle = {How partners mediate platform power},
	url = {https://doi.org/10.1177/20539517211025061},
	doi = {10.1177/20539517211025061},
	abstract = {Social media platforms’ digital advertising revenues depend considerably on partnerships. Business partnerships are endemic and essential to the business of platforms, yet their role remains relatively underexplored in the literature on platformisation and platform power. This article considers the significance of partnerships in the social media ecosystem to better understand how industry platforms, and the infrastructure they build, mediate and shape platform power and governance. We argue that partners contribute to ‘platformisation’ through their collective development of business-to-business platform infrastructures. Specifically, we examine how partners have integrated social media platforms with what we call the audience economy – an exceptionally complex global and interconnected marketplace of intermediaries involved in the creation, commodification, analysis, and circulation of data audiences for purposes including but not limited to digital advertising and marketing. We determined which relationships are involved, which are exclusive or shared, and identified key ecosystem partners. Further, we found that partners build and integrate extensive infrastructures for data-sourcing and media distribution, surfacing infrastructural and strategic sources and locations, or ‘nodes’, of power in this ecosystem. The empirical findings thus highlight the significance of partnerships and partner integrations and draw attention to the powerful industry players and intermediaries that remain largely invisible.},
	language = {EN},
	number = {1},
	urldate = {2025-03-28},
	journal = {Big Data \& Society},
	publisher = {SAGE Publications Ltd},
	author = {van der Vlist, Fernando N and Helmond, Anne},
	month = jan,
	year = {2021},
	pages = {20539517211025061},
	file = {SAGE PDF Full Text:/Users/dkapitan/Zotero/storage/FNBZHXJT/van der Vlist and Helmond - 2021 - How partners mediate platform power Mapping business and data partnerships in the social media ecos.pdf:application/pdf},
}

@article{bernabe2024building,
	title = {Building {Expertise} on {FAIR} {Through} {Evolving} {Bring} {Your} {Own} {Data} ({BYOD}) {Workshops}: {Describing} the {Data}, {Software}, and {Management}-focused {Approaches} and {Their} {Evolution}},
	volume = {6},
	issn = {2641-435X},
	shorttitle = {Building {Expertise} on {FAIR} {Through} {Evolving} {Bring} {Your} {Own} {Data} ({BYOD}) {Workshops}},
	url = {https://doi.org/10.1162/dint_a_00236},
	doi = {10.1162/dint_a_00236},
	abstract = {Since 2014, “Bring Your Own Data” workshops (BYODs) have been organised to inform people about the process and benefits of making resources Findable, Accessible, Interoperable, and Reusable (FAIR, and the FAIRification process). The BYOD workshops’ content and format differ depending on their goal, context, and the background and needs of participants. Data-focused BYODs educate domain experts on how to make their data FAIR to find new answers to research questions. Management-focused BYODs promote the benefits of making data FAIR and instruct project managers and policy-makers on the characteristics of FAIRification projects. Software-focused BYODs gather software developers and experts on FAIR to implement or improve software resources that are used to support FAIRification. Overall, these BYODs intend to foster collaboration between different types of stakeholders involved in data management, curation, and reuse (e.g. domain experts, trainers, developers, data owners, data analysts, FAIR experts). The BYODs also serve as an opportunity to learn what kind of support for FAIRification is needed from different communities and to develop teaching materials based on practical examples and experience. In this paper, we detail the three different structures of the BYODs and describe examples of early BYODs related to plant breeding data, and rare disease registries and biobanks, which have shaped the structure of the workshops. We discuss the latest insights into making BYODs more productive by leveraging our almost ten years of training experience in these workshops, including successes and encountered challenges. Finally, we examine how the participants’ feedback has motivated the research on FAIR, including the development of workflows and software.},
	number = {2},
	urldate = {2025-03-31},
	journal = {Data Intelligence},
	author = {Bernabé, César H. and Thielemans, Lieze and Kaliyaperumal, Rajaram and Carta, Claudio and Zhang, Shuxin and van Gelder, Celia W.G. and Benis, Nirupama and da Silva Santos, Luiz Olavo Bonino and Cornet, Ronald and dos Santos Vieira, Bruna and Lalout, Nawel and Henriques, Ines and Ballesteros, Alberto Cámara and Burger, Kees and Kersloot, Martijn G. and Ehrhart, Friederike and van Enckevort, Esther and Evelo, Chris T. and Gray, Alasdair J. G. and Hanauer, Marc and Hettne, Kristina and de Ligt, Joep and Pereira, Arnaldo and Queralt-Rosinach, Núria and Schultes, Erik and Taruscio, Domenica and Waagmeester, Andra and Wilkinson, Mark D. and Willighagen, Egon L. and Jansen, Mascha and Mons, Barend and Roos, Marco and Jacobsen, Annika},
	month = may,
	year = {2024},
	pages = {429--456},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/WR6W5VJL/Bernabé et al. - 2024 - Building Expertise on FAIR Through Evolving Bring Your Own Data (BYOD) Workshops Describing the Dat.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/UCP6IQ4L/Building-Expertise-on-FAIR-Through-Evolving-Bring.html:text/html},
}

@article{welten2024study,
	title = {A study on interoperability between two {Personal} {Health} {Train} infrastructures in leukodystrophy data analysis},
	volume = {11},
	copyright = {2024 The Author(s)},
	issn = {2052-4463},
	url = {https://www.nature.com/articles/s41597-024-03450-6},
	doi = {10.1038/s41597-024-03450-6},
	abstract = {The development of platforms for distributed analytics has been driven by a growing need to comply with various governance-related or legal constraints. Among these platforms, the so-called Personal Health Train (PHT) is one representative that has emerged over the recent years. However, in projects that require data from sites featuring different PHT infrastructures, institutions are facing challenges emerging from the combination of multiple PHT ecosystems, including data governance, regulatory compliance, or the modification of existing workflows. In these scenarios, the interoperability of the platforms is preferable. In this work, we introduce a conceptual framework for the technical interoperability of the PHT covering five essential requirements: Data integration, unified station identifiers, mutual metadata, aligned security protocols, and business logic. We evaluated our concept in a feasibility study that involves two distinct PHT infrastructures: PHT-meDIC and PADME. We analyzed data on leukodystrophy from patients in the University Hospitals of Tübingen and Leipzig, and patients with differential diagnoses at the University Hospital Aachen. The results of our study demonstrate the technical interoperability between these two PHT infrastructures, allowing researchers to perform analyses across the participating institutions. Our method is more space-efficient compared to the multi-homing strategy, and it shows only a minimal time overhead.},
	language = {en},
	number = {1},
	urldate = {2025-03-31},
	journal = {Scientific Data},
	publisher = {Nature Publishing Group},
	author = {Welten, Sascha and de Arruda Botelho Herr, Marius and Hempel, Lars and Hieber, David and Placzek, Peter and Graf, Michael and Weber, Sven and Neumann, Laurenz and Jugl, Maximilian and Tirpitz, Liam and Kindermann, Karl and Geisler, Sandra and Bonino da Silva Santos, Luiz Olavo and Decker, Stefan and Pfeifer, Nico and Kohlbacher, Oliver and Kirsten, Toralf},
	month = jun,
	year = {2024},
	keywords = {Health care, Research data},
	pages = {663},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/GW28S4JR/Welten et al. - 2024 - A study on interoperability between two Personal Health Train infrastructures in leukodystrophy data.pdf:application/pdf},
}

@article{moore2023omezarr,
	title = {{OME}-{Zarr}: a cloud-optimized bioimaging file format with international community support},
	volume = {160},
	issn = {1432-119X},
	shorttitle = {{OME}-{Zarr}},
	url = {https://doi.org/10.1007/s00418-023-02209-1},
	doi = {10.1007/s00418-023-02209-1},
	abstract = {A growing community is constructing a next-generation file format (NGFF) for bioimaging to overcome problems of scalability and heterogeneity. Organized by the Open Microscopy Environment (OME), individuals and institutes across diverse modalities facing these problems have designed a format specification process (OME-NGFF) to address these needs. This paper brings together a wide range of those community members to describe the cloud-optimized format itself—OME-Zarr—along with tools and data resources available today to increase FAIR access and remove barriers in the scientific process. The current momentum offers an opportunity to unify a key component of the bioimaging domain—the file format that underlies so many personal, institutional, and global data management and analysis tasks.},
	language = {en},
	number = {3},
	urldate = {2025-04-04},
	journal = {Histochemistry and Cell Biology},
	author = {Moore, Josh and Basurto-Lozada, Daniela and Besson, Sébastien and Bogovic, John and Bragantini, Jordão and Brown, Eva M. and Burel, Jean-Marie and Casas Moreno, Xavier and de Medeiros, Gustavo and Diel, Erin E. and Gault, David and Ghosh, Satrajit S. and Gold, Ilan and Halchenko, Yaroslav O. and Hartley, Matthew and Horsfall, Dave and Keller, Mark S. and Kittisopikul, Mark and Kovacs, Gabor and Küpcü Yoldaş, Aybüke and Kyoda, Koji and le Tournoulx de la Villegeorges, Albane and Li, Tong and Liberali, Prisca and Lindner, Dominik and Linkert, Melissa and Lüthi, Joel and Maitin-Shepard, Jeremy and Manz, Trevor and Marconato, Luca and McCormick, Matthew and Lange, Merlin and Mohamed, Khaled and Moore, William and Norlin, Nils and Ouyang, Wei and Özdemir, Bugra and Palla, Giovanni and Pape, Constantin and Pelkmans, Lucas and Pietzsch, Tobias and Preibisch, Stephan and Prete, Martin and Rzepka, Norman and Samee, Sameeul and Schaub, Nicholas and Sidky, Hythem and Solak, Ahmet Can and Stirling, David R. and Striebel, Jonathan and Tischer, Christian and Toloudis, Daniel and Virshup, Isaac and Walczysko, Petr and Watson, Alan M. and Weisbart, Erin and Wong, Frances and Yamauchi, Kevin A. and Bayraktar, Omer and Cimini, Beth A. and Gehlenborg, Nils and Haniffa, Muzlifah and Hotaling, Nathan and Onami, Shuichi and Royer, Loic A. and Saalfeld, Stephan and Stegle, Oliver and Theis, Fabian J. and Swedlow, Jason R.},
	month = sep,
	year = {2023},
	keywords = {FAIR, Data, Bioimaging, Cloud, Community, Format},
	pages = {223--251},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/6WG992Q9/Moore et al. - 2023 - OME-Zarr a cloud-optimized bioimaging file format with international community support.pdf:application/pdf},
}

@article{brancato2024standardizing,
	title = {Standardizing digital biobanks: integrating imaging, genomic, and clinical data for precision medicine},
	volume = {22},
	issn = {1479-5876},
	shorttitle = {Standardizing digital biobanks},
	url = {https://doi.org/10.1186/s12967-024-04891-8},
	doi = {10.1186/s12967-024-04891-8},
	abstract = {Advancements in data acquisition and computational methods are generating a large amount of heterogeneous biomedical data from diagnostic domains such as clinical imaging, pathology, and next-generation sequencing (NGS), which help characterize individual differences in patients. However, this information needs to be available and suitable to promote and support scientific research and technological development, supporting the effective adoption of the precision medicine approach in clinical practice. Digital biobanks can catalyze this process, facilitating the sharing of curated and standardized imaging data, clinical, pathological and molecular data, crucial to enable the development of a comprehensive and personalized data-driven diagnostic approach in disease management and fostering the development of computational predictive models. This work aims to frame this perspective, first by evaluating the state of standardization of individual diagnostic domains and then by identifying challenges and proposing a possible solution towards an integrative approach that can guarantee the suitability of information that can be shared through a digital biobank. Our analysis of the state of the art shows the presence and use of reference standards in biobanks and, generally, digital repositories for each specific domain. Despite this, standardization to guarantee the integration and reproducibility of the numerical descriptors generated by each domain, e.g. radiomic, pathomic and -omic features, is still an open challenge. Based on specific use cases and scenarios, an integration model, based on the JSON format, is proposed that can help address this problem. Ultimately, this work shows how, with specific standardization and promotion efforts, the digital biobank model can become an enabling technology for the comprehensive study of diseases and the effective development of data-driven technologies at the service of precision medicine.},
	number = {1},
	urldate = {2025-04-04},
	journal = {Journal of Translational Medicine},
	author = {Brancato, Valentina and Esposito, Giuseppina and Coppola, Luigi and Cavaliere, Carlo and Mirabelli, Peppino and Scapicchio, Camilla and Borgheresi, Rita and Neri, Emanuele and Salvatore, Marco and Aiello, Marco},
	month = feb,
	year = {2024},
	keywords = {Standardization, Big data, Data integration, Biobanking, Clinical decision support systems (CDSS), Imaging, NGS, Pathomics, Precision medicine, Radiomics},
	pages = {136},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/Y6DH8J4M/Brancato et al. - 2024 - Standardizing digital biobanks integrating imaging, genomic, and clinical data for precision medici.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/L2CQUC7J/s12967-024-04891-8.html:text/html},
}

@article{tabari2024stateoftheart,
	title = {State-of-the-{Art} {Fast} {Healthcare} {Interoperability} {Resources} ({FHIR})–{Based} {Data} {Model} and {Structure} {Implementations}: {Systematic} {Scoping} {Review}},
	volume = {12},
	copyright = {This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published JMIR Medical Informatics, is properly cited. The complete bibliographic information, a link to the original publication on https://medinform.jmir.org/, as well as this copyright and license information must be included.},
	shorttitle = {State-of-the-{Art} {Fast} {Healthcare} {Interoperability} {Resources} ({FHIR})–{Based} {Data} {Model} and {Structure} {Implementations}},
	url = {https://medinform.jmir.org/2024/1/e58445},
	doi = {10.2196/58445},
	abstract = {Background: Data models are crucial for clinical research as they enable researchers to fully use the vast amount of clinical data stored in medical systems. Standardized data and well-defined relationships between data points are necessary to guarantee semantic interoperability. Using the Fast Healthcare Interoperability Resources (FHIR) standard for clinical data representation would be a practical methodology to enhance and accelerate interoperability and data availability for research.
Objective: This research aims to provide a comprehensive overview of the state-of-the-art and current landscape in FHIR-based data models and structures. In addition, we intend to identify and discuss the tools, resources, limitations, and other critical aspects mentioned in the selected research papers.
Methods: To ensure the extraction of reliable results, we followed the instructions of the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) checklist. We analyzed the indexed articles in PubMed, Scopus, Web of Science, IEEE Xplore, the ACM Digital Library, and Google Scholar. After identifying, extracting, and assessing the quality and relevance of the articles, we synthesized the extracted data to identify common patterns, themes, and variations in the use of FHIR-based data models and structures across different studies.
Results: On the basis of the reviewed articles, we could identify 2 main themes: dynamic (pipeline-based) and static data models. The articles were also categorized into health care use cases, including chronic diseases, COVID-19 and infectious diseases, cancer research, acute or intensive care, random and general medical notes, and other conditions. Furthermore, we summarized the important or common tools and approaches of the selected papers. These items included FHIR-based tools and frameworks, machine learning approaches, and data storage and security. The most common resource was “Observation” followed by “Condition” and “Patient.” The limitations and challenges of developing data models were categorized based on the issues of data integration, interoperability, standardization, performance, and scalability or generalizability.
Conclusions: FHIR serves as a highly promising interoperability standard for developing real-world health care apps. The implementation of FHIR modeling for electronic health record data facilitates the integration, transmission, and analysis of data while also advancing translational research and phenotyping. Generally, FHIR-based exports of local data repositories improve data interoperability for systems and data warehouses across different settings. However, ongoing efforts to address existing limitations and challenges are essential for the successful implementation and integration of FHIR data models.},
	language = {EN},
	number = {1},
	urldate = {2025-04-04},
	journal = {JMIR Medical Informatics},
	publisher = {JMIR Publications Inc., Toronto, Canada},
	author = {Tabari, Parinaz and Costagliola, Gennaro and Rosa, Mattia De and Boeker, Martin},
	month = sep,
	year = {2024},
	note = {Company: JMIR Medical Informatics
Distributor: JMIR Medical Informatics
Institution: JMIR Medical Informatics
Label: JMIR Medical Informatics},
	pages = {e58445},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/I9S64U5Q/e58445.html:text/html},
}

@article{bernabe2023use,
	title = {The use of foundational ontologies in biomedical research},
	volume = {14},
	issn = {2041-1480},
	url = {https://jbiomedsem.biomedcentral.com/articles/10.1186/s13326-023-00300-z},
	doi = {10.1186/s13326-023-00300-z},
	abstract = {Abstract
            
              Background
              The FAIR principles recommend the use of controlled vocabularies, such as ontologies, to define data and metadata concepts. Ontologies are currently modelled following different approaches, sometimes describing conflicting definitions of the same concepts, which can affect interoperability. To cope with that, prior literature suggests organising ontologies in levels, where domain specific (low-level) ontologies are grounded in domain independent high-level ontologies (i.e., foundational ontologies). In this level-based organisation, foundational ontologies work as translators of intended meaning, thus improving interoperability. Despite their considerable acceptance in biomedical research, there are very few studies testing foundational ontologies. This paper describes a systematic literature mapping that was conducted to understand how foundational ontologies are used in biomedical research and to find empirical evidence supporting their claimed (dis)advantages.
            
            
              Results
              From a set of 79 selected papers, we identified that foundational ontologies are used for several purposes: ontology construction, repair, mapping, and ontology-based data analysis. Foundational ontologies are claimed to improve interoperability, enhance reasoning, speed up ontology development and facilitate maintainability. The complexity of using foundational ontologies is the most commonly cited downside. Despite being used for several purposes, there were hardly any experiments (1 paper) testing the claims for or against the use of foundational ontologies. In the subset of 49 papers that describe the development of an ontology, it was observed a low adherence to ontology construction (16 papers) and ontology evaluation formal methods (4 papers).
            
            
              Conclusion
              Our findings have two main implications. First, the lack of empirical evidence about the use of foundational ontologies indicates a need for evaluating the use of such artefacts in biomedical research. Second, the low adherence to formal methods illustrates how the field could benefit from a more systematic approach when dealing with the development and evaluation of ontologies. The understanding of how foundational ontologies are used in the biomedical field can drive future research towards the improvement of ontologies and, consequently, data FAIRness. The adoption of formal methods can impact the quality and sustainability of ontologies, and reusing these methods from other fields is encouraged.},
	language = {en},
	number = {1},
	urldate = {2025-04-07},
	journal = {Journal of Biomedical Semantics},
	author = {Bernabé, César H. and Queralt-Rosinach, Núria and Silva Souza, Vítor E. and Bonino Da Silva Santos, Luiz Olavo and Mons, Barend and Jacobsen, Annika and Roos, Marco},
	month = dec,
	year = {2023},
	pages = {21},
	file = {Full Text:/Users/dkapitan/Zotero/storage/I59ANSP3/Bernabé et al. - 2023 - The use of foundational ontologies in biomedical research.pdf:application/pdf},
}

@article{leiner2021bringing,
	title = {Bringing {AI} to the clinic: blueprint for a vendor-neutral {AI} deployment infrastructure},
	volume = {12},
	issn = {1869-4101},
	shorttitle = {Bringing {AI} to the clinic},
	url = {https://insightsimaging.springeropen.com/articles/10.1186/s13244-020-00931-1},
	doi = {10.1186/s13244-020-00931-1},
	abstract = {AI provides tremendous opportunities for improving patient care, but at present there is little evidence of real-world uptake. An important barrier is the lack of well-designed, vendor-neutral and future-proof infrastructures for deployment. Because current AI algorithms are very narrow in scope, it is expected that a typical hospital will deploy many algorithms concurrently. Managing stand-alone point solutions for all of these algorithms will be unmanageable. A solution to this problem is a dedicated platform for deployment of AI. Here we describe a blueprint for such a platform and the high-level design and implementation considerations of such a system that can be used clinically as well as for research and development. Close collaboration between radiologists, data scientists, software developers and experts in hospital IT as well as involvement of patients is crucial in order to successfully bring AI to the clinic.},
	language = {en},
	number = {1},
	urldate = {2025-04-08},
	journal = {Insights into Imaging},
	author = {Leiner, Tim and Bennink, Edwin and Mol, Christian P. and Kuijf, Hugo J. and Veldhuis, Wouter B.},
	month = dec,
	year = {2021},
	pages = {11},
	file = {PDF:/Users/dkapitan/Zotero/storage/KQYILQDC/Leiner et al. - 2021 - Bringing AI to the clinic blueprint for a vendor-neutral AI deployment infrastructure.pdf:application/pdf},
}

@article{tang2023creating,
	title = {Creating a {Medical} {Imaging} {Workflow} {Based} on {FHIR}, {DICOMweb}, and {SVG}},
	volume = {36},
	issn = {1618-727X},
	url = {https://doi.org/10.1007/s10278-021-00522-6},
	doi = {10.1007/s10278-021-00522-6},
	abstract = {This paper proposes a web-based workflow scheme for the organization of medical images using FHIR and DICOM servers equipped with standard RESTful APIs. In our integrated workflow, the client systems (including order placer, scheduler, imaging modality, viewer, and report creator) use standard FHIR and DICOMweb APIs. The proposed scheme also facilitates the creation of reports formatted as standard FHIR resources. This paper leverages W3C Scalable Vector Graphics (SVG) to record the image graphic annotations, and encapsulates the SVG image annotation in FHIR observation. FHIR DiagnosticReports and Observations are used to encapsulate reports, findings, and annotations, thereby facilitating the implementation and integration of the scheme within existing structures. The proposed scheme also provides the potential to make it possible to convert results of Computer Aided Detection/Diagnosis from medical images into FHIR DiagnosticReports and Observations to be stored on a FHIR server. The resulting web-based solution uses FHIR XML and/or JSON data to record and exchange information related to imaging workflow. It can also be used to store imaging reports, findings, and annotations linked to the images using the DICOM WADO-RS protocol. As a result, it is possible to integrate all information that is created in medical imaging workflow. Finally, the proposed scheme is easily integrated with other FHIR systems.},
	language = {en},
	number = {3},
	urldate = {2025-04-08},
	journal = {Journal of Digital Imaging},
	author = {Tang, Shih-Tsang and Tjia, Victoria and Noga, Thalia and Febri, Jeshika and Lien, Chung-Yueh and Chu, Woei-Chyn and Chen, Chin-Yu and Hsiao, Chia-Hung},
	month = jun,
	year = {2023},
	keywords = {FHIR, DICOMweb, RESTful, Scalable Vector Graphics (SVG)},
	pages = {794--803},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/KMBJTMUZ/Tang et al. - 2023 - Creating a Medical Imaging Workflow Based on FHIR, DICOMweb, and SVG.pdf:application/pdf},
}

@article{bak2025ethical,
	title = {Ethical {Design} of {Data}-{Driven} {Decision} {Support} {Tools} for {Improving} {Cancer} {Care}: {Embedded} {Ethics} {Review} of the {4D} {PICTURE} {Project}},
	volume = {11},
	copyright = {Unless stated otherwise, all articles are open-access distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work ("first published in the Journal of Medical Internet Research...") is properly cited with original URL and bibliographic citation information. The complete bibliographic information, a link to the original publication on http://www.jmir.org/, as well as this copyright and license information must be included.},
	shorttitle = {Ethical {Design} of {Data}-{Driven} {Decision} {Support} {Tools} for {Improving} {Cancer} {Care}},
	url = {https://cancer.jmir.org/2025/1/e65566},
	doi = {10.2196/65566},
	abstract = {Oncology patients often face complex choices between treatment regimens with different risk-benefit ratios. The 4D PICTURE (Producing Improved Cancer Outcomes Through User-Centered Research) project aims to support patients, their families, and clinicians with these complex decisions by developing data-driven decision support tools (DSTs) for patients with breast cancer, prostate cancer, and melanoma as part of care path redesign using a methodology called MetroMapping. There are myriad ethical issues to consider as the project will create data-driven prognostic models and develop conversation tools using artificial intelligence while including patient perspectives by setting up boards of experiential experts in 8 different countries. This paper aims to review the key ethical challenges related to the design and development of DSTs in oncology. To explore the ethics of DSTs in cancer care, the project adopted the Embedded Ethics approach—embedding ethicists into research teams to sensitize team members to ethical aspects and assist in reflecting on those aspects throughout the project. We conducted what we call an embedded review of the project drawing from key literature on topics related to the different work packages of the 4D PICTURE project, whereas the analysis was an iterative process involving discussions with researchers in the project. Our review identified 13 key ethical challenges related to the development of DSTs and the redesigning of care paths for more personalized cancer care. Several ethical aspects were related to general potential issues of data bias and privacy but prompted specific research questions, for instance, about the inclusion of certain demographic variables in models. Design methodology in the 4D PICTURE project can provide insights related to design justice, a novel consideration in health care DSTs. Ethical points of attention related to health care policy, such as cost-effectiveness, financial sustainability, and environmental impact, were also identified, along with challenges in the research process itself, emphasizing the importance of epistemic justice, the role of embedded ethicists, and psychological safety. This viewpoint highlights ethical aspects previously neglected in the digital health ethics literature and zooms in on real-world challenges in an ongoing project. It underscores the need for researchers and leaders in data-driven medical research projects to address ethical challenges beyond the scientific core of the project. More generally, our tailored review approach provides a model for embedding ethics into large data-driven oncology research projects from the start, which helps ensure that technological innovations are designed and developed in an appropriate and patient-centered manner.},
	language = {EN},
	number = {1},
	urldate = {2025-04-15},
	journal = {JMIR Cancer},
	publisher = {JMIR Publications Inc., Toronto, Canada},
	author = {Bak, Marieke and Hartman, Laura and Graafland, Charlotte and Korfage, Ida J. and Buyx, Alena and Schermer, Maartje and Consortium, 4d Picture},
	month = apr,
	year = {2025},
	note = {Company: JMIR Cancer
Distributor: JMIR Cancer
Institution: JMIR Cancer
Label: JMIR Cancer},
	pages = {e65566},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/XM367NS8/e65566.html:text/html},
}

@article{vangiessen2017systematic,
	title = {Systematic {Review} of {Health} {Economic} {Impact} {Evaluations} of {Risk} {Prediction} {Models}: {Stop} {Developing}, {Start} {Evaluating}},
	volume = {20},
	issn = {10983015},
	shorttitle = {Systematic {Review} of {Health} {Economic} {Impact} {Evaluations} of {Risk} {Prediction} {Models}},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S1098301516300328},
	doi = {10.1016/j.jval.2017.01.001},
	abstract = {Background: Although health economic evaluations (HEEs) are increasingly common for therapeutic interventions, they appear to be rare for the use of risk prediction models (PMs). Objectives: To evaluate the current state of HEEs of PMs by performing a comprehensive systematic review. Methods: Four databases were searched for HEEs of PM-based strategies. Two reviewers independently selected eligible articles. A checklist was compiled to score items focusing on general characteristics of HEEs of PMs, model characteristics and quality of HEEs, evidence on PMs typically used in the HEEs, and the specific challenges in performing HEEs of PMs. Results: After screening 791 abstracts, 171 full texts, and reference checking, 40 eligible HEEs evaluating 60 PMs were identified. In these HEEs, PM strategies were compared with current practice (n ¼ 32; 80\%), to other stratification methods for patient management (n ¼ 19; 48\%), to an extended PM (n ¼ 9; 23\%), or to alternative PMs (n ¼ 5; 13\%). The PMs guided decisions on treatment (n ¼ 42; 70\%), further testing (n ¼ 18; 30\%), or treatment prioritization (n ¼ 4; 7\%). For 36 (60\%) PMs, only a single decision threshold was evaluated. Costs of risk prediction were ignored for 28 (46\%) PMs. Uncertainty in outcomes was assessed using probabilistic sensitivity analyses in 22 (55\%) HEEs. Conclusions: Despite the huge number of PMs in the medical literature, HEE of PMs remains rare. In addition, we observed great variety in their quality and methodology, which may complicate interpretation of HEE results and implementation of PMs in practice. Guidance on HEE of PMs could encourage and standardize their application and enhance methodological quality, thereby improving adequate use of PM strategies.},
	language = {en},
	number = {4},
	urldate = {2025-04-15},
	journal = {Value in Health},
	author = {Van Giessen, Anoukh and Peters, Jaime and Wilcher, Britni and Hyde, Chris and Moons, Carl and De Wit, Ardine and Koffijberg, Erik},
	month = apr,
	year = {2017},
	pages = {718--726},
	file = {PDF:/Users/dkapitan/Zotero/storage/48A7LPZ2/Van Giessen et al. - 2017 - Systematic Review of Health Economic Impact Evaluations of Risk Prediction Models Stop Developing,.pdf:application/pdf},
}

@article{feng2022clinical,
	title = {Clinical artificial intelligence quality improvement: towards continual monitoring and updating of {AI} algorithms in healthcare},
	volume = {5},
	copyright = {2022 The Author(s)},
	issn = {2398-6352},
	shorttitle = {Clinical artificial intelligence quality improvement},
	url = {https://www.nature.com/articles/s41746-022-00611-y},
	doi = {10.1038/s41746-022-00611-y},
	abstract = {Machine learning (ML) and artificial intelligence (AI) algorithms have the potential to derive insights from clinical data and improve patient outcomes. However, these highly complex systems are sensitive to changes in the environment and liable to performance decay. Even after their successful integration into clinical practice, ML/AI algorithms should be continuously monitored and updated to ensure their long-term safety and effectiveness. To bring AI into maturity in clinical care, we advocate for the creation of hospital units responsible for quality assurance and improvement of these algorithms, which we refer to as “AI-QI” units. We discuss how tools that have long been used in hospital quality assurance and quality improvement can be adapted to monitor static ML algorithms. On the other hand, procedures for continual model updating are still nascent. We highlight key considerations when choosing between existing methods and opportunities for methodological innovation.},
	language = {en},
	number = {1},
	urldate = {2025-04-15},
	journal = {npj Digital Medicine},
	publisher = {Nature Publishing Group},
	author = {Feng, Jean and Phillips, Rachael V. and Malenica, Ivana and Bishara, Andrew and Hubbard, Alan E. and Celi, Leo A. and Pirracchio, Romain},
	month = may,
	year = {2022},
	keywords = {Statistics, Public health},
	pages = {1--9},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/46VZPAEQ/Feng et al. - 2022 - Clinical artificial intelligence quality improvement towards continual monitoring and updating of A.pdf:application/pdf},
}

@article{kapitan2025data,
	title = {Data {Interoperability} in {Context}: {The} {Importance} of {Open}-{Source} {Implementations} {When} {Choosing} {Open} {Standards}},
	volume = {27},
	shorttitle = {Data {Interoperability} in {Context}},
	url = {https://www.jmir.org/2025/1/e66616},
	doi = {10.2196/66616},
	abstract = {Following the proposal by Tsafnat et al (2024) to converge on three open health data standards, this viewpoint offers a critical reflection on their proposed alignment of openEHR, Fast Health Interoperability Resources (FHIR), and Observational Medical Outcomes Partnership (OMOP) as default data standards for clinical care and administration, data exchange, and longitudinal analysis, respectively. We argue that open standards are a necessary but not sufficient condition to achieve health data interoperability. The ecosystem of open-source software needs to be considered when choosing an appropriate standard for a given context. We discuss two specific contexts, namely standardization of (1) health data for federated learning, and (2) health data sharing in low- and middle-income countries. Specific design principles, practical considerations, and implementation choices for these two contexts are described, based on ongoing work in both areas. In the case of federated learning, we observe convergence toward OMOP and FHIR, where the two standards can effectively be used side-by-side given the availability of mediators between the two. In the case of health information exchanges in low and middle-income countries, we see a strong convergence toward FHIR as the primary standard. We propose practical guidelines for context-specific adaptation of open health data standards.},
	language = {EN},
	number = {1},
	urldate = {2025-04-15},
	journal = {Journal of Medical Internet Research},
	publisher = {JMIR Publications Inc., Toronto, Canada},
	author = {Kapitan, Daniel and Heddema, Femke and Dekker, André and Sieswerda, Melle and Verhoeff, Bart-Jan and Berg, Matt},
	month = apr,
	year = {2025},
	note = {Company: Journal of Medical Internet Research
Distributor: Journal of Medical Internet Research
Institution: Journal of Medical Internet Research
Label: Journal of Medical Internet Research},
	pages = {e66616},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/MFF97PKZ/e66616.html:text/html},
}

@misc{2024reference,
	title = {Reference {Architecture} {\textbar} {Public}},
	url = {https://bdi.gitbook.io/public},
	language = {en},
	urldate = {2025-05-06},
	month = sep,
	year = {2024},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/ADMWKNN9/public.html:text/html},
}

@incollection{elghosh2024semantic,
	title = {Towards {Semantic} {Interoperability} {Among} {Heterogeneous} {Cancer} {Data} {Models} {Using} a {Layered} {Modular} {Hyper}-{Ontology}},
	copyright = {https://creativecommons.org/licenses/by-nc/4.0/},
	isbn = {978-1-64368-561-8},
	url = {https://ebooks.iospress.nl/doi/10.3233/FAIA241305},
	doi = {10.3233/FAIA241305},
	abstract = {Semantic interoperability is a growing and challenging subject in the healthcare domain. It aims to ensure a coherent and unambiguous exchange, use, and reuse of health information among different systems and applications. In the context of the EUCAIM (Cancer Image Europe) project, semantic interoperability among various heterogeneous cancer image data models is required to support the communication, integration, and sharing of data in a standardized and structured way. For this purpose, hyper-ontology is developed as a common semantic metamodel that bridges the disparate imaging and clinical knowledge of the various repositories in EUCAIM and supports their integration. EUCAIM’s hyper-ontology is also an application-based ontology targeted for federated semantic querying and image annotation. To facilitate the hyper-ontology building process and ensure the extensibility of the ontology model, an iterative hybrid well-founded approach that divides the ontology structure into layers and modules is established.},
	language = {en},
	urldate = {2025-05-06},
	booktitle = {Frontiers in {Artificial} {Intelligence} and {Applications}},
	publisher = {IOS Press},
	author = {El Ghosh, Mirna and Kalokyri, Varvara and Sambres, Melanie and Vaterkowski, Morgan and Duclos, Catherine and Tannier, Xavier and Tsakou, Gianna and Tsiknakis, Manolis and Daniel, Christel and Dhombres, Ferdinand},
	editor = {Trojahn, Cassia and Porello, Daniele and Barcelos, Pedro Paulo Favato},
	month = dec,
	year = {2024},
	file = {PDF:/Users/dkapitan/Zotero/storage/YSCKWVGD/El Ghosh et al. - 2024 - Towards Semantic Interoperability Among Heterogeneous Cancer Data Models Using a Layered Modular Hyp.pdf:application/pdf},
}

@misc{laboratoryofmedicalinformaticsandknowledgeengineeringine-healthlimics2025eucaims,
	title = {{EUCAIM}'s {Hyper}-{Ontology}\_V1.2},
	copyright = {Creative Commons Attribution 4.0 International},
	url = {https://zenodo.org/doi/10.5281/zenodo.14765570},
	doi = {10.5281/ZENODO.14765570},
	abstract = {An updated version of EUCAIM's Hyper-Ontology (min-FIF).

{\textgreater}{\textgreater}{\textgreater} This effort is part of the EUCAIM project

{\textgreater}{\textgreater}{\textgreater} The ontology documentation is generated using WIDOCO},
	urldate = {2025-05-06},
	publisher = {Zenodo},
	author = {{Laboratory of Medical Informatics and Knowledge Engineering in e-Health (LIMICS)}},
	collaborator = {{Foundation for Research and Technology Hellas (FORTH)} and {Hospital Universitari i Politècnic La Fe} and {German Cancer Research Center (DKFZ)} and {Assistance publique - Hôpitaux de Paris (APHP)} and {Gdański Uniwersytet Medyczny (GUMed)} and {INCISIVE} and {ProCAncer-I} and {CHAIMELEON} and {EuCanImage}},
	month = jan,
	year = {2025},
}

@article{baker2023story,
	title = {The {Story} {Behind} the {HL7} {FHIR} to {CDISC} {Mapping} {Implementation} {Guide}},
	volume = {4},
	copyright = {Copyright: © 2023 The Author(s). SCDM publishes JSCDM content in an open access manner under a Attribution-Non-Commercial-ShareAlike (CC BY-NC-SA) license. This license lets others remix, adapt, and build upon the work non-commercially, as long as they credit SCDM and the author and license their new creations under the identical terms. See https://creativecommons.org/licenses/by-nc-sa/4.0/.},
	issn = {2694-1473},
	url = {https://www.jscdm.org/article/id/162/},
	doi = {10.47912/jscdm.162},
	abstract = {BackgroundHealth data has become an abundant and rich source of information that can be leveraged for clinical trials. Health Level Seven (HL7) provides standards for health care data, while the Clinical Data Interchange Standards Consortium (CDISC) provides standards for research data. Bridging these worlds and leveraging health data has the potential to enhance knowledge and data quality, while reducing delays and cost in clinical trials.Objectives The aim was to provide an overview of the HL7 Fast Healthcare Interoperability Resources (FHIR®) to CDISC Joint Mapping Implementation Guide (IG) development. The ultimate aim is to increase awareness of this rich resource.MethodsA gap analysis was performed to assess the possibility and feasibility of mapping from FHIR to the CDISC’s Study Data Tabulation Model (SDTM) and Clinical Data Acquisition Standards Harmonization (CDASH) standards. The mapping of CDISC domains commenced using FHIRPath, a path-based navigation and extraction language. The domains mapped were Medical History (MH), Concomitant Medications (CM), Procedures (PR), Vital Signs (VS), Laboratory (LB), Adverse Events (AE), and Demographics (DM). The proposed mappings were evaluated through a formal review process.ResultsThe review process consisted of a CDISC Internal Review and a simultaneous CDISC Public Review and HL7 Ballot Review.\  A total of 363 comments were obtained from the following reviews: 1) CDISC Internal Review (268), and 2) simultaneous Public Review (95) - CDISC (37), HL7 (58). The predominant gathered in the review included mapping updates, terminology, and requests for greater detail.ConclusionThe HL7 FHIR®\ to CDISC Joint Mapping Implementation Guide (IG) provides a rich resource for bridging health care and research standards that can be used with CDISC LB to LOINC mapping guide for leveraging real-world data for clinical trials. The guide assists stakeholders in utilizing health data through the HL7 FHIR® resources to CDISC, CDASH, and SDTM variables. As the community uses this resource, it will continue to mature and potentially expand into new domains.},
	language = {eng},
	number = {1},
	urldate = {2025-05-06},
	journal = {Journal of the Society for Clinical Data Management},
	publisher = {Society for Clinical Data Management},
	author = {Baker, Rebecca L. and Hamidi, Mike and McKenzie, Lloyd and Denney, Christine K. and Edgar, Theresia D.},
	month = aug,
	year = {2023},
	note = {Number: 1},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/9RKTDFET/Baker et al. - 2023 - The Story Behind the HL7 FHIR to CDISC Mapping Implementation Guide.pdf:application/pdf},
}

@article{hosch2023fhirpyrate,
	title = {{FHIR}-{PYrate}: a data science friendly {Python} package to query {FHIR} servers},
	volume = {23},
	issn = {1472-6963},
	shorttitle = {{FHIR}-{PYrate}},
	url = {https://doi.org/10.1186/s12913-023-09498-1},
	doi = {10.1186/s12913-023-09498-1},
	abstract = {We present FHIR-PYrate, a Python package to handle the full clinical data collection and extraction process. The software is to be plugged into a modern hospital domain, where electronic patient records are used to handle the entire patient’s history. Most research institutes follow the same procedures to build study cohorts, but mainly in a non-standardized and repetitive way. As a result, researchers spend time writing boilerplate code, which could be used for more challenging tasks.},
	language = {en},
	number = {1},
	urldate = {2025-05-06},
	journal = {BMC Health Services Research},
	author = {Hosch, René and Baldini, Giulia and Parmar, Vicky and Borys, Katarzyna and Koitka, Sven and Engelke, Merlin and Arzideh, Kamyar and Ulrich, Moritz and Nensa, Felix},
	month = jul,
	year = {2023},
	keywords = {FHIR, Python, Dataframe, Dicom, Electronic patient record, Information extraction},
	pages = {734},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/WE6FZEL3/Hosch et al. - 2023 - FHIR-PYrate a data science friendly Python package to query FHIR servers.pdf:application/pdf},
}

@inproceedings{pereira2025comparison,
	address = {Cham},
	title = {Comparison of {eHealth} {Interoperability} {Standards}: {HL7} {FHIR}, {OpenEHR}, and {CDISC}},
	isbn = {978-3-031-81685-7},
	shorttitle = {Comparison of {eHealth} {Interoperability} {Standards}},
	doi = {10.1007/978-3-031-81685-7_18},
	abstract = {This paper is a complete description and comparison of some of the most cited eHealth interoperability standards in the literature, openEHR, HL7 FHIR and CDISC. We searched the Scopus database using the keywords interoperability, information systems, and health. It was found that standards are needed to develop interoperability platforms for eHealth. We carried out additional research on the most cited standards, allowing us to analyze the characteristics and particularities of each one and make comparisons. As a result of this work, we defined a list of comparison criteria and evaluated the differences between these standards based on these criteria. The standards compared have some common characteristics, but they also have unique features for each of them, so the selection of the standard to use will depend on the characteristics and requirements of the eHealth platform you want to develop.},
	language = {en},
	booktitle = {The 18th {International} {Conference} {Interdisciplinarity} in {Engineering}},
	publisher = {Springer Nature Switzerland},
	author = {Pereira, José D. and Frade, Samuel and Ribeiro, Rui and Santos, Manuel and Brito, Miguel A. and Machado, Ricardo J.},
	editor = {Moldovan, Liviu and Gligor, Adrian},
	year = {2025},
	keywords = {Standards, HL7 FHIR, openEHR, Comparison, CDISC, EHealth},
	pages = {241--249},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/L8IELE5M/Pereira et al. - 2025 - Comparison of eHealth Interoperability Standards HL7 FHIR, OpenEHR, and CDISC.pdf:application/pdf},
}

@inproceedings{yuan2024ciphersteal,
	title = {{CipherSteal}: {Stealing} {Input} {Data} from {TEE}-{Shielded} {Neural} {Networks} with {Ciphertext} {Side} {Channels}},
	isbn = {979-8-3315-2236-0},
	issn = {2375-1207},
	shorttitle = {{CipherSteal}},
	url = {https://www.computer.org/csdl/proceedings-article/sp/2025/223600a079/21B7Rmh3jrO},
	doi = {10.1109/SP61157.2025.00079},
	abstract = {Shielding neural networks (NNs) from untrusted hosts with Trusted Execution Environments (TEEs) has been increasingly adopted. Nevertheless, this paper shows that the confidentiality of NNs and user data is compromised by the recently disclosed ciphertext side channels in TEEs, which leak memory write patterns of TEE-shielded NNs to malicious hosts. While recent works have used ciphertext side channels to recover cryptographic key bits, the technique does not apply to NN inputs which are more complex and only have partial information leaked. We propose an automated input recovery framework, CipherSteal, and for the first time demonstrate the severe threat of ciphertext side channels to NN inputs. CipherSteal novelly recasts the input recovery as a two-step approach — information transformation and reconstruction — and proposes optimizations to fully utilize partial input information leaked in ciphertext side channels. We evaluate CipherSteal on diverse NNs (e.g., Transformer) and image/video inputs, and successfully recover visually identical inputs under different levels of attacker’s pre-knowledge towards the target NNs and their inputs. We comprehensively evaluate two popular NN frameworks, TensorFlow and PyTorch, and NN executables generated by two recent NN compilers, TVM and Glow, and study their different attack surfaces. Moreover, we further steal the target NN’s functionality by training a surrogate NN with our recovered inputs, and also leverage the surrogate NN to generate "white-box" adversarial examples, effectively manipulating the target NN’s predictions.},
	language = {English},
	urldate = {2025-05-19},
	publisher = {IEEE Computer Society},
	author = {Yuan, Yuanyuan and Liu, Zhibo and Deng, Sen and Chen, Yanzuo and Wang, Shuai and Zhang, Yinqian and Su, Zhendong},
	month = nov,
	year = {2024},
	pages = {4136--4154},
}

@article{toure2025sphn,
	title = {The {SPHN} {Schema} {Forge} – transform healthcare semantics from human-readable to machine-readable by leveraging semantic web technologies},
	volume = {16},
	issn = {2041-1480},
	url = {https://doi.org/10.1186/s13326-025-00330-9},
	doi = {10.1186/s13326-025-00330-9},
	abstract = {The Swiss Personalized Health Network (SPHN) adopted the Resource Description Framework (RDF), a core component of the Semantic Web technology stack, for the formal encoding and exchange of healthcare data in a medical knowledge graph. The SPHN RDF Schema defines the semantics on how data elements should be represented. While RDF is proven to be machine readable and interpretable, it can be challenging for individuals without specialized background to read and understand the knowledge represented in RDF. For this reason, the semantics described in the SPHN RDF Schema are primarily defined in a user-accessible tabular format, the SPHN Dataset, before being translated into its RDF representation. However, this translation process was previously manual, time-consuming and labor-intensive.},
	number = {1},
	urldate = {2025-05-22},
	journal = {Journal of Biomedical Semantics},
	author = {Touré, Vasundra and Unni, Deepak and Krauss, Philip and Abdelwahed, Abdelhamid and Buchhorn, Jascha and Hinderling, Leon and Geiger, Thomas R. and Österle, Sabine},
	month = may,
	year = {2025},
	keywords = {Healthcare, Semantics, FAIR, Semantic Web, Conversion, RDF, Schema, Spreadsheet, Web Service},
	pages = {9},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/FGV3AHEL/Touré et al. - 2025 - The SPHN Schema Forge – transform healthcare semantics from human-readable to machine-readable by le.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/97848I6X/s13326-025-00330-9.html:text/html},
}

@article{deist2020distributed,
	title = {Distributed learning on 20 000+ lung cancer patients – {The} {Personal} {Health} {Train}},
	volume = {144},
	issn = {01678140},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0167814019334899},
	doi = {10.1016/j.radonc.2019.11.019},
	abstract = {Background and purpose: Access to healthcare data is indispensable for scientific progress and innovation. Sharing healthcare data is time-consuming and notoriously difficult due to privacy and regulatory concerns. The Personal Health Train (PHT) provides a privacy-by-design infrastructure connecting FAIR (Findable, Accessible, Interoperable, Reusable) data sources and allows distributed data analysis and machine learning. Patient data never leaves a healthcare institute. Materials and methods: Lung cancer patient-specific databases (tumor staging and post-treatment survival information) of oncology departments were translated according to a FAIR data model and stored locally in a graph database. Software was installed locally to enable deployment of distributed machine learning algorithms via a central server. Algorithms (MATLAB, code and documentation publicly available) are patient privacy-preserving as only summary statistics and regression coefficients are exchanged with the central server. A logistic regression model to predict post-treatment two-year survival was trained and evaluated by receiver operating characteristic curves (ROC), root mean square prediction error (RMSE) and calibration plots.
Results: In 4 months, we connected databases with 23 203 patient cases across 8 healthcare institutes in 5 countries (Amsterdam, Cardiff, Maastricht, Manchester, Nijmegen, Rome, Rotterdam, Shanghai) using the PHT. Summary statistics were computed across databases. A distributed logistic regression model predicting post-treatment two-year survival was trained on 14 810 patients treated between 1978 and 2011 and validated on 8 393 patients treated between 2012 and 2015.
Conclusion: The PHT infrastructure demonstrably overcomes patient privacy barriers to healthcare data sharing and enables fast data analyses across multiple institutes from different countries with different regulatory regimens. This infrastructure promotes global evidence-based medicine while prioritizing patient privacy.},
	language = {en},
	urldate = {2025-05-27},
	journal = {Radiotherapy and Oncology},
	author = {Deist, Timo M. and Dankers, Frank J.W.M. and Ojha, Priyanka and Scott Marshall, M. and Janssen, Tomas and Faivre-Finn, Corinne and Masciocchi, Carlotta and Valentini, Vincenzo and Wang, Jiazhou and Chen, Jiayan and Zhang, Zhen and Spezi, Emiliano and Button, Mick and Jan Nuyttens, Joost and Vernhout, René and Van Soest, Johan and Jochems, Arthur and Monshouwer, René and Bussink, Johan and Price, Gareth and Lambin, Philippe and Dekker, Andre},
	month = mar,
	year = {2020},
	pages = {189--200},
	file = {deist2020distributed-supplement:/Users/dkapitan/Zotero/storage/AA3T8A2B/deist2020distributed-supplement.docx:application/vnd.openxmlformats-officedocument.wordprocessingml.document;PDF:/Users/dkapitan/Zotero/storage/AY8GRR9Q/Deist et al. - 2020 - Distributed learning on 20 000+ lung cancer patients – The Personal Health Train.pdf:application/pdf},
}

@article{gbadegeshin2022overcoming,
	title = {Overcoming the {Valley} of {Death}: {A} {New} {Model} for {High} {Technology} {Startups}},
	volume = {4},
	issn = {26661888},
	shorttitle = {Overcoming the {Valley} of {Death}},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2666188822000119},
	doi = {10.1016/j.sftr.2022.100077},
	abstract = {The Valley of Death (VoD) reflects a series of challenges facing technology-based companies during their early development stages. Extant literature highlights the need for startups to equip themselves with the tools and resources to manage this turbulent transition. However, the existing frameworks propounded by fellow scholars and practitioners regarding VoD are fragmented, each covering only a few issues in the chasm. Thus, the current article proposes a new and comprehensive model for high technology-based startups. The new model emerged from an in-depth review of 128 scholarly materials and empirical data collected from 30 startups (from artificial intelligence, virtual and augmented realities, internet of things, medical, and cleantech industrial sectors). The model was piloted in three pre-startups. The model adds on the existing VoD frameworks to provide a holistic baseline for future research in this field by presenting different challenges underlying the pre-establishment years of a company while addressing courses of action needed to overcome this perilous transition.},
	language = {en},
	urldate = {2025-05-27},
	journal = {Sustainable Futures},
	author = {Gbadegeshin, Saheed A. and Natsheh, Anas Al and Ghafel, Kawtar and Mohammed, Omar and Koskela, Ashten and Rimpiläinen, Antti and Tikkanen, Joonas and Kuoppala, Antti},
	year = {2022},
	pages = {100077},
	file = {PDF:/Users/dkapitan/Zotero/storage/A7HDS9ER/Gbadegeshin et al. - 2022 - Overcoming the Valley of Death A New Model for High Technology Startups.pdf:application/pdf},
}

@article{gonzalez-gonzalo2022trustworthy,
	title = {Trustworthy {AI}: {Closing} the gap between development and integration of {AI} systems in ophthalmic practice},
	volume = {90},
	issn = {13509462},
	shorttitle = {Trustworthy {AI}},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S1350946221000951},
	doi = {10.1016/j.preteyeres.2021.101034},
	abstract = {An increasing number of artificial intelligence (AI) systems are being proposed in ophthalmology, motivated by the variety and amount of clinical and imaging data, as well as their potential benefits at the different stages of patient care. Despite achieving close or even superior performance to that of experts, there is a critical gap between development and integration of AI systems in ophthalmic practice. This work focuses on the importance of trustworthy AI to close that gap. We identify the main aspects or challenges that need to be considered along the AI design pipeline so as to generate systems that meet the requirements to be deemed trustworthy, including those concerning accuracy, resiliency, reliability, safety, and accountability. We elaborate on mechanisms and considerations to address those aspects or challenges, and define the roles and responsibilities of the different stakeholders involved in AI for ophthalmic care, i.e., AI developers, reading centers, healthcare providers, healthcare institutions, ophthalmological societies and working groups or committees, patients, regulatory bodies, and payers. Generating trustworthy AI is not a responsibility of a sole stakeholder. There is an impending necessity for a collaborative approach where the different stakeholders are represented along the AI design pipeline, from the definition of the intended use to post-market surveillance after regulatory approval. This work contributes to establish such multi-stakeholder interaction and the main action points to be taken so that the potential benefits of AI reach real-world ophthalmic settings.},
	language = {en},
	urldate = {2025-05-27},
	journal = {Progress in Retinal and Eye Research},
	author = {González-Gonzalo, Cristina and Thee, Eric F. and Klaver, Caroline C.W. and Lee, Aaron Y. and Schlingemann, Reinier O. and Tufail, Adnan and Verbraak, Frank and Sánchez, Clara I.},
	month = sep,
	year = {2022},
	pages = {101034},
	file = {PDF:/Users/dkapitan/Zotero/storage/HMMK9XXL/González-Gonzalo et al. - 2022 - Trustworthy AI Closing the gap between development and integration of AI systems in ophthalmic prac.pdf:application/pdf},
}

@article{zeist2024ai,
	title = {{AI} {Monitor} {Ziekenhuizen} 2024},
	language = {nl},
	author = {Zeist, JE},
	year = {2024},
	file = {PDF:/Users/dkapitan/Zotero/storage/SR7IXN9A/Zeist - 2024 - AI Monitor Ziekenhuizen 2024.pdf:application/pdf},
}

@techreport{mannotimpactanalyse,
	title = {Impactanalyse  {AI}-verordening},
	language = {nl},
	author = {Mannot, Pascal and Boer, Mona de},
	file = {PDF:/Users/dkapitan/Zotero/storage/S2CESI7J/Mannot - Met vriendelijke groet, PricewaterhouseCoopers Advisory N.V..pdf:application/pdf},
}

@article{thurin2022inception,
	title = {From {Inception} to {ConcePTION}: {Genesis} of a {Network} to {Support} {Better} {Monitoring} and {Communication} of {Medication} {Safety} {During} {Pregnancy} and {Breastfeeding}},
	volume = {111},
	issn = {0009-9236},
	shorttitle = {From {Inception} to {ConcePTION}},
	url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9299060/},
	doi = {10.1002/cpt.2476},
	abstract = {In 2019, the Innovative Medicines Initiative (IMI) funded the ConcePTION project—Building an ecosystem for better monitoring and communicating safety of medicines use in pregnancy and breastfeeding: validated and regulatory endorsed workflows for fast, optimised evidence generation—with the vision that there is a societal obligation to rapidly reduce uncertainty about the safety of medication use in pregnancy and breastfeeding. The present paper introduces the set of concepts used to describe the European data sources involved in the ConcePTION project and illustrates the ConcePTION Common Data Model (CDM), which serves as the keystone of the federated ConcePTION network. Based on data availability and content analysis of 21 European data sources, the ConcePTION CDM has been structured with six tables designed to capture data from routine healthcare, three tables for data from public health surveillance activities, three curated tables for derived data on population (e.g., observation time and mother‐child linkage), plus four metadata tables. By its first anniversary, the ConcePTION CDM has enabled 13 data sources to run common scripts to contribute to major European projects, demonstrating its capacity to facilitate effective and transparent deployment of distributed analytics, and its potential to address questions about utilization, effectiveness, and safety of medicines in special populations, including during pregnancy and breastfeeding, and, more broadly, in the general population.},
	number = {1},
	urldate = {2025-06-02},
	journal = {Clinical Pharmacology and Therapeutics},
	author = {Thurin, Nicolas H. and Pajouheshnia, Romin and Roberto, Giuseppe and Dodd, Caitlin and Hyeraci, Giulia and Bartolini, Claudia and Paoletti, Olga and Nordeng, Hedvig and Wallach‐Kildemoes, Helle and Ehrenstein, Vera and Dudukina, Elena and MacDonald, Thomas and De Paoli, Giorgia and Loane, Maria and Damase‐Michel, Christine and Beau, Anna‐Belle and Droz‐Perroteau, Cécile and Lassalle, Régis and Bergman, Jorieke and Swart, Karin and Schink, Tania and Cavero‐Carbonell, Clara and Barrachina‐Bonet, Laia and Gomez‐Lumbreras, Ainhoa and Giner‐Soriano, Maria and Aragón, María and Neville, Amanda J. and Puccini, Aurora and Pierini, Anna and Ientile, Valentina and Trifirò, Gianluca and Rissmann, Anke and Leinonen, Maarit K. and Martikainen, Visa and Jordan, Sue and Thayer, Daniel and Scanlon, Ieuan and Georgiou, Mary E. and Cunnington, Marianne and Swertz, Morris and Sturkenboom, Miriam and Gini, Rosa},
	month = jan,
	year = {2022},
	pages = {321--331},
	file = {Full Text:/Users/dkapitan/Zotero/storage/9XSBRUCZ/Thurin et al. - 2022 - From Inception to ConcePTION Genesis of a Network to Support Better Monitoring and Communication of.pdf:application/pdf},
}

@article{opend,
	title = {Open {Business} {Data} {Lake} ({O}-{BDL})},
	language = {en},
	file = {PDF:/Users/dkapitan/Zotero/storage/TM7LK39E/Open Business Data Lake (O-BDL).pdf:application/pdf},
}

@incollection{vanderwerf2025dataa,
	address = {Cham},
	title = {Towards a {Data} {Mesh} {Reference} {Architecture}},
	volume = {537},
	isbn = {978-3-031-79058-4 978-3-031-79059-1},
	url = {https://link.springer.com/10.1007/978-3-031-79059-1_21},
	doi = {10.1007/978-3-031-79059-1_21},
	abstract = {Future work should validate the data mesh reference architecture in practice through case studies in various industries. Additionally, a study comparing the efficiency of designing a data mesh solution architecture with the RA, compared to a group not using the RA, can be performed. Research could be performed to asses if the usefulness, quality and variability of the model improve after improvements have been made to the model. Lastly, future research is needed to update this research with new findings from theory and practice, for example, regarding best practices or by identifying different archetypes.},
	language = {en},
	urldate = {2025-06-05},
	booktitle = {Enterprise {Design}, {Operations}, and {Computing}. {EDOC} 2024 {Workshops}},
	publisher = {Springer Nature Switzerland},
	author = {Van Der Werf, Daniel and Moreira, João and Piest, Jean Paul Sebastian},
	editor = {Kaczmarek-Heß, Monika and Rosenthal, Kristina and Suchánek, Marek and Da Silva, Miguel Mira and Proper, Henderik A. and Schnellmann, Marianne},
	year = {2025},
	note = {Series Title: Lecture Notes in Business Information Processing},
	pages = {339--353},
	file = {PDF:/Users/dkapitan/Zotero/storage/8W5W4HMS/Van Der Werf et al. - 2025 - Towards a Data Mesh Reference Architecture.pdf:application/pdf},
}

@book{kleppmann2026designing,
	title = {Designing data-intensive applications, 2nd edtion (early release)},
	publisher = {O'Reilly},
	author = {Kleppmann, Martin and Riccomini, Chris},
	month = jan,
	year = {2026},
}

@misc{ehds,
	title = {European {Health} {Data} {Space} {Regulation} ({EHDS})},
	url = {https://health.ec.europa.eu/ehealth-digital-health-and-care/european-health-data-space-regulation-ehds_en},
	abstract = {EHDS empowers health data control for innovation and cross-border healthcare when travelling. Secure and efficient data use.},
	language = {en},
	urldate = {2025-06-09},
	month = jun,
	year = {2025},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/UZSSPXTW/european-health-data-space-regulation-ehds_en.html:text/html},
}

@misc{dssc2025data,
	title = {Data {Spaces} {Blueprint} v2.0},
	url = {https://dssc.eu/space/BVE2/1071251457/Data+Spaces+Blueprint+v2.0+-+Home},
	urldate = {2025-06-09},
	file = {Data Spaces Blueprint v2.0 - Home - Blueprint v2.0 - Data Spaces Support Centre:/Users/dkapitan/Zotero/storage/Q93JZ5E6/Data+Spaces+Blueprint+v2.html:text/html},
}

@misc{simpl,
	title = {Simpl {Programme}},
	url = {https://simpl-programme.ec.europa.eu/},
	abstract = {.},
	language = {en},
	urldate = {2025-06-09},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/TQDIVTR8/simpl-programme.ec.europa.eu.html:text/html},
}

@misc{tehdas2,
	title = {{TEHDAS2}},
	url = {https://tehdas.eu/},
	abstract = {The TEHDAS2 joint action prepares the ground for the harmonised implementation of the secondary use of health data in the European Health Data Space – EHDS.},
	language = {en-US},
	urldate = {2025-06-09},
	journal = {Tehdas},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/QRLE3XYU/tehdas.eu.html:text/html},
}

@inproceedings{raasveldt2019duckdb,
	address = {Amsterdam Netherlands},
	title = {{DuckDB}: an {Embeddable} {Analytical} {Database}},
	isbn = {978-1-4503-5643-5},
	shorttitle = {{DuckDB}},
	url = {https://dl.acm.org/doi/10.1145/3299869.3320212},
	doi = {10.1145/3299869.3320212},
	abstract = {The immense popularity of SQLite shows that there is a need for unobtrusive in-process data management solutions. However, there is no such system yet geared towards analytical workloads. We demonstrate DuckDB, a novel data management system designed to execute analytical SQL queries while embedded in another process. In our demonstration, we pit DuckDB against other data management solutions to showcase its performance in the embedded analytics scenario. DuckDB is available as Open Source software under a permissive license.},
	language = {en},
	urldate = {2025-06-09},
	booktitle = {Proceedings of the 2019 {International} {Conference} on {Management} of {Data}},
	publisher = {ACM},
	author = {Raasveldt, Mark and Mühleisen, Hannes},
	month = jun,
	year = {2019},
	pages = {1981--1984},
	file = {PDF:/Users/dkapitan/Zotero/storage/DF6EFTJR/Raasveldt and Mühleisen - 2019 - DuckDB an Embeddable Analytical Database.pdf:application/pdf},
}

@inproceedings{nahrstedt2024empirical,
	address = {Salerno Italy},
	title = {An {Empirical} {Study} on the {Energy} {Usage} and {Performance} of {Pandas} and {Polars} {Data} {Analysis} {Python} {Libraries}},
	isbn = {979-8-4007-1701-7},
	url = {https://dl.acm.org/doi/10.1145/3661167.3661203},
	doi = {10.1145/3661167.3661203},
	abstract = {Method. We performed four separate experiment blocks including 8 Data Analysis Tasks (DATs) from an official TPCH Benchmark done by Polars and 6 Synthetic DATs. Both DATs groups are run with small and large dataframes and for both libraries.
Results. Polars is more energy-efficient than Pandas when manipulating large dataframes. For small dataframes, the TPCH Benchmarking DATs does not show significant differences, while for the Synthetic DATs, Polars performs significantly better. We identified strong positive correlations between energy usage and execution time, as well as memory usage for Pandas, while Polars did not show significant memory usage correlations for the majority of runs. There is a significantly negative correlation between energy usage and CPU usage for Pandas.
Conclusions. We recommend using Polars for energy-efficient and fast data analysis, emphasizing the importance of CPU core utilization in library selection. ACM Reference Format: Felix Nahrstedt, Mehdi Karmouche, Karolina Bargieł, Pouyeh Banijamali, Apoorva Nalini Pradeep Kumar, and Ivano Malavolta. 2024. An Empirical Study on the Energy Usage and Performance of Pandas and Polars Data ∗These authors contributed equally to the study Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from permissions@acm.org.},
	language = {en},
	urldate = {2025-06-09},
	booktitle = {Proceedings of the 28th {International} {Conference} on {Evaluation} and {Assessment} in {Software} {Engineering}},
	publisher = {ACM},
	author = {Nahrstedt, Felix and Karmouche, Mehdi and Bargieł, Karolina and Banijamali, Pouyeh and Nalini Pradeep Kumar, Apoorva and Malavolta, Ivano},
	month = jun,
	year = {2024},
	pages = {58--68},
	file = {PDF:/Users/dkapitan/Zotero/storage/8MRIRW27/Nahrstedt et al. - 2024 - An Empirical Study on the Energy Usage and Performance of Pandas and Polars Data Analysis Python Lib.pdf:application/pdf},
}

@techreport{royalsociety2023privacy,
	title = {From privacy to partnership},
	institution = {The Royal Society},
	author = {Royal Society, The},
	month = jan,
	year = {2023},
	file = {From Privacy to Partnership:/Users/dkapitan/Zotero/storage/N7XUTWRD/From Privacy to Partnership.pdf:application/pdf},
}

@misc{sphn,
	title = {{SPHN} - {Swiss} {Personalized} {Health} {Network} ({SPHN})},
	url = {https://sphn.ch/},
	abstract = {Swiss Personalized Health Network (SPHN). Infrastructure building to enable nationwide use and exchange of health data for research.},
	language = {en-GB},
	urldate = {2025-06-09},
	journal = {SPHN},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/YXNRLBE6/sphn.ch.html:text/html},
}

@techreport{2024kikv,
	title = {{KIK}-{V} x {GERDA}},
	url = {https://populationhealthdata.nl/wp-content/uploads/2024/07/Whitepaper-GERDA-x-KIK-V_-databeschikbaarheid-door-hergebruik.pdf},
	institution = {Zorginstituut},
	month = apr,
	year = {2024},
	file = {Whitepaper-GERDA-x-KIK-V_-databeschikbaarheid-door-hergebruik:/Users/dkapitan/Zotero/storage/UD59GDH5/Whitepaper-GERDA-x-KIK-V_-databeschikbaarheid-door-hergebruik.pdf:application/pdf},
}

@book{buschmann1996system,
	series = {Pattern-{Oriented} {Software} {Architecture}},
	title = {A {System} of {Patterns}},
	volume = {1},
	publisher = {Wiley},
	author = {Buschmann, Frank and Meunier, Regine and Rohnert, Hans and Sommerlad, Peter and Stal, Michael},
	year = {1996},
}

@article{nijsse2022fair,
	title = {{FAIR} data station for lightweight metadata management and validation of omics studies},
	volume = {12},
	url = {https://dx.doi.org/10.1093/gigascience/giad014},
	doi = {10.1093/gigascience/giad014},
	abstract = {AbstractBackground. The life sciences are one of the biggest suppliers of scientific data. Reusing and connecting these data can uncover hidden insights an},
	language = {en},
	urldate = {2025-06-10},
	journal = {GigaScience},
	publisher = {Oxford Academic},
	author = {Nijsse, Bart and Schaap, Peter J. and Koehorst, Jasper J.},
	month = dec,
	year = {2022},
	file = {Submitted Version:/Users/dkapitan/Zotero/storage/6ZMHAH44/Nijsse et al. - 2022 - FAIR data station for lightweight metadata management and validation of omics studies.pdf:application/pdf},
}

@incollection{rinaldi2023international,
	title = {International {Clinical} {Research} {Data} {Ecosystem}: {From} {Data} {Standardization} to {Federated} {Analysis}},
	shorttitle = {International {Clinical} {Research} {Data} {Ecosystem}},
	url = {https://ebooks.iospress.nl/doi/10.3233/SHTI230757},
	doi = {10.3233/SHTI230757},
	language = {en},
	urldate = {2025-06-11},
	booktitle = {Telehealth {Ecosystems} in {Practice}},
	publisher = {IOS Press},
	author = {Rinaldi, Eugenia and Dellacasa, Chiara and Puskaric, Miroslav and Osmo, Thomas and Gorska, Anna and Stellmach, Caroline},
	year = {2023},
	pages = {133--134},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/V9I4G94C/Rinaldi et al. - 2023 - International Clinical Research Data Ecosystem From Data Standardization to Federated Analysis.pdf:application/pdf},
}

@article{boninodasilvasantos2022personal,
	title = {Personal {Health} {Train} {Architecture} with {Dynamic} {Cloud} {Staging}},
	volume = {4},
	doi = {10.1007/s42979-022-01422-4},
	abstract = {Scientific advances, especially in the healthcare domain, can be accelerated by making data available for analysis. However, in traditional data analysis systems, data need to be moved to a central processing unit that performs analyses, which may be undesirable, e.g. due to privacy regulations in case these data contain personal information. This paper discusses the Personal Health Train (PHT) approach in which data processing is brought to the (personal health) data rather than the other way around, allowing (private) data accessed to be controlled, and to observe ethical and legal concerns. This paper introduces the PHT architecture and discusses the data staging solution that allows processing to be delegated to components spawned in a private cloud environment in case the (health) organisation hosting the data has limited resources to execute the required processing. This paper shows the feasibility and suitability of the solution with a relatively simple, yet representative, case study of data analysis of Covid-19 infections, which is performed by components that are created on demand and run in the Amazon Web Services platform. This paper also shows that the performance of our solution is acceptable, and that our solution is scalable. This paper demonstrates that the PHT approach enables data analysis with controlled access, preserving privacy and complying with regulations such as GDPR, while the solution is deployed in a private cloud environment.},
	journal = {SN Computer Science},
	author = {Bonino da Silva Santos, Luiz Olavo and Ferreira Pires, Luis and Martinez, Virginia and Moreira, João and Guizzardi, Renata},
	month = oct,
	year = {2022},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/VSEU4UGA/Bonino da Silva Santos et al. - 2022 - Personal Health Train Architecture with Dynamic Cloud Staging.pdf:application/pdf},
}

@inproceedings{martinez2025framework,
	title = {A {Framework} for {Staging} {Personal} {Health} {Trains} in the {Cloud}},
	isbn = {978-989-758-536-4},
	url = {https://www.scitepress.org/Link.aspx?doi=10.5220/0010712800003058},
	abstract = {Digital Library},
	urldate = {2025-06-11},
	author = {Martinez, Virginia Graciano and Pires, Luís Ferreira and Santos, Luiz Olavo Bonino da Silva and Moreira, João Luiz Rebelo and Souza, Renata Guizzardi-Silva},
	month = jun,
	year = {2025},
	pages = {133--144},
	file = {PDF:/Users/dkapitan/Zotero/storage/NMUDIEWN/Martinez et al. - 2025 - A Framework for Staging Personal Health Trains in the Cloud.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/YRB8D83A/Link.html:text/html},
}

@article{avraam2025datashield,
	title = {{DataSHIELD}: mitigating disclosure risk in a multi-site federated analysis platform},
	volume = {5},
	issn = {2635-0041},
	shorttitle = {{DataSHIELD}},
	url = {https://doi.org/10.1093/bioadv/vbaf046},
	doi = {10.1093/bioadv/vbaf046},
	abstract = {The validity of epidemiologic findings can be increased using triangulation, i.e. comparison of findings across contexts, and by having sufficiently large amounts of relevant data to analyse. However, access to data is often constrained by practical considerations and by ethico-legal and data governance restrictions. Gaining access to such data can be time-consuming due to the governance requirements associated with data access requests to institutions in different jurisdictions.DataSHIELD is a software solution that enables remote analysis without the need for data transfer (federated analysis). DataSHIELD is a scientifically mature, open-source data access and analysis platform aligned with the ‘Five Safes’ framework, the international framework governing safe research access to data. It allows real-time analysis while mitigating disclosure risk through an active multi-layer system of disclosure-preventing mechanisms. This combination of real-time remote statistical analysis, disclosure prevention mechanisms, and federation capabilities makes DataSHIELD a solution for addressing many of the technical and regulatory challenges in performing the large-scale statistical analysis of health and biomedical data. This paper describes the key components that comprise the disclosure protection system of DataSHIELD. These broadly fall into three classes: (i) system protection elements, (ii) analysis protection elements, and (iii) governance protection elements.Information about the DataSHIELD software is available in https://datashield.org/ and https://github.com/datashield.},
	number = {1},
	urldate = {2025-06-11},
	journal = {Bioinformatics Advances},
	author = {Avraam, Demetris and Wilson, Rebecca C and Aguirre Chan, Noemi and Banerjee, Soumya and Bishop, Tom R P and Butters, Olly and Cadman, Tim and Cederkvist, Luise and Duijts, Liesbeth and Escribà Montagut, Xavier and Garner, Hugh and Gonçalves, Gonçalo and González, Juan R and Haakma, Sido and Hartlev, Mette and Hasenauer, Jan and Huth, Manuel and Hyde, Eleanor and Jaddoe, Vincent W V and Marcon, Yannick and Mayrhofer, Michaela Th and Molnar-Gabor, Fruzsina and Morgan, Andrei Scott and Murtagh, Madeleine and Nestor, Marc and Nybo Andersen, Anne-Marie and Parker, Simon and Pinot de Moira, Angela and Schwarz, Florian and Strandberg-Larsen, Katrine and Swertz, Morris A and Welten, Marieke and Wheater, Stuart and Burton, Paul},
	month = jan,
	year = {2025},
	pages = {vbaf046},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/JI3FX63E/Avraam et al. - 2025 - DataSHIELD mitigating disclosure risk in a multi-site federated analysis platform.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/Y88VAUQG/8068803.html:text/html},
}

@article{escriba-montagut2024federated,
	title = {Federated privacy-protected meta- and mega-omics data analysis in multi-center studies with a fully open-source analytic platform},
	volume = {20},
	issn = {1553-7358},
	url = {https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1012626},
	doi = {10.1371/journal.pcbi.1012626},
	abstract = {The importance of maintaining data privacy and complying with regulatory requirements is highlighted especially when sharing omic data between different research centers. This challenge is even more pronounced in the scenario where a multi-center effort for collaborative omics studies is necessary. OmicSHIELD is introduced as an open-source tool aimed at overcoming these challenges by enabling privacy-protected federated analysis of sensitive omic data. In order to ensure this, multiple security mechanisms have been included in the software. This innovative tool is capable of managing a wide range of omic data analyses specifically tailored to biomedical research. These include genome and epigenome wide association studies and differential gene expression analyses. OmicSHIELD is designed to support both meta- and mega-analysis, so that it offers a wide range of capabilities for different analysis designs. We present a series of use cases illustrating some examples of how the software addresses real-world analyses of omic data.},
	language = {en},
	number = {12},
	urldate = {2025-06-11},
	journal = {PLOS Computational Biology},
	publisher = {Public Library of Science},
	author = {Escriba-Montagut, Xavier and Marcon, Yannick and Anguita-Ruiz, Augusto and Avraam, Demetris and Urquiza, Jose and Morgan, Andrei S. and Wilson, Rebecca C. and Burton, Paul and Gonzalez, Juan R.},
	month = dec,
	year = {2024},
	keywords = {Genome analysis, Genome-wide association studies, Algorithms, Data management, Genomics, Statistical data, Metaanalysis, Single nucleotide polymorphisms},
	pages = {e1012626},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/DPUFPQ2I/Escriba-Montagut et al. - 2024 - Federated privacy-protected meta- and mega-omics data analysis in multi-center studies with a fully.pdf:application/pdf},
}

@article{mansouri-benssassi2023disclosure,
	title = {Disclosure control of machine learning models from trusted research environments ({TRE}): {New} challenges and opportunities},
	volume = {9},
	issn = {2405-8440},
	shorttitle = {Disclosure control of machine learning models from trusted research environments ({TRE})},
	url = {https://www.sciencedirect.com/science/article/pii/S2405844023023502},
	doi = {10.1016/j.heliyon.2023.e15143},
	abstract = {Introduction
Artificial intelligence (AI) applications in healthcare and medicine have increased in recent years. To enable access to personal data, Trusted Research Environments (TREs) (otherwise known as Safe Havens) provide safe and secure environments in which researchers can access sensitive personal data and develop AI (in particular machine learning (ML)) models. However, currently few TREs support the training of ML models in part due to a gap in the practical decision-making guidance for TREs in handling model disclosure. Specifically, the training of ML models creates a need to disclose new types of outputs from TREs. Although TREs have clear policies for the disclosure of statistical outputs, the extent to which trained models can leak personal training data once released is not well understood.
Background
We review, for a general audience, different types of ML models and their applicability within healthcare. We explain the outputs from training a ML model and how trained ML models can be vulnerable to external attacks to discover personal data encoded within the model.
Risks
We present the challenges for disclosure control of trained ML models in the context of training and exporting models from TREs. We provide insights and analyse methods that could be introduced within TREs to mitigate the risk of privacy breaches when disclosing trained models.
Discussion
Although specific guidelines and policies exist for statistical disclosure controls in TREs, they do not satisfactorily address these new types of output requests; i.e., trained ML models. There is significant potential for new interdisciplinary research opportunities in developing and adapting policies and tools for safely disclosing ML outputs from TREs.},
	number = {4},
	urldate = {2025-06-11},
	journal = {Heliyon},
	author = {Mansouri-Benssassi, Esma and Rogers, Simon and Reel, Smarti and Malone, Maeve and Smith, Jim and Ritchie, Felix and Jefferson, Emily},
	month = apr,
	year = {2023},
	keywords = {Data privacy, Machine learning, AI, Disclosure control, Safe haven, Trusted research environment},
	pages = {e15143},
	file = {Full Text:/Users/dkapitan/Zotero/storage/3KFCB3T9/Mansouri-Benssassi et al. - 2023 - Disclosure control of machine learning models from trusted research environments (TRE) New challeng.pdf:application/pdf},
}

@incollection{rosenau2024structureda,
	title = {Structured {Queries} to {AQL}: {Querying} {OpenEHR} {Data} {Leveraging} a {FHIR}-{Based} {Infrastructure} for {Federated} {Feasibility} {Queries}},
	copyright = {https://creativecommons.org/licenses/by-nc/4.0/},
	isbn = {978-1-64368-456-7 978-1-64368-457-4},
	shorttitle = {Structured {Queries} to {AQL}},
	url = {https://ebooks.iospress.nl/doi/10.3233/SHTI230922},
	doi = {10.3233/SHTI230922},
	abstract = {In digital healthcare, data heterogeneity is a reoccurring issue caused by proprietary source systems. It is often overcome by utilizing ETL processes resulting in data warehouses, which ensure common data models for interoperability. Unfortunately, the achieved interoperability is usually limited to an institutional level. The broad solution space to achieve interoperability with different health data standards is part of the problem, resulting in different standards used at various institutions. For cross-institutional use cases like federated feasibility queries, the issue of heterogeneity is reintroduced. This work showcases how the existing German infrastructure for federated feasibility queries based on Hl7 FHIR can be extended to support openEHR without further data transformation. By utilizing an intermediate query format that can be transferred to FHIR Search, CQL, and AQL.},
	language = {en},
	urldate = {2025-06-11},
	booktitle = {Studies in {Health} {Technology} and {Informatics}},
	publisher = {IOS Press},
	author = {Rosenau, Lorenz and Ingenerf, Josef},
	editor = {Bichel-Findlay, Jen and Otero, Paula and Scott, Philip and Huesing, Elaine},
	month = jan,
	year = {2024},
	file = {PDF:/Users/dkapitan/Zotero/storage/CX272RB6/Rosenau and Ingenerf - 2024 - Structured Queries to AQL Querying OpenEHR Data Leveraging a FHIR-Based Infrastructure for Federate.pdf:application/pdf},
}

@misc{wijnbergen2024fair,
	title = {The {FAIR} {Data} {Point} {Populator}: collaborative {FAIRification} and population of {FAIR} {Data} {Points}},
	copyright = {© 2024, Posted by Cold Spring Harbor Laboratory. The copyright holder for this pre-print is the author. All rights reserved. The material may not be redistributed, re-used or adapted without the author's permission.},
	shorttitle = {The {FAIR} {Data} {Point} {Populator}},
	url = {https://www.biorxiv.org/content/10.1101/2024.09.06.611505v1},
	doi = {10.1101/2024.09.06.611505},
	abstract = {Background Use of the FAIR principles (Findable, Accessible, Interoperable and Reusable) allows the rapidly growing number of biomedical datasets to be optimally (re)used. An important aspect of the FAIR principles is metadata. The FAIR Data Point specifications and reference implementation have been designed as an example on how to publish metadata according to the FAIR principles. Various tools to create metadata have been created, but many of these have limitations, such as interfaces that are not intuitive, metadata that does not adhere to a common metadata schema, limited scalability, and inefficient collaboration. We aim to address these limitations in the FAIR Data Point Populator.
Results The FAIR Data Point Populator consists of a GitHub workflow together with Excel templates that have tooltips, validation and documentation. The Excel templates are targeted towards non-technical users, and can be used collaboratively in online spreadsheet software. A more technical user then uses the GitHub workflow to read multiple entries in the Excel sheets, and transform it into machine readable metadata. This metadata is then automatically uploaded to a connected FAIR Data Point. We applied the FAIR Data Point Populator on the metadata of two datasets, and a patient registry. We were then able to run a query on the FAIR Data Point Index, in order to retrieve one of the datasets.
Conclusion The FAIR Data Point Populator addresses several limitations of other tools. It makes creating metadata easier, ensures adherence to a common metadata schema, allows bulk creation of metadata entries and increases collaboration. As a result of this, the barrier of entry for FAIRification is lower, which enables the creation of FAIR data by more people.},
	language = {en},
	urldate = {2025-06-11},
	publisher = {bioRxiv},
	author = {Wijnbergen, Daphne and Kaliyaperumal, Rajaram and Burger, Kees and Santos, Luiz Olavo Bonino da Silva and Mons, Barend and Roos, Marco and Mina, Eleni},
	month = sep,
	year = {2024},
	note = {Pages: 2024.09.06.611505
Section: New Results},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/TJ7SRJ62/Wijnbergen et al. - 2024 - The FAIR Data Point Populator collaborative FAIRification and population of FAIR Data Points.pdf:application/pdf},
}

@article{queralt-rosinach2022applying,
	title = {Applying the {FAIR} principles to data in a hospital: challenges and opportunities in a pandemic},
	volume = {13},
	issn = {2041-1480},
	shorttitle = {Applying the {FAIR} principles to data in a hospital},
	url = {https://doi.org/10.1186/s13326-022-00263-7},
	doi = {10.1186/s13326-022-00263-7},
	abstract = {The COVID-19 pandemic has challenged healthcare systems and research worldwide. Data is collected all over the world and needs to be integrated and made available to other researchers quickly. However, the various heterogeneous information systems that are used in hospitals can result in fragmentation of health data over multiple data ‘silos’ that are not interoperable for analysis. Consequently, clinical observations in hospitalised patients are not prepared to be reused efficiently and timely. There is a need to adapt the research data management in hospitals to make COVID-19 observational patient data machine actionable, i.e. more Findable, Accessible, Interoperable and Reusable (FAIR) for humans and machines. We therefore applied the FAIR principles in the hospital to make patient data more FAIR.},
	number = {1},
	urldate = {2025-06-11},
	journal = {Journal of Biomedical Semantics},
	author = {Queralt-Rosinach, Núria and Kaliyaperumal, Rajaram and Bernabé, César H. and Long, Qinqin and Joosten, Simone A. and van der Wijk, Henk Jan and Flikkenschild, Erik L.A. and Burger, Kees and Jacobsen, Annika and Mons, Barend and Roos, Marco and {BEAT-COVID Group} and {COVID-19 LUMC Group}},
	month = apr,
	year = {2022},
	keywords = {Ontologies, Open science, FAIR, Hospital, Patient data, Research data management},
	pages = {12},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/TNNJGUKZ/Queralt-Rosinach et al. - 2022 - Applying the FAIR principles to data in a hospital challenges and opportunities in a pandemic.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/S579ATQU/s13326-022-00263-7.html:text/html},
}

@incollection{bader2020internationala,
	address = {Cham},
	title = {The {International} {Data} {Spaces} {Information} {Model} – {An} {Ontology} for {Sovereign} {Exchange} of {Digital} {Content}},
	volume = {12507},
	isbn = {978-3-030-62465-1 978-3-030-62466-8},
	url = {https://link.springer.com/10.1007/978-3-030-62466-8_12},
	doi = {10.1007/978-3-030-62466-8_12},
	abstract = {The International Data Spaces initiative (IDS) is building an ecosystem to facilitate data exchange in a secure, trusted, and semantically interoperable way. It aims at providing a basis for smart services and cross-company business processes, while at the same time guaranteeing data owners’ sovereignty over their content. The IDS Information Model is an RDFS/OWL ontology defining the fundamental concepts for describing actors in a data space, their interactions, the resources exchanged by them, and data usage restrictions. After introducing the conceptual model and design of the ontology, we explain its implementation on top of standard ontologies as well as the process for its continuous evolution and quality assurance involving a community driven by industry and research organisations. We demonstrate tools that support generation, validation, and usage of instances of the ontology with the focus on data control and protection in a federated ecosystem.},
	language = {en},
	urldate = {2025-06-12},
	booktitle = {The {Semantic} {Web} – {ISWC} 2020},
	publisher = {Springer International Publishing},
	author = {Bader, Sebastian and Pullmann, Jaroslav and Mader, Christian and Tramp, Sebastian and Quix, Christoph and Müller, Andreas W. and Akyürek, Haydar and Böckmann, Matthias and Imbusch, Benedikt T. and Lipp, Johannes and Geisler, Sandra and Lange, Christoph},
	editor = {Pan, Jeff Z. and Tamma, Valentina and d’Amato, Claudia and Janowicz, Krzysztof and Fu, Bo and Polleres, Axel and Seneviratne, Oshani and Kagal, Lalana},
	year = {2020},
	note = {Series Title: Lecture Notes in Computer Science},
	pages = {176--192},
	file = {PDF:/Users/dkapitan/Zotero/storage/3SPYNRRS/Bader et al. - 2020 - The International Data Spaces Information Model – An Ontology for Sovereign Exchange of Digital Cont.pdf:application/pdf},
}

@misc{martella2025designing,
	title = {Designing {Data} {Spaces}: {Navigating} the {European} {Initiatives} {Along} {Technical} {Specifications}},
	shorttitle = {Designing {Data} {Spaces}},
	url = {http://arxiv.org/abs/2503.15993},
	doi = {10.48550/arXiv.2503.15993},
	abstract = {The emerging paradigm of data economy can constitute an unmissable and attractive opportunity for companies that aim to consider their data as valuable assets. To fully leverage this opportunity, data owners need to have specific and precise guarantees regarding the protection of data they share from unauthorized access, but also from their misuse. Thus, it becomes crucial to provide mechanisms for secure and trusted data sharing capable of protecting data ownership rights and specifying agreed-upon methods of use. In this sense, data space technology can represent a promising and innovative solution in data management that aims to promote effective and trusted data exchange and sharing. By providing standardized technologies and legal frameworks, data spaces seek to eliminate barriers to data sharing among companies and organizations and, ultimately, fostering the development of innovative value-added services. By promoting interoperability and data sovereignty, data spaces play a crucial role in enhancing collaboration and innovation in the data economy. In this paper, the key European initiatives are collected and organized, with the goal of identifying the most recent advances in the direction of harmonizing the specifications, to facilitate the seamless integration between different solutions and foster secure, flexible and scalable data spaces implementations. The results of this study provide guidelines that can support data space designers in driving the choice of the most proper technical specifications to adopt, among the available open-source solutions.},
	language = {en},
	urldate = {2025-06-12},
	publisher = {arXiv},
	author = {Martella, Angelo and Martella, Cristian and Longo, Antonella},
	month = mar,
	year = {2025},
	note = {arXiv:2503.15993 [cs]},
	keywords = {Computer Science - Databases},
	file = {PDF:/Users/dkapitan/Zotero/storage/FFL78BU9/Martella et al. - 2025 - Designing Data Spaces Navigating the European Initiatives Along Technical Specifications.pdf:application/pdf},
}

@techreport{krewer2024digital,
	title = {Digital {Commons} as {Providers} of {Public} {Digital} {Infrastructures}},
	url = {https://openfuture.eu/publication/digital-commons-as-providers-of-public-digital-infrastructures},
	abstract = {This paper examines literature on public digital infrastructures and current global debates. It presents five case studies demonstrating how Digital Commons can support and improve these infrastructures.},
	language = {en-US},
	urldate = {2025-06-15},
	institution = {Open Future Foundation},
	author = {Krewer, Jan and Warso, Zuzanna},
	month = nov,
	year = {2024},
	file = {PDF:/Users/dkapitan/Zotero/storage/QJSMLMF5/Digital Commons as Providers of Public Digital Infrastructures.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/W9N8CT3J/digital-commons-as-providers-of-public-digital-infrastructures.html:text/html},
}

@misc{welten2024pasta4pht,
	title = {{PASTA}-4-{PHT}: {A} {Pipeline} for {Automated} {Security} and {Technical} {Audits} for the {Personal} {Health} {Train}},
	shorttitle = {{PASTA}-4-{PHT}},
	url = {http://arxiv.org/abs/2412.01275},
	doi = {10.48550/arXiv.2412.01275},
	abstract = {With the introduction of data protection regulations, the need for innovative privacy-preserving approaches to process and analyse sensitive data has become apparent. One approach is the Personal Health Train (PHT) that brings analysis code to the data and conducts the data processing at the data premises. However, despite its demonstrated success in various studies, the execution of external code in sensitive environments, such as hospitals, introduces new research challenges because the interactions of the code with sensitive data are often incomprehensible and lack transparency. These interactions raise concerns about potential effects on the data and increases the risk of data breaches. To address this issue, this work discusses a PHT-aligned security and audit pipeline inspired by DevSecOps principles. The automated pipeline incorporates multiple phases that detect vulnerabilities. To thoroughly study its versatility, we evaluate this pipeline in two ways. First, we deliberately introduce vulnerabilities into a PHT. Second, we apply our pipeline to five real-world PHTs, which have been utilised in real-world studies, to audit them for potential vulnerabilities. Our evaluation demonstrates that our designed pipeline successfully identifies potential vulnerabilities and can be applied to real-world studies. In compliance with the requirements of the GDPR for data management, documentation, and protection, our automated approach supports researchers using in their data-intensive work and reduces manual overhead. It can be used as a decision-making tool to assess and document potential vulnerabilities in code for data processing. Ultimately, our work contributes to an increased security and overall transparency of data processing activities within the PHT framework.},
	urldate = {2025-06-17},
	publisher = {arXiv},
	author = {Welten, Sascha and Kindermann, Karl and Polat, Ahmet and Görz, Martin and Jugl, Maximilian and Neumann, Laurenz and Neumann, Alexander and Lohmöller, Johannes and Pennekamp, Jan and Decker, Stefan},
	month = dec,
	year = {2024},
	note = {arXiv:2412.01275 [cs]},
	keywords = {Computer Science - Cryptography and Security, Computer Science - Distributed, Parallel, and Cluster Computing},
	file = {Preprint PDF:/Users/dkapitan/Zotero/storage/23LW6353/Welten et al. - 2024 - PASTA-4-PHT A Pipeline for Automated Security and Technical Audits for the Personal Health Train.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/33YWYVIL/2412.html:text/html},
}

@article{raab2023federated,
	title = {Federated electronic health records for the {European} {Health} {Data} {Space}},
	volume = {5},
	issn = {2589-7500},
	doi = {10.1016/S2589-7500(23)00156-5},
	abstract = {The European Commission's draft for the European Health Data Space (EHDS) aims to empower citizens to access their personal health data and share it with physicians and other health-care providers. It further defines procedures for the secondary use of electronic health data for research and development. Although this planned legislation is undoubtedly a step in the right direction, implementation approaches could potentially result in centralised data silos that pose data privacy and security risks for individuals. To address this concern, we propose federated personal health data spaces, a novel architecture for storing, managing, and sharing personal electronic health records that puts citizens at the centre-both conceptually and technologically. The proposed architecture puts citizens in control by storing personal health data on a combination of personal devices rather than in centralised data silos. We describe how this federated architecture fits within the EHDS and can enable the same features as centralised systems while protecting the privacy of citizens. We further argue that increased privacy and control do not contradict the use of electronic health data for research and development. Instead, data sovereignty and transparency encourage active participation in studies and data sharing. This combination of privacy-by-design and transparent, privacy-preserving data sharing can enable health-care leaders to break the privacy-exploitation barrier, which currently limits the secondary use of health data in many cases.},
	language = {eng},
	number = {11},
	journal = {The Lancet. Digital Health},
	author = {Raab, René and Küderle, Arne and Zakreuskaya, Anastasiya and Stern, Ariel D. and Klucken, Jochen and Kaissis, Georgios and Rueckert, Daniel and Boll, Susanne and Eils, Roland and Wagener, Harald and Eskofier, Bjoern M.},
	month = nov,
	year = {2023},
	keywords = {Humans, Privacy, Physicians, Electronic Health Records, Delivery of Health Care, Computer Security},
	pages = {e840--e847},
	file = {Full Text:/Users/dkapitan/Zotero/storage/KNN6MPCE/Raab et al. - 2023 - Federated electronic health records for the European Health Data Space.pdf:application/pdf},
}

@article{kahn2006framework,
	title = {A framework for distributed digital object services},
	volume = {6},
	copyright = {http://www.springer.com/tdm},
	issn = {1432-5012, 1432-1300},
	url = {http://link.springer.com/10.1007/s00799-005-0128-x},
	doi = {10.1007/s00799-005-0128-x},
	language = {en},
	number = {2},
	urldate = {2025-06-19},
	journal = {International Journal on Digital Libraries},
	author = {Kahn, Robert and Wilensky, Robert},
	month = apr,
	year = {2006},
	pages = {115--123},
	file = {PDF:/Users/dkapitan/Zotero/storage/X42TYRC3/Kahn and Wilensky - 2006 - A framework for distributed digital object services.pdf:application/pdf},
}

@misc{boninodasilvasantos2022fair,
	title = {{FAIR} {Digital} {Object} {Framework}},
	url = {https://fairdigitalobjectframework.org/},
	urldate = {2025-06-19},
	author = {Bonino da Silva Santos, Luiz Olavo and Guizzardi, Giancarlo and Prince Sales, Tiago},
	month = oct,
	year = {2022},
}

@article{wang2025survey,
	title = {A {Survey} on {Federated} {Analytics}: {Taxonomy}, {Enabling} {Techniques}, {Applications} and {Open} {Issues}},
	copyright = {https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html},
	issn = {1553-877X, 2373-745X},
	shorttitle = {A {Survey} on {Federated} {Analytics}},
	url = {https://ieeexplore.ieee.org/document/10960683/},
	doi = {10.1109/COMST.2025.3558755},
	abstract = {The escalating influx of data generated by networked edge devices, coupled with the growing awareness of data privacy, has restricted the traditional data analytics workflow, where the edge data are gathered by a centralized server to be further utilized by data analysts. To continue leveraging vast edge data to support various data-incentive applications, computing paradigms have promoted a transformative shift from centralized data processing to privacy-preserved distributed data processing. The need to perform data analytics on private edge data motivates federated analytics (FA), an emerging technique to support collaborative data analytics among diverse data owners without centralizing the raw data. Despite the wide applications of FA in industry and academia, a comprehensive examination of existing research efforts in FA has been notably absent. This survey aims to bridge this gap by first providing an overview of FA, elucidating key concepts, and discussing its relationship with similar concepts. We then thoroughly examine FA, including its key challenges, taxonomy, and enabling techniques. Diverse FA applications, including statistical metrics, frequency-related applications, database query operations, FL-assisting FA tasks, and other wireless network applications are then carefully reviewed. We complete the survey with several open research issues, future directions, and a comprehensive lessons learned part. This survey intends to provide a holistic understanding of the emerging FA techniques and foster the continued evolution of privacy-preserving distributed data processing in the emerging networked society.},
	language = {en},
	urldate = {2025-06-19},
	journal = {IEEE Communications Surveys \& Tutorials},
	author = {Wang, Zibo and Ji, Haichao and Zhu, Yifei and Wang, Dan and Han, Zhu},
	year = {2025},
	pages = {1--1},
	file = {PDF:/Users/dkapitan/Zotero/storage/FWAP8KGY/Wang et al. - 2025 - A Survey on Federated Analytics Taxonomy, Enabling Techniques, Applications and Open Issues.pdf:application/pdf},
}

@inproceedings{gorod2008paradox,
	title = {Paradox: {Holarchical} view of system of systems engineering management},
	shorttitle = {Paradox},
	url = {https://ieeexplore.ieee.org/abstract/document/4724171},
	doi = {10.1109/SYSOSE.2008.4724171},
	abstract = {This paper focuses on a method of developing a framework for effective System of Systems Engineering (SoSE) management.While developing the management process in dealing with SoSE, we are searching for ways to engineer multiple integrated complex systems, which can be concurrently, highly emergent and effectively governable. The authors propose to utilize the "holarchical view" methodology to identify and examine this essential phenomenon of paradoxes of SoSE management. The proposed method is based on the Boardman-Sauser five distinguishing characteristics of Autonomy, Belonging, Connectivty, Diversity, and Emergence. The outcome of this research would influence further studies on the topic and greatly contribute to the SoSE body of knowledge.},
	urldate = {2025-06-23},
	booktitle = {2008 {IEEE} {International} {Conference} on {System} of {Systems} {Engineering}},
	author = {Gorod, Alex and Sauser, Brian and Boardman, John},
	month = jun,
	year = {2008},
	keywords = {Autonomy, Belonging, Chaos, Character recognition, Connectivity, Disaster management, Diversity, Emergence, Engineering management, Glass, Holarchical view, Military computing, Paradox, Production systems, Research and development management, SoSE Management, Systems engineering and theory, Technology management},
	pages = {1--6},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/47EGSQFJ/Gorod et al. - 2008 - Paradox Holarchical view of system of systems engineering management.pdf:application/pdf},
}

@article{sansone2012interoperable,
	title = {Toward interoperable bioscience data},
	volume = {44},
	copyright = {2012 The Author(s)},
	issn = {1546-1718},
	url = {https://www.nature.com/articles/ng.1054},
	doi = {10.1038/ng.1054},
	abstract = {To make full use of research data, the bioscience community needs to adopt technologies and reward mechanisms that support interoperability and promote the growth of an open 'data commoning' culture. Here we describe the prerequisites for data commoning and present an established and growing ecosystem of solutions using the shared 'Investigation-Study-Assay' framework to support that vision.},
	language = {en},
	number = {2},
	urldate = {2025-06-23},
	journal = {Nature Genetics},
	publisher = {Nature Publishing Group},
	author = {Sansone, Susanna-Assunta and Rocca-Serra, Philippe and Field, Dawn and Maguire, Eamonn and Taylor, Chris and Hofmann, Oliver and Fang, Hong and Neumann, Steffen and Tong, Weida and Amaral-Zettler, Linda and Begley, Kimberly and Booth, Tim and Bougueleret, Lydie and Burns, Gully and Chapman, Brad and Clark, Tim and Coleman, Lee-Ann and Copeland, Jay and Das, Sudeshna and de Daruvar, Antoine and de Matos, Paula and Dix, Ian and Edmunds, Scott and Evelo, Chris T. and Forster, Mark J. and Gaudet, Pascale and Gilbert, Jack and Goble, Carole and Griffin, Julian L. and Jacob, Daniel and Kleinjans, Jos and Harland, Lee and Haug, Kenneth and Hermjakob, Henning and Sui, Shannan J. Ho and Laederach, Alain and Liang, Shaoguang and Marshall, Stephen and McGrath, Annette and Merrill, Emily and Reilly, Dorothy and Roux, Magali and Shamu, Caroline E. and Shang, Catherine A. and Steinbeck, Christoph and Trefethen, Anne and Williams-Jones, Bryn and Wolstencroft, Katherine and Xenarios, Ioannis and Hide, Winston},
	month = feb,
	year = {2012},
	keywords = {Research data},
	pages = {121--126},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/7CEPP88H/Sansone et al. - 2012 - Toward interoperable bioscience data.pdf:application/pdf},
}

@article{johnson2021isa,
	title = {{ISA} {API}: {An} open platform for interoperable life science experimental metadata},
	volume = {10},
	issn = {2047-217X},
	shorttitle = {{ISA} {API}},
	url = {https://doi.org/10.1093/gigascience/giab060},
	doi = {10.1093/gigascience/giab060},
	abstract = {The Investigation/Study/Assay (ISA) Metadata Framework is an established and widely used set of open source community specifications and software tools for enabling discovery, exchange, and publication of metadata from experiments in the life sciences. The original ISA software suite provided a set of user-facing Java tools for creating and manipulating the information structured in ISA-Tab—a now widely used tabular format. To make the ISA framework more accessible to machines and enable programmatic manipulation of experiment metadata, the JSON serialization ISA-JSON was developed.In this work, we present the ISA API, a Python library for the creation, editing, parsing, and validating of ISA-Tab and ISA-JSON formats by using a common data model engineered as Python object classes. We describe the ISA API feature set, early adopters, and its growing user community.The ISA API provides users with rich programmatic metadata-handling functionality to support automation, a common interface, and an interoperable medium between the 2 ISA formats, as well as with other life science data formats required for depositing data in public databases.},
	number = {9},
	urldate = {2025-06-23},
	journal = {GigaScience},
	author = {Johnson, David and Batista, Dominique and Cochrane, Keeva and Davey, Robert P and Etuk, Anthony and Gonzalez-Beltran, Alejandra and Haug, Kenneth and Izzo, Massimiliano and Larralde, Martin and Lawson, Thomas N and Minotto, Alice and Moreno, Pablo and Nainala, Venkata Chandrasekhar and O'Donovan, Claire and Pireddu, Luca and Roger, Pierrick and Shaw, Felix and Steinbeck, Christoph and Weber, Ralf J M and Sansone, Susanna-Assunta and Rocca-Serra, Philippe},
	month = sep,
	year = {2021},
	pages = {giab060},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/BPDN8CDA/Johnson et al. - 2021 - ISA API An open platform for interoperable life science experimental metadata.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/D5CZY3RD/6371038.html:text/html},
}

@article{ladewig2023ga4gh,
	title = {{GA4GH} {Phenopackets}: {A} {Practical} {Introduction}},
	volume = {4},
	issn = {2641-6573},
	shorttitle = {{GA4GH} {Phenopackets}},
	url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/ggn2.202200016},
	doi = {10.1002/ggn2.202200016},
	abstract = {The Global Alliance for Genomics and Health (GA4GH) is developing a suite of coordinated standards for genomics for healthcare. The Phenopacket is a new GA4GH standard for sharing disease and phenotype information that characterizes an individual person, linking that individual to detailed phenotypic descriptions, genetic information, diagnoses, and treatments. A detailed example is presented that illustrates how to use the schema to represent the clinical course of a patient with retinoblastoma, including demographic information, the clinical diagnosis, phenotypic features and clinical measurements, an examination of the extirpated tumor, therapies, and the results of genomic analysis. The Phenopacket Schema, together with other GA4GH data and technical standards, will enable data exchange and provide a foundation for the computational analysis of disease and phenotype information to improve our ability to diagnose and conduct research on all types of disorders, including cancer and rare diseases.},
	language = {en},
	number = {1},
	urldate = {2025-06-23},
	journal = {Advanced Genetics},
	author = {Ladewig, Markus S. and Jacobsen, Julius O. B. and Wagner, Alex H. and Danis, Daniel and El Kassaby, Baha and Gargano, Michael and Groza, Tudor and Baudis, Michael and Steinhaus, Robin and Seelow, Dominik and Bechrakis, Nikolaos E. and Mungall, Christopher J. and Schofield, Paul N. and Elemento, Olivier and Smith, Lindsay and McMurry, Julie A. and Munoz-Torres, Monica and Haendel, Melissa A. and Robinson, Peter N.},
	year = {2023},
	note = {\_eprint: https://advanced.onlinelibrary.wiley.com/doi/pdf/10.1002/ggn2.202200016},
	keywords = {FAIR data, deep phenotyping, Global Alliance for Genomics and Health, Human Phenotype Ontology, Phenopacket Schema},
	pages = {2200016},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/CEZQNW8L/Ladewig et al. - 2023 - GA4GH Phenopackets A Practical Introduction.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/9PDDJBQE/ggn2.html:text/html},
}

@article{cadavid2024docker,
	title = {Beyond {Docker}: {Enhancing} vantage6 with {Kubernetes} for {Federated} {Learning}},
	volume = {316},
	issn = {1879-8365},
	shorttitle = {Beyond {Docker}},
	doi = {10.3233/SHTI240729},
	abstract = {Vantage6, a powerful platform for privacy-preserving analysis in the life-sciences domain, employs Docker in its data nodes when performing tasks like federated learning. This tight bond to Docker poses challenges on infrastructure security, efficient computing resources usage, and integration of alternative container technologies. To overcome these challenges, we explored the integration of Kubernetes into vantage6 through a Proof-of-Concept (PoC) approach. The PoC designed and implemented a Kubernetes-based architecture for vantage6, which can be easily deployed on a single machine or a cluster. This PoC serves as the reference to accelerate the adoption of Kubernetes in vantage6.},
	language = {eng},
	journal = {Studies in Health Technology and Informatics},
	author = {Cadavid, Héctor and Geng, Cunliang},
	month = aug,
	year = {2024},
	keywords = {Humans, Machine Learning, Software, Federated learning, Kubernetes, Computer Security, Biological Science Disciplines, Containers, Docker, vantage6},
	pages = {1603--1604},
	file = {Full Text:/Users/dkapitan/Zotero/storage/ZGKKEMBM/Cadavid and Geng - 2024 - Beyond Docker Enhancing vantage6 with Kubernetes for Federated Learning.pdf:application/pdf},
}

@article{riviera2023felebrities,
	title = {{FeLebrities}: {A} {User}-{Centric} {Assessment} of {Federated} {Learning} {Frameworks}},
	volume = {11},
	issn = {2169-3536},
	shorttitle = {{FeLebrities}},
	url = {https://ieeexplore.ieee.org/ielx7/6287639/10005208/10242027.pdf},
	doi = {10.1109/ACCESS.2023.3312579},
	abstract = {Federated Learning (FL) is a new paradigm aimed at solving data access problems. It provides a solution by moving the focus from sharing data to sharing models. The FL paradigm involves different entities (institutions) holding proprietary datasets that, contributing with each other to train a global Artificial Intelligence (AI) model using their own locally available data. Although several studies have proposed methods to distribute the computation or aggregate results, few efforts have been made to cover on how to implement FL pipelines. With the aim of accelerating the exploitation of FL frameworks, this paper proposes a survey of public tools that are currently available for building FL pipelines, an objective ranking based on the current state of user preferences, and an assessment of the growing trend of the tool’s popularity over a one year time window, with measurements performed every six months. These measurements include objective metrics, like the number of “Watch,” “Star” and “Follow” available from software repositories as well as thirteen custom metrics grouped into three main categories: Usability, Portability, and Flexibility. Finally, a ranking of the maturity of the tools is derived based on the key aspects to consider when building a FL pipeline.},
	urldate = {2025-06-24},
	journal = {IEEE Access},
	author = {Riviera, Walter and Galazzo, Ilaria Boscolo and Menegaz, Gloria},
	year = {2023},
	keywords = {Artificial intelligence, Data models, Computational modeling, Federated learning, Surveys, AI at scale, Distributed management, distributed systems, Federated learning tools, Guidelines},
	pages = {96865--96878},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/H3KEUTSJ/Riviera et al. - 2023 - FeLebrities A User-Centric Assessment of Federated Learning Frameworks.pdf:application/pdf},
}

@book{li2024challenges,
	title = {From {Challenges} and {Pitfalls} to {Recommendations} and {Opportunities}: {Implementing} {Federated} {Learning} in {Healthcare}},
	shorttitle = {From {Challenges} and {Pitfalls} to {Recommendations} and {Opportunities}},
	doi = {10.48550/arXiv.2409.09727},
	abstract = {Federated learning holds great potential for enabling large-scale healthcare research and collaboration across multiple centres while ensuring data privacy and security are not compromised. Although numerous recent studies suggest or utilize federated learning based methods in healthcare, it remains unclear which ones have potential clinical utility. This review paper considers and analyzes the most recent studies up to May 2024 that describe federated learning based methods in healthcare. After a thorough review, we find that the vast majority are not appropriate for clinical use due to their methodological flaws and/or underlying biases which include but are not limited to privacy concerns, generalization issues, and communication costs. As a result, the effectiveness of federated learning in healthcare is significantly compromised. To overcome these challenges, we provide recommendations and promising opportunities that might be implemented to resolve these problems and improve the quality of model development in federated learning with healthcare.},
	author = {Li, Ming and Xu, Pengcheng and Hu, Junjie and Tang, Zeyu and Yang, Guang},
	month = sep,
	year = {2024},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/7LYW3Y58/Li et al. - 2024 - From Challenges and Pitfalls to Recommendations and Opportunities Implementing Federated Learning i.pdf:application/pdf},
}

@misc{jmirc,
	title = {{JMIR} {AI} - {Advancing} {Privacy}-{Preserving} {Health} {Care} {Analytics} and {Implementation} of the {Personal} {Health} {Train}: {Federated} {Deep} {Learning} {Study}},
	url = {https://ai.jmir.org/2025/1/e60847},
	urldate = {2025-06-24},
	file = {JMIR AI - Advancing Privacy-Preserving Health Care Analytics and Implementation of the Personal Health Train\: Federated Deep Learning Study:/Users/dkapitan/Zotero/storage/UB8FREI6/e60847.html:text/html},
}

@misc{eosc-entrust,
	title = {European network of trusted research environments ({EOSC}-{ENTRUST}) project},
	url = {https://eosc-entrust.eu/},
	abstract = {EOSC-ENTRUST aims to create a European network of Trusted Research Environments (TREs) for sensitive data.},
	language = {en},
	urldate = {2025-06-26},
	journal = {EOSC-ENTRUST},
	month = mar,
	year = {2024},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/8MUED39X/eosc-entrust.eu.html:text/html},
}

@article{choudhury2025advancing,
	title = {Advancing {Privacy}-{Preserving} {Health} {Care} {Analytics} and {Implementation} of the {Personal} {Health} {Train}: {Federated} {Deep} {Learning} {Study}},
	volume = {4},
	shorttitle = {Advancing {Privacy}-{Preserving} {Health} {Care} {Analytics} and {Implementation} of the {Personal} {Health} {Train}},
	url = {https://ai.jmir.org/2025/1/e60847},
	doi = {10.2196/60847},
	abstract = {Background: The rapid advancement of deep learning in health care presents significant opportunities for automating complex medical tasks and improving clinical workflows. However, widespread adoption is impeded by data privacy concerns and the necessity for large, diverse datasets across multiple institutions. Federated learning (FL) has emerged as a viable solution, enabling collaborative artificial intelligence model development without sharing individual patient data. To effectively implement FL in health care, robust and secure infrastructures are essential. Developing such federated deep learning frameworks is crucial to harnessing the full potential of artificial intelligence while ensuring patient data privacy and regulatory compliance.
Objective: The objective is to introduce an innovative FL infrastructure called the Personal Health Train (PHT) that includes the procedural, technical, and governance components needed to implement FL on real-world health care data, including training deep learning neural networks. The study aims to apply this federated deep learning infrastructure to the use case of gross tumor volume segmentation on chest computed tomography images of patients with lung cancer and present the results from a proof-of-concept experiment.
Methods: The PHT framework addresses the challenges of data privacy when sharing data, by keeping data close to the source and instead bringing the analysis to the data. Technologically, PHT requires 3 interdependent components: “tracks” (protected communication channels), “trains” (containerized software apps), and “stations” (institutional data repositories), which are supported by the open source “Vantage6” software. The study applies this federated deep learning infrastructure to the use case of gross tumor volume segmentation on chest computed tomography images of patients with lung cancer, with the introduction of an additional component called the secure aggregation server, where the model averaging is done in a trusted and inaccessible environment.
Results: We demonstrated the feasibility of executing deep learning algorithms in a federated manner using PHT and presented the results from a proof-of-concept study. The infrastructure linked 12 hospitals across 8 nations, covering 4 continents, demonstrating the scalability and global reach of the proposed approach. During the execution and training of the deep learning algorithm, no data were shared outside the hospital.
Conclusions: The findings of the proof-of-concept study, as well as the implications and limitations of the infrastructure and the results, are discussed. The application of federated deep learning to unstructured medical imaging data, facilitated by the PHT framework and Vantage6 platform, represents a significant advancement in the field. The proposed infrastructure addresses the challenges of data privacy and enables collaborative model development, paving the way for the widespread adoption of deep learning–based tools in the medical domain and beyond. The introduction of the secure aggregation server implied that data leakage problems in FL can be prevented by careful design decisions of the infrastructure.
Trial Registration: ClinicalTrials.gov NCT05775068; https://clinicaltrials.gov/study/NCT05775068},
	language = {EN},
	number = {1},
	urldate = {2025-06-26},
	journal = {JMIR AI},
	publisher = {JMIR Publications Inc., Toronto, Canada},
	author = {Choudhury, Ananya and Volmer, Leroy and Martin, Frank and Fijten, Rianne and Wee, Leonard and Dekker, Andre and Soest, Johan van},
	month = feb,
	year = {2025},
	note = {Company: JMIR AI
Distributor: JMIR AI
Institution: JMIR AI
Label: JMIR AI},
	pages = {e60847},
	file = {PDF:/Users/dkapitan/Zotero/storage/2JCJLFIT/Choudhury et al. - 2025 - Advancing Privacy-Preserving Health Care Analytics and Implementation of the Personal Health Train.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/MXEUL77T/e60847.html:text/html},
}

@incollection{bader2020international,
	address = {Cham},
	title = {The {International} {Data} {Spaces} {Information} {Model} – {An} {Ontology} for {Sovereign} {Exchange} of {Digital} {Content}},
	volume = {12507},
	isbn = {978-3-030-62465-1 978-3-030-62466-8},
	url = {https://link.springer.com/10.1007/978-3-030-62466-8_12},
	doi = {10.1007/978-3-030-62466-8_12},
	abstract = {The International Data Spaces initiative (IDS) is building an ecosystem to facilitate data exchange in a secure, trusted, and semantically interoperable way. It aims at providing a basis for smart services and cross-company business processes, while at the same time guaranteeing data owners’ sovereignty over their content. The IDS Information Model is an RDFS/OWL ontology defining the fundamental concepts for describing actors in a data space, their interactions, the resources exchanged by them, and data usage restrictions. After introducing the conceptual model and design of the ontology, we explain its implementation on top of standard ontologies as well as the process for its continuous evolution and quality assurance involving a community driven by industry and research organisations. We demonstrate tools that support generation, validation, and usage of instances of the ontology with the focus on data control and protection in a federated ecosystem.},
	language = {en},
	urldate = {2025-06-26},
	booktitle = {The {Semantic} {Web} – {ISWC} 2020},
	publisher = {Springer International Publishing},
	author = {Bader, Sebastian and Pullmann, Jaroslav and Mader, Christian and Tramp, Sebastian and Quix, Christoph and Müller, Andreas W. and Akyürek, Haydar and Böckmann, Matthias and Imbusch, Benedikt T. and Lipp, Johannes and Geisler, Sandra and Lange, Christoph},
	editor = {Pan, Jeff Z. and Tamma, Valentina and d’Amato, Claudia and Janowicz, Krzysztof and Fu, Bo and Polleres, Axel and Seneviratne, Oshani and Kagal, Lalana},
	year = {2020},
	note = {Series Title: Lecture Notes in Computer Science},
	pages = {176--192},
	file = {PDF:/Users/dkapitan/Zotero/storage/VCISXZ4K/Bader et al. - 2020 - The International Data Spaces Information Model – An Ontology for Sovereign Exchange of Digital Cont.pdf:application/pdf},
}

@article{mcmurry2024cumulusa,
	title = {Cumulus: a federated electronic health record-based learning system powered by {Fast} {Healthcare} {Interoperability} {Resources} and artificial intelligence},
	volume = {31},
	issn = {1527-974X},
	shorttitle = {Cumulus},
	url = {https://doi.org/10.1093/jamia/ocae130},
	doi = {10.1093/jamia/ocae130},
	abstract = {To address challenges in large-scale electronic health record (EHR) data exchange, we sought to develop, deploy, and test an open source, cloud-hosted app “listener” that accesses standardized data across the SMART/HL7 Bulk FHIR Access application programming interface (API).We advance a model for scalable, federated, data sharing and learning. Cumulus software is designed to address key technology and policy desiderata including local utility, control, and administrative simplicity as well as privacy preservation during robust data sharing, and artificial intelligence (AI) for processing unstructured text.Cumulus relies on containerized, cloud-hosted software, installed within a healthcare organization’s security envelope. Cumulus accesses EHR data via the Bulk FHIR interface and streamlines automated processing and sharing. The modular design enables use of the latest AI and natural language processing tools and supports provider autonomy and administrative simplicity. In an initial test, Cumulus was deployed across 5 healthcare systems each partnered with public health. Cumulus output is patient counts which were aggregated into a table stratifying variables of interest to enable population health studies. All code is available open source. A policy stipulating that only aggregate data leave the institution greatly facilitated data sharing agreements.Cumulus addresses barriers to data sharing based on (1) federally required support for standard APIs, (2) increasing use of cloud computing, and (3) advances in AI. There is potential for scalability to support learning across myriad network configurations and use cases.},
	number = {8},
	urldate = {2025-06-26},
	journal = {Journal of the American Medical Informatics Association},
	author = {McMurry, Andrew J and Gottlieb, Daniel I and Miller, Timothy A and Jones, James R and Atreja, Ashish and Crago, Jennifer and Desai, Pankaja M and Dixon, Brian E and Garber, Matthew and Ignatov, Vladimir and Kirchner, Lyndsey A and Payne, Philip R O and Saldanha, Anil J and Shankar, Prabhu R V and Solad, Yauheni V and Sprouse, Elizabeth A and Terry, Michael and Wilcox, Adam B and Mandl, Kenneth D},
	month = aug,
	year = {2024},
	pages = {1638--1647},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/D3T6DUWZ/ocae130.html:text/html},
}

@article{lehvaslaiho2025spe,
	title = {{SPE} and {TRE} terminology for sensitive data processing},
	url = {https://zenodo.org/records/15696511},
	doi = {10.5281/zenodo.15696511},
	abstract = {This white paper summarises the finding of the first version of the EOSC-ENTRUST Architecture Blueprint about terminology used to describe computing environments for sensitive data processing. They are commonly used interchangeably, but in professional context they can have different scope and need to be used correctly.},
	urldate = {2025-06-26},
	author = {Lehväslaiho, Heikki},
	month = jun,
	year = {2025},
	keywords = {ELIXIR, EOSC-ENTRUST, SPE, TRE},
}

@article{antunesanalysis,
	title = {Analysis of {Federated} {Enterprise} {Architecture} {Models}},
	abstract = {Enterprise architecture models support decision-making as they help organizations to understand, communicate and analyse how business processes are performed, the goals they achieve, the information they use, as well as the applications that realize the business, and the supporting technological infrastructure. The integrated analysis of these models is not straightforward because it cross-cuts different domains that are described using heterogeneous concepts. This paper explores the application of ontologies to analyse enterprise architecture models. Ontologies represent knowledge that can be analysed using computational inference. The contributions of this paper are (1) the specification of multiple enterprise architecture models as ontological schemas, (2) the integration of ontological schemas, and (3) the analysis of the integrated models. The solution artefact consists of a federated model specified as a set of ontological schemas described in OWL-DL that integrates multiple enterprise models and assists their analysis using computational inference. The paper demonstrates the application of the federated model to the ArchiMate language as a means to assess the compliance of business requirements in a civil engineering scenario.},
	language = {en},
	author = {Antunes, Goncalo and Barateiro, Jose and Caetano, Artur and Borbinha, Jose},
	file = {PDF:/Users/dkapitan/Zotero/storage/DD27IF3K/Antunes et al. - Analysis of Federated Enterprise Architecture Models.pdf:application/pdf},
}

@misc{sharma2025hubs,
	title = {Hubs and {Spokes} {Learning}: {Efficient} and {Scalable} {Collaborative} {Machine} {Learning}},
	shorttitle = {Hubs and {Spokes} {Learning}},
	url = {http://arxiv.org/abs/2504.20988},
	doi = {10.48550/arXiv.2504.20988},
	abstract = {We introduce the Hubs and Spokes Learning (HSL) framework, a novel paradigm for collaborative machine learning that combines the strengths of Federated Learning (FL) and Decentralized Learning (P2PL). HSL employs a two-tier communication structure that avoids the single point of failure inherent in FL and outperforms the state-of-the-art P2PL framework, Epidemic Learning Local (ELL). At equal communication budgets (total edges), HSL achieves higher performance than ELL, while at significantly lower communication budgets, it can match ELL's performance. For instance, with only 400 edges, HSL reaches the same test accuracy that ELL achieves with 1000 edges for 100 peers (spokes) on CIFAR-10, demonstrating its suitability for resource-constrained systems. HSL also achieves stronger consensus among nodes after mixing, resulting in improved performance with fewer training rounds. We substantiate these claims through rigorous theoretical analyses and extensive experimental results, showcasing HSL's practicality for large-scale collaborative learning.},
	urldate = {2025-06-30},
	publisher = {arXiv},
	author = {Sharma, Atul and Herath, Kavindu and Bagchi, Saurabh and Liu, Chaoyue and Chaterji, Somali},
	month = apr,
	year = {2025},
	note = {arXiv:2504.20988 [cs]},
	keywords = {Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Distributed, Parallel, and Cluster Computing},
	file = {Preprint PDF:/Users/dkapitan/Zotero/storage/UM88KZJ2/Sharma et al. - 2025 - Hubs and Spokes Learning Efficient and Scalable Collaborative Machine Learning.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/BNHYHUAH/2504.html:text/html},
}

@inproceedings{kancharla2023breaking,
	title = {Breaking {Down} {Data} {Silos}: {Data} {Mesh} to {Achieve} {Effective} {Aggregation} in {Data} {Localization}},
	shorttitle = {Breaking {Down} {Data} {Silos}},
	url = {https://ieeexplore.ieee.org/document/10262765},
	doi = {10.1109/IC2E357697.2023.10262765},
	abstract = {Data localization laws are becoming more common, which makes it hard for companies to manage and combine data that is spread out in different parts of the world. This is especially hard because data is scattered and there are limits on how data can be sent across borders. Data Mesh, a new way of thinking about data architecture, offers a solution to this problem by offering a decentralized way of managing data that can make it easier to put together data in a local context. In this paper, we discuss the problems that organizations face when trying to manage data localization with respect to the data regulations in different regions, the problems with traditional approaches to data management, and the benefits of using a data mesh architecture to gather data. We also discuss a region-based unified data mesh architecture that was made with data localization in mind, pointing out its most important parts and benefits. Our proposed unified data mesh abstraction model can help organizations to deal with the problems caused by data localization and use their data assets to make better decisions and get better insights.},
	urldate = {2025-06-30},
	booktitle = {2023 {International} {Conference} on {Computer}, {Electronics} \& {Electrical} {Engineering} \& their {Applications} ({IC2E3})},
	author = {Kancharla, Jaganmohan Reddy and Madhu Kumar, S. D.},
	month = jun,
	year = {2023},
	keywords = {Data models, Regulation, Analytics, Companies, Data Aggregation, Data Architecture, Data localization, Data mesh, Data Silos, Faces, Location awareness, Region oriented},
	pages = {1--5},
	file = {PDF:/Users/dkapitan/Zotero/storage/FJURBEL5/Kancharla and Madhu Kumar - 2023 - Breaking Down Data Silos Data Mesh to Achieve Effective Aggregation in Data Localization.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/GZPT56U5/10262765.html:text/html},
}

@article{schoonderbeek2024ontology,
	title = {Toward an ontology for {EA} modeling and {EA} model quality},
	volume = {23},
	issn = {1619-1374},
	url = {https://doi.org/10.1007/s10270-023-01146-w},
	doi = {10.1007/s10270-023-01146-w},
	abstract = {Models have long since been used, in different shapes and forms, to understand, communicate about, and (re)shape, the world around us; including many different social, economic, biological, chemical, physical, and digital aspects. This is also the case in the context of enterprise architecture (EA), where we see a wide range of models in many different shapes and forms being used as well. Researchers in EA modeling usually introduce their own lexicon, and perspective of what a model actually is, while accepting (often implicitly) the accompanying ontological commitments. Similarly, practitioners of EA modeling implicitly also commit to (different) ontologies, resulting in models that have an uncertain ontological standing. This is because, for the subject domain of enterprise architecture models (as opposed to the content of such models), no single ontology has gained major traction. As a result, studies into aspects of enterprise architecture models, such as “model quality” and “return on modeling effort”, are fragmented, and cannot readily be compared or combined. This paper proposes a comprehensive applied ontology, specifically geared to enterprise architecture modeling. Ontologies represent structured knowledge about a particular subject domain. It allows for study into, and reasoning about, that subject domain. Our ontology is derived from a theory of modeling, while clarifying concepts such as “enterprise architecture model”, and introduces novel concepts such as “model audience” and “model objective”. Furthermore, the relevant interrelations between these different concepts are identified and defined. The resulting ontology for enterprise architecture models is represented in OntoUML, and shown to be consistent with the foundational ontology for modeling, Unified Foundational Ontology.},
	language = {en},
	number = {3},
	urldate = {2025-06-30},
	journal = {Software and Systems Modeling},
	author = {Schoonderbeek, Jan A. H. and Proper, Henderik A.},
	month = jun,
	year = {2024},
	keywords = {Architecture, Ontology, Enterprise architecture, Information Model, Gene ontology, Building Information Modeling, Enterprise Architecture, Domain model, Enterprise architecture model, Enterprise architecture modeling, Model quality, Model Theory},
	pages = {535--558},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/WYKZDA9P/Schoonderbeek and Proper - 2024 - Toward an ontology for EA modeling and EA model quality.pdf:application/pdf},
}

@article{hanser2025datadriven,
	title = {Data-driven federated learning in drug discovery with knowledge distillation},
	volume = {7},
	copyright = {2025 The Author(s), under exclusive licence to Springer Nature Limited},
	issn = {2522-5839},
	url = {https://www.nature.com/articles/s42256-025-00991-2},
	doi = {10.1038/s42256-025-00991-2},
	abstract = {A main challenge for artificial intelligence in scientific research is ensuring access to sufficient, high-quality data for the development of impactful models. Despite the abundance of public data, the most valuable knowledge often remains embedded within confidential corporate data silos. Although industries are increasingly open to sharing non-competitive insights, such collaboration is often constrained by the confidentiality of the underlying data. Federated learning makes it possible to share knowledge without compromising data privacy, but it has notable limitations. Here, we introduce FLuID (federated learning using information distillation), a data-centric application of federated distillation tailored to drug discovery aiming to preserve data privacy. We validate FLuID in two experiments, first involving public data simulating a virtual consortium and second in a real-world research collaboration between eight pharmaceutical companies. Although the alignment of the models with the partner specific domain remains challenging, the data-driven nature of FLuID offers several avenues to mitigate domain shift. FLuID fosters knowledge sharing among pharmaceutical organizations, paving the way for a new generation of models with enhanced performance and an expanded applicability domain in biological activity predictions.},
	language = {en},
	number = {3},
	urldate = {2025-06-30},
	journal = {Nature Machine Intelligence},
	publisher = {Nature Publishing Group},
	author = {Hanser, Thierry and Ahlberg, Ernst and Amberg, Alexander and Anger, Lennart T. and Barber, Chris and Brennan, Richard J. and Brigo, Alessandro and Delaunois, Annie and Glowienke, Susanne and Greene, Nigel and Johnston, Laura and Kuhn, Daniel and Kuhnke, Lara and Marchaland, Jean-François and Muster, Wolfgang and Plante, Jeffrey and Rippmann, Friedrich and Sabnis, Yogesh and Schmidt, Friedemann and van Deursen, Ruud and Werner, Stéphane and White, Angela and Wichard, Joerg and Yukawa, Tomoya},
	month = mar,
	year = {2025},
	keywords = {Chemical tools, Cheminformatics, Computational chemistry, Drug safety},
	pages = {423--436},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/K86DFKMK/Hanser et al. - 2025 - Data-driven federated learning in drug discovery with knowledge distillation.pdf:application/pdf},
}

@article{yang2024federated,
	title = {Federated {Continual} {Learning} via {Knowledge} {Fusion}: {A} {Survey}},
	volume = {36},
	issn = {1558-2191},
	shorttitle = {Federated {Continual} {Learning} via {Knowledge} {Fusion}},
	url = {https://ieeexplore.ieee.org/abstract/document/10423871},
	doi = {10.1109/TKDE.2024.3363240},
	abstract = {Data privacy and silos are nontrivial and greatly challenging in many real-world applications. Federated learning is a decentralized approach to training models across multiple local clients without the exchange of raw data from client devices to global servers. However, existing works focus on a static data environment and ignore continual learning from streaming data with incremental tasks. Federated Continual Learning (FCL) is an emerging paradigm to address model learning in both federated and continual learning environments. The key objective of FCL is to fuse heterogeneous knowledge from different clients and retain knowledge of previous tasks while learning on new ones. In this work, we delineate federated learning and continual learning first and then discuss their integration, i.e., FCL, and particular FCL via knowledge fusion. In summary, our motivations are four-fold: we (1) raise a fundamental problem called “spatial-temporal catastrophic forgetting” and evaluate its impact on the performance using a well-known method called federated averaging (FedAvg), (2) integrate most of the existing FCL methods into two generic frameworks, namely synchronous FCL and asynchronous FCL, (3) categorize a large number of methods according to the mechanism involved in knowledge fusion, and finally (4) showcase an outlook on the future work of FCL.},
	number = {8},
	urldate = {2025-06-30},
	journal = {IEEE Transactions on Knowledge and Data Engineering},
	author = {Yang, Xin and Yu, Hao and Gao, Xin and Wang, Hao and Zhang, Junbo and Li, Tianrui},
	month = aug,
	year = {2024},
	keywords = {Privacy, Data models, Training, Servers, Task analysis, Federated learning, Biological system modeling, federated learning, Continual learning, federated continual learning, knowledge fusion, spatial-temporal catastrophic forgetting},
	pages = {3832--3850},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/EIZJNTXX/Yang et al. - 2024 - Federated Continual Learning via Knowledge Fusion A Survey.pdf:application/pdf},
}

@article{zhao2025federation,
	title = {The {Federation} {Strikes} {Back}: {A} {Survey} of {Federated} {Learning} {Privacy} {Attacks}, {Defenses}, {Applications}, and {Policy} {Landscape}},
	volume = {57},
	issn = {0360-0300},
	shorttitle = {The {Federation} {Strikes} {Back}},
	url = {https://dl.acm.org/doi/10.1145/3724113},
	doi = {10.1145/3724113},
	abstract = {Deep learning has shown incredible potential across a wide array of tasks, and accompanied by this growth has been an insatiable appetite for data. However, a large amount of data needed for enabling deep learning is stored on personal devices, and recent concerns on privacy have further highlighted challenges for accessing such data. As a result, federated learning (FL) has emerged as an important privacy-preserving technology that enables collaborative training of machine learning models without the need to send the raw, potentially sensitive, data to a central server. However, the fundamental premise that sending model updates to a server is privacy-preserving only holds if the updates cannot be “reverse engineered” to infer information about the private training data. It has been shown under a wide variety of settings that this privacy premise does not hold. In this article we provide a comprehensive literature review of the different privacy attacks and defense methods in FL. We identify the current limitations of these attacks and highlight the settings in which the privacy of an FL client can be broken. We further dissect some of the successful industry applications of FL and draw lessons for future successful adoption. We survey the emerging landscape of privacy regulation for FL and conclude with future directions for taking FL toward the cherished goal of generating accurate models while preserving the privacy of the data from its participants.},
	number = {9},
	urldate = {2025-06-30},
	journal = {ACM Comput. Surv.},
	author = {Zhao, Joshua and Bagchi, Saurabh and Avestimehr, Salman and Chan, Kevin and Chaterji, Somali and Dimitriadis, Dimitris and Li, Jiacheng and Li, Ninghui and Nourian, Arash and Roth, Holger},
	month = apr,
	year = {2025},
	pages = {230:1--230:37},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/TIQ2CRMP/Zhao et al. - 2025 - The Federation Strikes Back A Survey of Federated Learning Privacy Attacks, Defenses, Applications,.pdf:application/pdf},
}

@article{yuan2024decentralized,
	title = {Decentralized {Federated} {Learning}: {A} {Survey} and {Perspective}},
	volume = {11},
	issn = {2327-4662},
	shorttitle = {Decentralized {Federated} {Learning}},
	url = {https://ieeexplore.ieee.org/abstract/document/10542323},
	doi = {10.1109/JIOT.2024.3407584},
	abstract = {Federated learning (FL) has been gaining attention for its ability to share knowledge while maintaining user data, protecting privacy, increasing learning efficiency, and reducing communication overhead. Decentralized FL (DFL) is a decentralized network architecture that eliminates the need for a central server in contrast to centralized FL (CFL). DFL enables direct communication between clients, resulting in significant savings in communication resources. In this article, a comprehensive survey and profound perspective are provided for DFL. First, a review of the methodology, challenges, and variants of CFL is conducted, laying the background of DFL. Then, a systematic and detailed perspective on DFL is introduced, including iteration order, communication protocols, network topologies, paradigm proposals, and temporal variability. Next, based on the definition of DFL, several extended variants and categorizations are proposed with state-of-the-art (SOTA) technologies. Lastly, in addition to summarizing the current challenges in the DFL, some possible solutions and future research directions are also discussed.},
	number = {21},
	urldate = {2025-06-30},
	journal = {IEEE Internet of Things Journal},
	author = {Yuan, Liangqi and Wang, Ziran and Sun, Lichao and Yu, Philip S. and Brinton, Christopher G.},
	month = nov,
	year = {2024},
	keywords = {Data models, Protocols, Servers, Internet of Things, Internet of Things (IoT), Surveys, privacy preservation, Adaptation models, Decentralized learning, federated learning (FL), network, Taxonomy},
	pages = {34617--34638},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/C6J59EIZ/Yuan et al. - 2024 - Decentralized Federated Learning A Survey and Perspective.pdf:application/pdf},
}

@misc{interactivea,
	title = {An {Interactive} {Introduction} to {Model}-{Agnostic} {Meta}-{Learning} 👩‍🔬},
	url = {https://interactive-maml.github.io/first-order.html},
	urldate = {2025-06-30},
	file = {An Interactive Introduction to Model-Agnostic Meta-Learning 👩‍🔬:/Users/dkapitan/Zotero/storage/X74R3KCY/first-order.html:text/html},
}

@misc{hall2021syft,
	title = {Syft 0.5: {A} {Platform} for {Universally} {Deployable} {Structured} {Transparency}},
	shorttitle = {Syft 0.5},
	url = {http://arxiv.org/abs/2104.12385},
	doi = {10.48550/arXiv.2104.12385},
	abstract = {We present Syft 0.5, a general-purpose framework that combines a core group of privacy-enhancing technologies that facilitate a universal set of structured transparency systems. This framework is demonstrated through the design and implementation of a novel privacy-preserving inference information flow where we pass homomorphically encrypted activation signals through a split neural network for inference. We show that splitting the model further up the computation chain significantly reduces the computation time of inference and the payload size of activation signals at the cost of model secrecy. We evaluate our proposed flow with respect to its provision of the core structural transparency principles.},
	urldate = {2025-06-30},
	publisher = {arXiv},
	author = {Hall, Adam James and Jay, Madhava and Cebere, Tudor and Cebere, Bogdan and Veen, Koen Lennart van der and Muraru, George and Xu, Tongye and Cason, Patrick and Abramson, William and Benaissa, Ayoub and Shah, Chinmay and Aboudib, Alan and Ryffel, Théo and Prakash, Kritika and Titcombe, Tom and Khare, Varun Kumar and Shang, Maddie and Junior, Ionesio and Gupta, Animesh and Paumier, Jason and Kang, Nahua and Manannikov, Vova and Trask, Andrew},
	month = apr,
	year = {2021},
	note = {arXiv:2104.12385 [cs]},
	keywords = {Computer Science - Machine Learning, Computer Science - Cryptography and Security},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/X86GMIQD/Hall et al. - 2021 - Syft 0.5 A Platform for Universally Deployable Structured Transparency.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/L4BLDQ3V/2104.html:text/html},
}

@misc{odrl,
	title = {{ODRL} {Information} {Model} 2.2},
	url = {https://www.w3.org/TR/odrl-model/},
	urldate = {2025-06-30},
	file = {ODRL Information Model 2.2:/Users/dkapitan/Zotero/storage/TN69EZEM/odrl-model.html:text/html},
}

@article{milosevic2016open,
	title = {An open architecture for event-based analytics},
	volume = {2},
	issn = {2364-4168},
	url = {https://doi.org/10.1007/s41060-016-0029-7},
	doi = {10.1007/s41060-016-0029-7},
	abstract = {Event-based analytics is increasingly gaining prominence in business and social applications. Despite the availability of many solutions specializing in event processing systems (e.g. CEP technology), there is currently no commonly agreed way of describing event and event pattern types, and thus no standardized method for interchange of event pattern instances between systems. This paper advocates an open architecture for event-based analytics comprising a common model that supports interoperability of data between different systems. It introduces the foundational concepts for describing event patterns including events, event pattern types and event pattern occurrences. The event pattern meta-model is also formalized using a UML meta-model to facilitate its adoption and usage across the event analytics community. The paper provides a case study introducing several event pattern types from the financial market data analytics domain. This case study illustrates a number of specific event pattern types used by finance experts and an application that requires interoperability between two separate software component frameworks (a rule-based front-end and a CEP). Results show that the meta-model concepts are sufficient to represent and implement a class of real-life business analytics solutions. The paper also identified a number of semantic challenges in developing interoperability solutions for the event-based processing, in spite of the fact that we needed to merge only two separately developed event-based conceptual models.},
	language = {en},
	number = {1},
	urldate = {2025-06-30},
	journal = {International Journal of Data Science and Analytics},
	author = {Milosevic, Zoran and Chen, Weisi and Berry, Andrew and Rabhi, Fethi A.},
	month = dec,
	year = {2016},
	keywords = {Information Model, Building Information Modeling, Enterprise Architecture, ADAGE, Business Analytics, Complex event processing, Data Analytics, Data modelling, Event-based analytics, Real-time analytics, Service-oriented architecture, Sport Analytics},
	pages = {13--27},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/VMWDXMYN/Milosevic et al. - 2016 - An open architecture for event-based analytics.pdf:application/pdf},
}

@article{bhanbhro2024issues,
	title = {Issues in federated learning: some experiments and preliminary results},
	volume = {14},
	copyright = {2024 The Author(s)},
	issn = {2045-2322},
	shorttitle = {Issues in federated learning},
	url = {https://www.nature.com/articles/s41598-024-81732-0},
	doi = {10.1038/s41598-024-81732-0},
	abstract = {The growing need for data privacy and security in machine learning has led to exploring novel approaches like federated learning (FL) that allow collaborative training on distributed datasets, offering a decentralized alternative to traditional data collection methods. A prime benefit of FL is its emphasis on privacy, enabling data to stay on local devices by moving models instead of data. Despite its pioneering nature, FL faces issues such as diversity in data types, model complexity, privacy concerns, and the need for efficient resource distribution. This paper illustrates an empirical analysis of these challenges within specially designed scenarios, each aimed at studying a specific problem. In particular, differently from existing literature, we isolate the issues that can arise in an FL framework to observe their nature without the interference of external factors.},
	language = {en},
	number = {1},
	urldate = {2025-06-30},
	journal = {Scientific Reports},
	publisher = {Nature Publishing Group},
	author = {Bhanbhro, Jamsher and Nisticò, Simona and Palopoli, Luigi},
	month = dec,
	year = {2024},
	keywords = {Engineering, Mathematics and computing},
	pages = {29881},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/KP9MAB5G/Bhanbhro et al. - 2024 - Issues in federated learning some experiments and preliminary results.pdf:application/pdf},
}

@article{saeed2025comprehensive,
	title = {Comprehensive review of federated learning challenges: a data preparation viewpoint},
	volume = {12},
	issn = {2196-1115},
	shorttitle = {Comprehensive review of federated learning challenges},
	url = {https://doi.org/10.1186/s40537-025-01195-6},
	doi = {10.1186/s40537-025-01195-6},
	abstract = {Machine learning model accuracy, generalization, and reliability are greatly affected by the training data quality. High-quality data-characterized by completeness, consistency, accuracy, representativeness and homogeneity enables meaningful pattern learning and robust prediction. In federated learning (FL), the learning process is collaborative and conducted across decentralized and locally private data nodes. The heterogeneity of data across these nodes degrade model performance and may lead to overfitting, underfitting, and erroneous decision-making. Heterogeneity is caused by inconsistent labeling, missing values, and class imbalances across these nodes. Proper data preparation, including cleaning, normalization, and augmentation, is essential to mitigate these issues and ensure that these distributed datasets reflect the problem domain accurately. The raw data, which is generated from diverse sources with the fundamental constraint that this data cannot be shared among learning nodes exacerbates these challenges. Although data preparation has received great interest in recent years; little attention has been given to data challenges posed when FL is used. Although some surveys mention FL challenges, it is discussed superficially. These papers predominantly focus on one aspect of data challenges such as quality, homogeneity or balance discussing FL within the context of these specific challenges. No recent survey examine all data-related challenges in FL, including their interdependencies and interactions. To address these limitations, the main contribution of this paper is providing a comprehensive overview of data challenges in FL, encompassing data heterogeneity, skewness, representation, quality, bias, and fairness. The paper begins by identifying the data challenges highlighted in the existing literature, with a particular focus on the interrelationships among these challenges, which are categorized into two main groups: non-independently and non-identically distributed (Non-IID) data issues and data quality issues. Subsequently, the paper reviews and compares recognized data challenges solution approaches exploring additional data preparation techniques that could serve as candidate solutions. The paper aims to define the necessary work to optimize the effectiveness of these techniques with respect to distributed and isolated data in FL.},
	number = {1},
	urldate = {2025-06-30},
	journal = {Journal of Big Data},
	author = {Saeed, Nawraz and Ashour, Mohamed and Mashaly, Maggie},
	month = jun,
	year = {2025},
	keywords = {Federated learning, Data preparation, Distributed data, Heterogeneity},
	pages = {153},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/STZIXEQ7/Saeed et al. - 2025 - Comprehensive review of federated learning challenges a data preparation viewpoint.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/JZ6WTCR8/s40537-025-01195-6.html:text/html},
}

@misc{trask2024privacy,
	title = {Beyond {Privacy} {Trade}-offs with {Structured} {Transparency}},
	url = {http://arxiv.org/abs/2012.08347},
	doi = {10.48550/arXiv.2012.08347},
	abstract = {Successful collaboration involves sharing information. However, parties may disagree on how the information they need to share should be used. We argue that many of these concerns reduce to 'the copy problem': once a bit of information is copied and shared, the sender can no longer control how the recipient uses it. From the perspective of each collaborator, this presents a dilemma that can inhibit collaboration. The copy problem is often amplified by three related problems which we term the bundling, edit, and recursive enforcement problems. We find that while the copy problem is not solvable, aspects of these amplifying problems have been addressed in a variety of disconnected fields. We observe that combining these efforts could improve the governability of information flows and thereby incentivise collaboration. We propose a five-part framework which groups these efforts into specific capabilities and offers a foundation for their integration into an overarching vision we call "structured transparency". We conclude by surveying an array of use-cases that illustrate the structured transparency principles and their related capabilities.},
	urldate = {2025-06-30},
	publisher = {arXiv},
	author = {Trask, Andrew and Bluemke, Emma and Collins, Teddy and Drexler, Ben Garfinkel Eric and Cuervas-Mons, Claudia Ghezzou and Gabriel, Iason and Dafoe, Allan and Isaac, William},
	month = mar,
	year = {2024},
	note = {arXiv:2012.08347 [cs]},
	keywords = {Computer Science - Cryptography and Security, Computer Science - Computers and Society},
	file = {Preprint PDF:/Users/dkapitan/Zotero/storage/S4XKFKJZ/Trask et al. - 2024 - Beyond Privacy Trade-offs with Structured Transparency.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/6V6FE5H5/2012.html:text/html},
}

@misc{padme,
	title = {{PADME} {\textbar} {Platform} for {Analytics} and {Distributed} {Machine} {Learning} for {Enterprises}},
	url = {https://padme-analytics.de/},
	urldate = {2025-06-30},
	file = {PADME | Platform for Analytics and Distributed Machine Learning for Enterprises:/Users/dkapitan/Zotero/storage/YSIUR7E7/padme-analytics.de.html:text/html},
}

@article{brohet2025using,
	title = {Using {Real}-{World} {Data} for {Machine}-{Learning} {Algorithms} to {Predict} the {Treatment} {Response} in {Advanced} {Melanoma}: {A} {Pilot} {Study} for {Personalizing} {Cancer} {Care}},
	shorttitle = {Using {Real}-{World} {Data} for {Machine}-{Learning} {Algorithms} to {Predict} the {Treatment} {Response} in {Advanced} {Melanoma}},
	url = {https://ascopubs.org/doi/10.1200/CCI-24-00181},
	doi = {10.1200/CCI-24-00181},
	abstract = {PurposeThe use of real-world data (RWD) in oncology is becoming increasingly important for clinical decision making and tailoring treatment. Despite the significant success of targeted therapy and immunotherapy in advanced melanoma, substantial variability in clinical responses to these treatments emphasizes the need for personalized approaches to therapy.Materials and MethodsIn this pilot study, 239 patients with melanoma were included to predict the response to both targeted therapies and immunotherapies. We used machine learning (ML) to incorporate RWD and applied explainable artificial intelligence (XAI) to explain the individual predictions.ResultsWe developed, validated, and compared four ML models to evaluate 2-year survival using RWD. Our research showed encouraging outcomes, achieving an AUC of more than 80\% and an estimated accuracy of over 74\% across the four ML models. The random forest model exhibited the highest performance in predicting 2-year survival with an AUC of 0.85. Local interpretable model-agnostic explanations was used to explain individual predictions and provide trust and insights into the clinical implications of the ML model.ConclusionWith this proof-of-concept, we integrated RWD into predictive modeling using ML techniques to predict clinical outcomes and explore their potential implications for clinical decision making. The potential of XAI was demonstrated to enhance trust and improve the usability of the model in clinical settings. Further research, including foundation modeling and generative AI, will likely increase the predictive power of prognostic and predictive ML models in advanced melanoma.},
	number = {9},
	urldate = {2025-06-30},
	journal = {JCO Clinical Cancer Informatics},
	publisher = {Wolters Kluwer},
	author = {Brohet, Richard M. and de Boer, Elianne C.S. and Mossink, Joram M. and van der Eerden, Joni J.N. and Oostmeyer, Alexander and Idzerda, Luuk H.W. and Maring, Jan Gerard and Paardekooper, Gabriel M.R.M. and Beld, Michel and Lijffijt, Fiona and Dille, Joep and de Groot, Jan Willem B.},
	month = apr,
	year = {2025},
	pages = {e2400181},
}

@article{quiroz2022extract,
	title = {Extract, transform, load framework for the conversion of health databases to {OMOP}},
	volume = {17},
	issn = {1932-6203},
	url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9000122/},
	doi = {10.1371/journal.pone.0266911},
	abstract = {Common data models standardize the structures and semantics of health datasets, enabling reproducibility and large-scale studies that leverage the data from multiple locations and settings. The Observational Medical Outcomes Partnership Common Data Model (OMOP CDM) is one of the leading common data models. While there is a strong incentive to convert datasets to OMOP, the conversion is time and resource-intensive, leaving the research community in need of tools for mapping data to OMOP. We propose an extract, transform, load (ETL) framework that is metadata-driven and generic across source datasets. The ETL framework uses a new data manipulation language (DML) that organizes SQL snippets in YAML. Our framework includes a compiler that converts YAML files with mapping logic into an ETL script. Access to the ETL framework is available via a web application, allowing users to upload and edit YAML files via web editor and obtain an ETL SQL script for use in development environments. The structure of the DML maximizes readability, refactoring, and maintainability, while minimizing technical debt and standardizing the writing of ETL operations for mapping to OMOP. Our framework also supports transparency of the mapping process and reuse by different institutions.},
	number = {4},
	urldate = {2025-07-01},
	journal = {PLoS ONE},
	author = {Quiroz, Juan C. and Chard, Tim and Sa, Zhisheng and Ritchie, Angus and Jorm, Louisa and Gallego, Blanca},
	month = apr,
	year = {2022},
	pages = {e0266911},
	file = {Full Text:/Users/dkapitan/Zotero/storage/HSIZSSFR/Quiroz et al. - 2022 - Extract, transform, load framework for the conversion of health databases to OMOP.pdf:application/pdf},
}

@misc{eapen2025dermatologist,
	title = {dermatologist/pyomop},
	copyright = {GPL-3.0},
	url = {https://github.com/dermatologist/pyomop},
	abstract = {Python package for managing OHDSI clinical data models. Includes support for LLM based plain text queries!},
	urldate = {2025-07-01},
	author = {Eapen, Bell},
	month = jul,
	year = {2025},
	note = {original-date: 2020-05-02T16:09:27Z},
	keywords = {python, cdm, clinical-trials, datawarehouse, hacktoberfest, health-data-analysis, health-informatics, llm, ohdsi, text-to-sql},
}

@article{finster2025etl,
	title = {{ETL}: {From} the {German} {Health} {Data} {Lab} data formats to the {OMOP} {Common} {Data} {Model}},
	volume = {20},
	issn = {1932-6203},
	shorttitle = {{ETL}},
	url = {https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0311511},
	doi = {10.1371/journal.pone.0311511},
	abstract = {Objective The German Health Data Lab is going to provide access to German statutory health insurance claims data ranging from 2009 to the present for research purposes. Due to evolving data formats within the German Health Data Lab, there is a need to standardize this data into a Common Data Model to facilitate collaborative health research and minimize the need for researchers to adapt to multiple data formats. For this purpose we selected transforming the data to the Observational Medical Outcomes Partnership Common Data Model. Methods We developed an Extract, Transform, and Load (ETL) pipeline for two distinct German Health Data Lab data formats: Format 1 (2009-2016) and Format 3 (2019 onwards). Due to the identical format structure of Format 1 and Format 2 (2017 -2018), the ETL pipeline of Format 1 can be applied on Format 2 as well. Our ETL process, supported by Observational Health Data Sciences and Informatics tools, includes specification development, SQL skeleton creation, and concept mapping. We detail the process characteristics and present a quality assessment that includes field coverage and concept mapping accuracy using example data. Results For Format 1, we achieved a field coverage of 92.7\%. The Data Quality Dashboard showed 100.0\% conformance and 80.6\% completeness, although plausibility checks were disabled. The mapping coverage for the Condition domain was low at 18.3\% due to invalid codes and missing mappings in the provided example data. For Format 3, the field coverage was 86.2\%, with Data Quality Dashboard reporting 99.3\% conformance and 75.9\% completeness. The Procedure domain had very low mapping coverage (2.2\%) due to the use of mocked data and unmapped local concepts The Condition domain results with 99.8\% of unique codes mapped. The absence of real data limits the comprehensive assessment of quality. Conclusion The ETL process effectively transforms the data with high field coverage and conformance. It simplifies data utilization for German Health Data Lab users and enhances the use of OHDSI analysis tools. This initiative represents a significant step towards facilitating cross-border research in Europe by providing publicly available, standardized ETL processes (https://github.com/FraunhoferMEVIS/ETLfromHDLtoOMOP) and evaluations of their performance.},
	language = {en},
	number = {1},
	urldate = {2025-07-01},
	journal = {PLOS ONE},
	publisher = {Public Library of Science},
	author = {Finster, Melissa and Moinat, Maxim and Taghizadeh, Elham},
	month = jan,
	year = {2025},
	keywords = {Inpatients, Physicians, Source code, Health insurance, Health informatics, Outpatients, Blood, Rabbits},
	pages = {e0311511},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/8MMWDKEX/Finster et al. - 2025 - ETL From the German Health Data Lab data formats to the OMOP Common Data Model.pdf:application/pdf},
}

@article{biedermann2021standardizing,
	title = {Standardizing registry data to the {OMOP} {Common} {Data} {Model}: experience from three pulmonary hypertension databases},
	volume = {21},
	issn = {1471-2288},
	shorttitle = {Standardizing registry data to the {OMOP} {Common} {Data} {Model}},
	url = {https://doi.org/10.1186/s12874-021-01434-3},
	doi = {10.1186/s12874-021-01434-3},
	abstract = {The Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) can be used to transform observational health data to a common format. CDM transformation allows for analysis across disparate databases for the generation of new, real-word evidence, which is especially important in rare disease where data are limited. Pulmonary hypertension (PH) is a progressive, life-threatening disease, with rare subgroups such as pulmonary arterial hypertension (PAH), for which generating real-world evidence is challenging. Our objective is to document the process and outcomes of transforming registry data in PH to the OMOP CDM, and highlight challenges and our potential solutions.},
	number = {1},
	urldate = {2025-07-02},
	journal = {BMC Medical Research Methodology},
	author = {Biedermann, Patricia and Ong, Rose and Davydov, Alexander and Orlova, Alexandra and Solovyev, Philip and Sun, Hong and Wetherill, Graham and Brand, Monika and Didden, Eva-Maria},
	month = nov,
	year = {2021},
	keywords = {Data mapping, Common data model, Observational data, Pulmonary hypertension, Registry},
	pages = {238},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/LM2QW6PZ/Biedermann et al. - 2021 - Standardizing registry data to the OMOP Common Data Model experience from three pulmonary hypertens.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/VTT8UXEW/s12874-021-01434-3.html:text/html},
}

@misc{2025mappingcommons,
	title = {mapping-commons/semantic-mapping-vocabulary},
	url = {https://github.com/mapping-commons/semantic-mapping-vocabulary},
	abstract = {https://mapping-commons.github.io/semantic-mapping-vocabulary/},
	urldate = {2025-07-02},
	publisher = {Mapping Commons},
	month = jul,
	year = {2025},
	note = {original-date: 2022-04-14T08:42:55Z},
}

@incollection{vanderwerf2025data,
	address = {Cham},
	title = {Towards a {Data} {Mesh} {Reference} {Architecture}},
	volume = {537},
	isbn = {978-3-031-79058-4 978-3-031-79059-1},
	url = {https://link.springer.com/10.1007/978-3-031-79059-1_21},
	doi = {10.1007/978-3-031-79059-1_21},
	abstract = {The increasing complexity and volume of organizational data have led to the emergence of the Data Mesh paradigm, a data architecture with a federated governance aimed at addressing the limitations of traditional monolithic data systems that has overlapping principles with the microservices architectural style. Although related work exists, the majority of architectural approaches regarding Data Mesh are conceptual, technology-centric or vendor specific. This paper introduces a Data Mesh Reference Architecture (RA) using the ArchiMate enterprise architecture modeling language, designed to assist organizations in implementing (or migrating towards) data mesh solutions. The RA comprises three main components: domain architecture, self-serve data platform architecture, and federated governance, which reflect the main Data Mesh principles. Through a systematic literature review, four data mesh archetypes (Pure, Semi-Pure, Hybrid, and Distributed) were identified, along with challenges, limitations, and motivational factors for adoption. A questionnaire-based validation among experts confirmed the RA’s utility, quality, and variability. However, practical validation was not conducted within this study. The study contributes to both literature and practice by offering a structured approach and a set of reference models for designing data mesh architectures. Future research can contribute to practical validation, assessment of RA-driven design efficiency, and extending the RA with domain-driven solution architectures.},
	language = {en},
	urldate = {2025-07-02},
	booktitle = {Enterprise {Design}, {Operations}, and {Computing}. {EDOC} 2024 {Workshops}},
	publisher = {Springer Nature Switzerland},
	author = {Van Der Werf, Daniel and Moreira, João and Piest, Jean Paul Sebastian},
	editor = {Kaczmarek-Heß, Monika and Rosenthal, Kristina and Suchánek, Marek and Da Silva, Miguel Mira and Proper, Henderik A. and Schnellmann, Marianne},
	year = {2025},
	note = {Series Title: Lecture Notes in Business Information Processing},
	pages = {339--353},
	file = {PDF:/Users/dkapitan/Zotero/storage/GRIM4ZZS/Van Der Werf et al. - 2025 - Towards a Data Mesh Reference Architecture.pdf:application/pdf},
}

@article{ayeelyan2024federated,
	title = {Federated learning design and functional models: survey},
	volume = {58},
	issn = {1573-7462},
	shorttitle = {Federated learning design and functional models},
	url = {https://link.springer.com/10.1007/s10462-024-10969-y},
	doi = {10.1007/s10462-024-10969-y},
	abstract = {Federated learning is a multiple device collaboration setup designed to solve machine learning problems under framework for aggregation and knowledge transfer in distributed local data. This distributed model ensures the privacy of data at each local node. Owing to its relevance, there has been extensive research activities and outcomes in federated learning with expanded applicability to different areas by the research community. As such, there is a vast research archive made available by the community with research work and articles related to the various aspects of federated learning such as applications, challenges, privacy, functionalities, and design. With respect to the function and design of federated learning, client selection, aggregation, knowledge transfer, management of distributed data (Non-IID), Incentive of data and communication cost are of paramount importance. Any effective design of federated learning requires these aspects to be well considered. There are numerous survey articles found among the available literature that focus on its application and challenges, opportunities, data privacy and protection, as well as on federated learning on internet of things, federated learning on edge computing, etc. In this paper, a review of the available literature on the various elements of design and functionalities in federated learning has been carried out with an aim to lay emphasis on the important challenges and research opportunities. More specifically, this work has endeavored to understand and summarize the various functional methods available, along with their techniques and goals. Additionally, it has strived to get a bird’s eye view of how various functions and designs of federated learning have been used in applications, and how it has helped uncover challenges and promising research directions for the future.},
	language = {en},
	number = {1},
	urldate = {2025-07-05},
	journal = {Artificial Intelligence Review},
	author = {Ayeelyan, John and Utomo, Sapdo and Rouniyar, Adarsh and Hsu, Hsiu-Chun and Hsiung, Pao-Ann},
	month = nov,
	year = {2024},
	pages = {21},
	file = {PDF:/Users/dkapitan/Zotero/storage/ZI3737Y9/Ayeelyan et al. - 2024 - Federated learning design and functional models survey.pdf:application/pdf},
}

@article{ratnayake2023review,
	title = {A review of federated learning: taxonomy, privacy and future directions},
	volume = {61},
	issn = {0925-9902, 1573-7675},
	shorttitle = {A review of federated learning},
	url = {https://link.springer.com/10.1007/s10844-023-00797-x},
	doi = {10.1007/s10844-023-00797-x},
	abstract = {The data generated and stored in mobile devices owned by individuals as well as in various organizations contains a large amount of valuable and important information that can be used to improve service quality, user experience, and satisfaction. However, due to privacy concerns, many entities are reluctant to share their data with others, and this is a major barrier to developing comprehensive models that can provide accurate predictions. Federated learning is a state-of-the-art distributed machine learning approach where multiple clients are allowed to collaboratively train a model while keeping their private training data locally. Although federated learning seems to be a viable solution for jointly training a machine learning model without compromising privacy, sensitive privacy information may still be leaked through shared model parameters and query results. Over the past six years, the researchers have extensively studied privacy protection enhancements of federated learning, and they have revealed that general privacy protection mechanisms can be adopted to mitigate privacy issues of federated learning. However, protecting privacy through federated learning while maintaining data utility is still an open issue. This article provides an overview of federated learning while discussing privacy leakages, possible defense mechanisms, and future research directions of privacy-preserved federated learning.},
	language = {en},
	number = {3},
	urldate = {2025-07-05},
	journal = {Journal of Intelligent Information Systems},
	author = {Ratnayake, Hashan and Chen, Lin and Ding, Xiaofeng},
	month = dec,
	year = {2023},
	pages = {923--949},
	file = {PDF:/Users/dkapitan/Zotero/storage/4XZZJ7C8/Ratnayake et al. - 2023 - A review of federated learning taxonomy, privacy and future directions.pdf:application/pdf},
}

@book{ludwig2022federated,
	address = {Cham},
	title = {Federated {Learning}: {A} {Comprehensive} {Overview} of {Methods} and {Applications}},
	copyright = {https://www.springer.com/tdm},
	isbn = {978-3-030-96895-3 978-3-030-96896-0},
	shorttitle = {Federated {Learning}},
	url = {https://link.springer.com/10.1007/978-3-030-96896-0},
	doi = {10.1007/978-3-030-96896-0},
	language = {en},
	urldate = {2025-07-05},
	publisher = {Springer International Publishing},
	editor = {Ludwig, Heiko and Baracaldo, Nathalie},
	year = {2022},
	file = {PDF:/Users/dkapitan/Zotero/storage/CDJ4YTAP/Ludwig and Baracaldo - 2022 - Federated Learning A Comprehensive Overview of Methods and Applications.pdf:application/pdf},
}

@article{fu2023client,
	title = {Client {Selection} in {Federated} {Learning}: {Principles}, {Challenges}, and {Opportunities}},
	volume = {10},
	copyright = {https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html},
	issn = {2327-4662, 2372-2541},
	shorttitle = {Client {Selection} in {Federated} {Learning}},
	url = {https://ieeexplore.ieee.org/document/10197174/},
	doi = {10.1109/JIOT.2023.3299573},
	abstract = {As a privacy-preserving paradigm for training machine learning (ML) models, federated learning (FL) has received tremendous attention from both industry and academia. In a typical FL scenario, clients exhibit significant heterogeneity in terms of data distribution and hardware configurations. Thus, randomly sampling clients in each training round may not fully exploit the local updates from heterogeneous clients, resulting in lower model accuracy, slower convergence rate, degraded fairness, etc. To tackle the FL client heterogeneity problem, various client selection algorithms have been developed, showing promising performance improvement. In this article, we systematically present recent advances in the emerging field of FL client selection and its challenges and research opportunities. We hope to facilitate practitioners in choosing the most suitable client selection mechanisms for their applications, as well as inspire researchers and newcomers to better understand this exciting research topic.},
	language = {en},
	number = {24},
	urldate = {2025-07-05},
	journal = {IEEE Internet of Things Journal},
	author = {Fu, Lei and Zhang, Huanle and Gao, Ge and Zhang, Mi and Liu, Xin},
	month = dec,
	year = {2023},
	pages = {21811--21819},
	file = {PDF:/Users/dkapitan/Zotero/storage/6CNN3GFJ/Fu et al. - 2023 - Client Selection in Federated Learning Principles, Challenges, and Opportunities.pdf:application/pdf},
}

@article{papadopoulos2024recent,
	title = {Recent {Advancements} in {Federated} {Learning}: {State} of the {Art}, {Fundamentals}, {Principles}, {IoT} {Applications} and {Future} {Trends}},
	volume = {16},
	copyright = {https://creativecommons.org/licenses/by/4.0/},
	issn = {1999-5903},
	shorttitle = {Recent {Advancements} in {Federated} {Learning}},
	url = {https://www.mdpi.com/1999-5903/16/11/415},
	doi = {10.3390/fi16110415},
	abstract = {Federated learning (FL) is creating a paradigm shift in machine learning by directing the focus of model training to where the data actually exist. Instead of drawing all data into a central location, which raises concerns about privacy, costs, and delays, FL allows learning to take place directly on the device, keeping the data safe and minimizing the need for transfer. This approach is especially important in areas like healthcare, where protecting patient privacy is critical, and in industrial IoT settings, where moving large numbers of data is not practical. What makes FL even more compelling is its ability to reduce the bias that can occur when all data are centralized, leading to fairer and more inclusive machine learning outcomes. However, it is not without its challenges—particularly with regard to keeping the models secure from attacks. Nonetheless, the potential benefits are clear: FL can lower the costs associated with data storage and processing, while also helping organizations to meet strict privacy regulations like GDPR. As edge computing continues to grow, FL’s decentralized approach could play a key role in shaping how we handle data in the future, moving toward a more privacy-conscious world. This study identifies ongoing challenges in ensuring model security against adversarial attacks, pointing to the need for further research in this area.},
	language = {en},
	number = {11},
	urldate = {2025-07-05},
	journal = {Future Internet},
	author = {Papadopoulos, Christos and Kollias, Konstantinos-Filippos and Fragulis, George F.},
	month = nov,
	year = {2024},
	pages = {415},
	file = {PDF:/Users/dkapitan/Zotero/storage/HM6BG5JM/Papadopoulos et al. - 2024 - Recent Advancements in Federated Learning State of the Art, Fundamentals, Principles, IoT Applicati.pdf:application/pdf},
}

@misc{srinivas2025papaya,
	title = {{PAPAYA} {Federated} {Analytics} {Stack}: {Engineering} {Privacy}, {Scalability} and {Practicality}},
	shorttitle = {{PAPAYA} {Federated} {Analytics} {Stack}},
	url = {http://arxiv.org/abs/2412.02340},
	doi = {10.48550/arXiv.2412.02340},
	abstract = {Cross-device Federated Analytics (FA) is a distributed computation paradigm designed to answer analytics queries about and derive insights from data held locally on users' devices. On-device computations combined with other privacy and security measures ensure that only minimal data is transmitted off-device, achieving a high standard of data protection. Despite FA's broad relevance, the applicability of existing FA systems is limited by compromised accuracy; lack of flexibility for data analytics; and an inability to scale effectively. In this paper, we describe our approach to combine privacy, scalability, and practicality to build and deploy a system that overcomes these limitations. Our FA system leverages trusted execution environments (TEEs) and optimizes the use of on-device computing resources to facilitate federated data processing across large fleets of devices, while ensuring robust, defensible, and verifiable privacy safeguards. We focus on federated analytics (statistics and monitoring), in contrast to systems for federated learning (ML workloads), and we flag the key differences.},
	urldate = {2025-07-05},
	publisher = {arXiv},
	author = {Srinivas, Harish and Cormode, Graham and Honarkhah, Mehrdad and Lurye, Samuel and Hehir, Jonathan and He, Lunwen and Hong, George and Magdy, Ahmed and Huba, Dzmitry and Wang, Kaikai and Guo, Shen and Bhattacharya, Shoubhik},
	month = mar,
	year = {2025},
	note = {arXiv:2412.02340 [cs]},
	keywords = {Computer Science - Machine Learning},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/4G7VPITU/Srinivas et al. - 2025 - PAPAYA Federated Analytics Stack Engineering Privacy, Scalability and Practicality.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/ZYRR9R6S/2412.html:text/html},
}

@misc{federated,
	title = {Federated {Analytics}: {Collaborative} {Data} {Science} without {Data} {Collection}},
	shorttitle = {Federated {Analytics}},
	url = {https://research.google/blog/federated-analytics-collaborative-data-science-without-data-collection/},
	abstract = {Posted by Daniel Ramage, Research Scientist and Stefano Mazzocchi, Software Engineer, Google Research   Federated learning, introduced in 2017, ena...},
	language = {en},
	urldate = {2025-07-05},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/8DYEVVDC/federated-analytics-collaborative-data-science-without-data-collection.html:text/html},
}

@misc{togaf,
	title = {The {TOGAF}® {Standard}, {Version} 9.2},
	url = {https://pubs.opengroup.org/architecture/togaf9-doc/arch/index.html},
	urldate = {2025-07-07},
	file = {The TOGAF® Standard, Version 9.2:/Users/dkapitan/Zotero/storage/PHABB93X/index.html:text/html},
}

@article{kohler2023eosb,
	title = {Eos and {OMOCL}: {Towards} a seamless integration of {openEHR} records into the {OMOP} {Common} {Data} {Model}},
	volume = {144},
	issn = {1532-0480},
	shorttitle = {Eos and {OMOCL}},
	doi = {10.1016/j.jbi.2023.104437},
	abstract = {BACKGROUND: The reuse of data from electronic health records (EHRs) for research purposes promises to improve the data foundation for clinical trials and may even support to enable them. Nevertheless, EHRs are characterized by both, heterogeneous structure and semantics. To standardize this data for research, the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) standard has recently seen an increase in use. However, the conversion of these EHRs into the OMOP CDM requires complex and resource intensive Extract Transform and Load (ETL) processes. This hampers the reuse of clinical data for research. To solve the issues of heterogeneity of EHRs and the lack of semantic precision on the care site, the openEHR standard has recently seen wider adoption. A standardized process to integrate openEHR records into the CDM potentially lowers the barriers of making EHRs accessible for research. Yet, a comprehensive approach about the integration of openEHR records into the OMOP CDM has not yet been made.
METHODS: We analyzed both standards and compared their models to identify possible mappings. Based on this, we defined the necessary processes to transform openEHR records into CDM tables. We also discuss the limitation of openEHR with its unspecific demographics model and propose two possible solutions.
RESULTS: We developed the OMOP Conversion Language (OMOCL) which enabled us to define a declarative openEHR archetype-to-CDM mapping language. Using OMOCL, it was possible to define a set of mappings. As a proof-of-concept, we implemented the Eos tool, which uses the OMOCL-files to successfully automatize the ETL from real-world and sample EHRs into the OMOP CDM.
DISCUSSION: Both Eos and OMOCL provide a way to define generic mappings for an integration of openEHR records into OMOP. Thus, it represents a significant step towards achieving interoperability between the clinical and the research data domains. However, the transformation of openEHR data into the less expressive OMOP CDM leads to a loss of semantics.},
	language = {eng},
	journal = {Journal of Biomedical Informatics},
	author = {Kohler, Severin and Boscá, Diego and Kärcher, Florian and Haarbrandt, Birger and Prinz, Manuel and Marschollek, Michael and Eils, Roland},
	month = aug,
	year = {2023},
	keywords = {Semantics, Electronic Health Records, Reference Standards, Databases, Factual, EHR, Secondary use, ETL, OMOP, OHDSI, OpenEHR},
	pages = {104437},
}

@article{henke2024conceptual,
	title = {Conceptual design of a generic data harmonization process for {OMOP} common data model},
	volume = {24},
	issn = {1472-6947},
	doi = {10.1186/s12911-024-02458-7},
	abstract = {BACKGROUND: To gain insight into the real-life care of patients in the healthcare system, data from hospital information systems and insurance systems are required. Consequently, linking clinical data with claims data is necessary. To ensure their syntactic and semantic interoperability, the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) from the Observational Health Data Sciences and Informatics (OHDSI) community was chosen. However, there is no detailed guide that would allow researchers to follow a generic process for data harmonization, i.e. the transformation of local source data into the standardized OMOP CDM format. Thus, the aim of this paper is to conceptualize a generic data harmonization process for OMOP CDM.
METHODS: For this purpose, we conducted a literature review focusing on publications that address the harmonization of clinical or claims data in OMOP CDM. Subsequently, the process steps used and their chronological order as well as applied OHDSI tools were extracted for each included publication. The results were then compared to derive a generic sequence of the process steps.
RESULTS: From 23 publications included, a generic data harmonization process for OMOP CDM was conceptualized, consisting of nine process steps: dataset specification, data profiling, vocabulary identification, coverage analysis of vocabularies, semantic mapping, structural mapping, extract-transform-load-process, qualitative and quantitative data quality analysis. Furthermore, we identified seven OHDSI tools which supported five of the process steps.
CONCLUSIONS: The generic data harmonization process can be used as a step-by-step guide to assist other researchers in harmonizing source data in OMOP CDM.},
	language = {eng},
	number = {1},
	journal = {BMC medical informatics and decision making},
	author = {Henke, Elisa and Zoch, Michele and Peng, Yuan and Reinecke, Ines and Sedlmayr, Martin and Bathelt, Franziska},
	month = feb,
	year = {2024},
	keywords = {Humans, Interoperability, Medical Informatics, Semantics, Electronic Health Records, Databases, Factual, Data harmonization, OMOP, OHDSI, Vocabulary, Claims data, Clinical data, Data Science},
	pages = {58},
	file = {Full Text:/Users/dkapitan/Zotero/storage/JWKEG8FH/Henke et al. - 2024 - Conceptual design of a generic data harmonization process for OMOP common data model.pdf:application/pdf},
}

@article{wagenaar2024introduction,
	title = {Introduction: {Advancing} the {Commonsverse}: {The} {Political} {Economy} of {The} {Commons}},
	volume = {18},
	issn = {1875-0281},
	shorttitle = {Introduction},
	url = {https://www.thecommonsjournal.org/articles/10.5334/ijc.1400/},
	doi = {10.5334/ijc.1400},
	abstract = {This introductory article sets out the twin goals of this special issue: “Advancing the Commonsverse: The Political Economy of the Commons”. The first is to introduce the innovative work of David Bollier and Silke Helfrich in theorizing and researching the commons. The second is to explore the possibilities and constraints of the commons and the process of commoning as they unfold in real-world political-economic settings. Bollier and Helfrich have formulated a remarkable, ‘in-the-round’, moral-empirical theory of the commons. In their social ontology, peer governance and moral economy commons form a subversive alternative to the capitalist order. Bollier and Helfrich’s theory restores an older tradition of a moral critique of capitalism in the tradition of “moral economists” such as Karl Polanyi and H.P. Tawney. It raises important questions about the socio-ethical foundations of our society and economy, the relationship between civil associations and the state, and the nature of the state. In the final part of this introduction, we discuss the complex relationship between the commons and the state. We frame this relationship as one of mutual dependency and argue for the careful redesign of our institutions of public administration and democratic governance to make them more receptive and accessible to the creative powers of the commons. Finally, we introduce the contributions to this special issue, including a reflective concluding essay by David Bolllier.},
	language = {en},
	number = {1},
	urldate = {2025-07-14},
	journal = {International Journal of the Commons},
	publisher = {Ubiquity Press, Ltd.},
	author = {Wagenaar, Hendrik and Bartels, Koen},
	month = apr,
	year = {2024},
	pages = {337--350},
}

@article{zhu2025fedweight,
	title = {{FedWeight}: mitigating covariate shift of federated learning on electronic health records data through patients re-weighting},
	volume = {8},
	copyright = {2025 The Author(s)},
	issn = {2398-6352},
	shorttitle = {{FedWeight}},
	url = {https://www.nature.com/articles/s41746-025-01661-8},
	doi = {10.1038/s41746-025-01661-8},
	abstract = {Federated learning (FL) enables collaborative analysis of decentralized medical data while preserving patient privacy. However, the covariate shift from demographic and clinical differences can reduce model generalizability. We propose FedWeight, a novel FL framework that mitigates covariate shift by reweighting patient data from the source sites using density estimators, allowing the trained model to better align with the distribution of the target site. To support unsupervised applications, we introduce FedWeight ETM, a federated embedded topic model. We evaluated FedWeight in cross-site FL on the eICU dataset and cross-dataset FL between eICU and MIMIC III. FedWeight consistently outperforms standard FL baselines in predicting ICU mortality, ventilator use, sepsis diagnosis, and length of stay. SHAP-based interpretation and ETM-based topic modeling reveal improved identification of clinically relevant characteristics and disease topics associated with ICU readmission.},
	language = {en},
	number = {1},
	urldate = {2025-07-16},
	journal = {npj Digital Medicine},
	publisher = {Nature Publishing Group},
	author = {Zhu, He and Bai, Jun and Li, Na and Li, Xiaoxiao and Liu, Dianbo and Buckeridge, David L. and Li, Yue},
	month = may,
	year = {2025},
	keywords = {Diagnosis, Epidemiology},
	pages = {286},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/SEY2XS4G/Zhu et al. - 2025 - FedWeight mitigating covariate shift of federated learning on electronic health records data throug.pdf:application/pdf},
}

@misc{complete,
	title = {The complete guide to federated data analysis - {Lifebit}},
	url = {https://lifebit.ai/federated-data-analysis/the-complete-guide-to-federated-data-analysis/},
	abstract = {This complete guide to data federation discusses the benefits, the requirements to enable data federation and use cases worldwide.},
	language = {en-US},
	urldate = {2025-07-18},
	note = {Running Time: 80},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/33FRI5RC/the-complete-guide-to-federated-data-analysis.html:text/html},
}

@techreport{giles2024trefx,
	title = {{TRE}-{FX} {Technical} {Documentation} - {Primary} {Implementation}},
	url = {https://zenodo.org/records/10376658},
	doi = {10.5281/zenodo.10376658},
	abstract = {This report documents the primary TRE-FX implementation, which uses a microservice architecture, to be deployed with layers outside and inside the Trusted Research Environments.},
	urldate = {2025-07-18},
	institution = {Zenodo},
	author = {Giles, Thomas and Couldridge, Jonathan and Cox, Sam and Lea, Daniel and Panagi, Vasiliki and Thompson, Simon and Quinlan, Philip},
	month = jan,
	year = {2024},
	file = {PDF:/Users/dkapitan/Zotero/storage/6NSW5MX8/Giles et al. - 2024 - TRE-FX Technical Documentation - Primary Implementation.pdf:application/pdf},
}

@misc{bonawitz2019federated,
	title = {Towards {Federated} {Learning} at {Scale}: {System} {Design}},
	shorttitle = {Towards {Federated} {Learning} at {Scale}},
	url = {http://arxiv.org/abs/1902.01046},
	doi = {10.48550/arXiv.1902.01046},
	abstract = {Federated Learning is a distributed machine learning approach which enables model training on a large corpus of decentralized data. We have built a scalable production system for Federated Learning in the domain of mobile devices, based on TensorFlow. In this paper, we describe the resulting high-level design, sketch some of the challenges and their solutions, and touch upon the open problems and future directions.},
	urldate = {2025-08-09},
	publisher = {arXiv},
	author = {Bonawitz, Keith and Eichner, Hubert and Grieskamp, Wolfgang and Huba, Dzmitry and Ingerman, Alex and Ivanov, Vladimir and Kiddon, Chloe and Konečný, Jakub and Mazzocchi, Stefano and McMahan, H. Brendan and Overveldt, Timon Van and Petrou, David and Ramage, Daniel and Roselander, Jason},
	month = mar,
	year = {2019},
	note = {arXiv:1902.01046 [cs]},
	keywords = {Computer Science - Machine Learning, Statistics - Machine Learning, Computer Science - Distributed, Parallel, and Cluster Computing},
	file = {Preprint PDF:/Users/dkapitan/Zotero/storage/5KDYC8A2/Bonawitz et al. - 2019 - Towards Federated Learning at Scale System Design.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/5LDMGW6K/1902.html:text/html},
}

@article{zhang2025federated,
	title = {Federated {Heavy} {Hitter} {Analytics} with {Local} {Differential} {Privacy}},
	volume = {3},
	url = {https://dl.acm.org/doi/10.1145/3709739},
	doi = {10.1145/3709739},
	abstract = {Federated heavy hitter analytics enables service providers to better understand the preferences of cross-party users by analyzing the most frequent items. As with federated learning, it faces challenges of privacy concerns, statistical heterogeneity, and expensive communication. Local differential privacy (LDP), as the de facto standard for privacy-preserving data collection, solves the privacy challenge by letting each user perturb her data locally and report the sanitized version. However, in federated settings, applying LDP complicates the other two challenges, due to the deteriorated utility by the injected LDP noise or increasing communication/computation costs by perturbation mechanism. To tackle these problems, we propose a novel target-aligning prefix tree mechanism satisfying ε-LDP, for federated heavy hitter analytics. In particular, we propose an adaptive extension strategy to address the inconsistencies between covering necessary prefixes and estimating heavy hitters within a party to enhance the utility. We also present a consensus-based pruning strategy that utilizes noisy prior knowledge from other parties to further align the inconsistency between finding heavy hitters in each party and providing reasonable frequency information to identify the global ones. To the best of our knowledge, our study is the first solution to the federated heavy hitter analytics in a cross-party setting while satisfying the stringent ε-LDP. Comprehensive experiments on both real-world and synthetic datasets confirm the effectiveness of our proposed mechanism.},
	number = {1},
	urldate = {2025-08-09},
	journal = {Proc. ACM Manag. Data},
	author = {Zhang, Yuemin and Ye, Qingqing and Hu, Haibo},
	month = feb,
	year = {2025},
	pages = {42:1--42:27},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/DKAL9H52/Zhang et al. - 2025 - Federated Heavy Hitter Analytics with Local Differential Privacy.pdf:application/pdf},
}

@article{hundepoolhandbook,
	title = {Handbook on {Statistical} {Disclosure} {Control}},
	language = {en},
	author = {Hundepool, Anco and Domingo-Ferrer, Josep and Franconi, Luisa and Giessing, Sarah and Lenz, Rainer and Naylor, Jane and Nordholt, Eric Schulte and Seri, Giovanni and Wolf, Peter-Paul De and Tent, Reinhard and Młodak, Andrzej and Gussenbauer, Johannes and Wilak, Kamil},
	file = {PDF:/Users/dkapitan/Zotero/storage/4W34GRPG/Hundepool et al. - Handbook on Statistical Disclosure Control.pdf:application/pdf},
}

@book{rehman2021federated,
	address = {Cham},
	series = {Studies in {Computational} {Intelligence}},
	title = {Federated {Learning} {Systems}: {Towards} {Next}-{Generation} {AI}},
	volume = {965},
	copyright = {https://www.springer.com/tdm},
	isbn = {978-3-030-70603-6 978-3-030-70604-3},
	shorttitle = {Federated {Learning} {Systems}},
	url = {https://link.springer.com/10.1007/978-3-030-70604-3},
	doi = {10.1007/978-3-030-70604-3},
	language = {en},
	urldate = {2025-08-09},
	publisher = {Springer International Publishing},
	editor = {Rehman, Muhammad Habib Ur and Gaber, Mohamed Medhat},
	year = {2021},
	file = {PDF:/Users/dkapitan/Zotero/storage/K7VPJLCU/Rehman and Gaber - 2021 - Federated Learning Systems Towards Next-Generation AI.pdf:application/pdf},
}

@book{nguyen2024federated,
	title = {Federated {Learning}: {Theory} and {Practice}},
	isbn = {978-0-443-19038-4},
	shorttitle = {Federated {Learning}},
	abstract = {Federated Learning: Theory and Practi ce provides a holisti c treatment to federated learning as a distributed learning system with various forms of decentralized data and features. Part I of the book begins with a broad overview of opti mizati on fundamentals and modeling challenges, covering various aspects of communicati on effi ciency, theoretical convergence, and security. Part II featuresemerging challenges stemming from many socially driven concerns of federated learning as a future public machine learning service. Part III concludes the book with a wide array of industrial applicati ons of federated learning, as well as ethical considerations, showcasing its immense potential for driving innovation while safeguarding sensitive data.Federated Learning: Theory and Practi ce provides a comprehensive and accessible introducti on to federated learning which is suitable for researchers and students in academia, and industrial practitioners who seek to leverage the latest advance in machine learning for their entrepreneurial endeavors. - Presents the fundamentals and a survey of key developments in the field of federated learning - Provides emerging, state-of-the art topics that build on fundamentals - Contains industry applications - Gives an overview of visions of the future},
	language = {en},
	publisher = {Elsevier},
	author = {Nguyen, Lam M. and Hoang, Trong Nghia and Chen, Pin-Yu},
	month = feb,
	year = {2024},
	note = {Google-Books-ID: ddPKEAAAQBAJ},
	keywords = {Computers / Artificial Intelligence / Expert Systems, Computers / Artificial Intelligence / General},
	file = {PDF:/Users/dkapitan/Zotero/storage/GZNHMEGS/2024 - Front Matter.pdf:application/pdf},
}

@article{kohler2023eosa,
	title = {Eos and {OMOCL}: {Towards} a seamless integration of {openEHR} records into the {OMOP} {Common} {Data} {Model}},
	volume = {144},
	issn = {1532-0464},
	shorttitle = {Eos and {OMOCL}},
	url = {https://www.sciencedirect.com/science/article/pii/S1532046423001582},
	doi = {10.1016/j.jbi.2023.104437},
	abstract = {Background:
The reuse of data from electronic health records (EHRs) for research purposes promises to improve the data foundation for clinical trials and may even support to enable them. Nevertheless, EHRs are characterized by both, heterogeneous structure and semantics. To standardize this data for research, the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) standard has recently seen an increase in use. However, the conversion of these EHRs into the OMOP CDM requires complex and resource intensive Extract Transform and Load (ETL) processes. This hampers the reuse of clinical data for research. To solve the issues of heterogeneity of EHRs and the lack of semantic precision on the care site, the openEHR standard has recently seen wider adoption. A standardized process to integrate openEHR records into the CDM potentially lowers the barriers of making EHRs accessible for research. Yet, a comprehensive approach about the integration of openEHR records into the OMOP CDM has not yet been made.
Methods:
We analyzed both standards and compared their models to identify possible mappings. Based on this, we defined the necessary processes to transform openEHR records into CDM tables. We also discuss the limitation of openEHR with its unspecific demographics model and propose two possible solutions.
Results:
We developed the OMOP Conversion Language (OMOCL) which enabled us to define a declarative openEHR archetype-to-CDM mapping language. Using OMOCL, it was possible to define a set of mappings. As a proof-of-concept, we implemented the Eos tool, which uses the OMOCL-files to successfully automatize the ETL from real-world and sample EHRs into the OMOP CDM.
Discussion:
Both Eos and OMOCL provide a way to define generic mappings for an integration of openEHR records into OMOP. Thus, it represents a significant step towards achieving interoperability between the clinical and the research data domains. However, the transformation of openEHR data into the less expressive OMOP CDM leads to a loss of semantics.},
	urldate = {2025-08-11},
	journal = {Journal of Biomedical Informatics},
	author = {Kohler, Severin and Boscá, Diego and Kärcher, Florian and Haarbrandt, Birger and Prinz, Manuel and Marschollek, Michael and Eils, Roland},
	month = aug,
	year = {2023},
	keywords = {EHR, Secondary use, ETL, OMOP, OHDSI, OpenEHR},
	pages = {104437},
	file = {ScienceDirect Snapshot:/Users/dkapitan/Zotero/storage/VC97KT7Q/S1532046423001582.html:text/html},
}

@article{alammar2021machine,
	title = {{MACHINE} {LEARNING} {RESEARCH} {COMMUNICATION} {VIA} {ILLUSTRATED} {AND} {INTERACTIVE} {WEB} {ARTICLES}},
	abstract = {The recent explosion in machine learning research activity poses challenges for both researchers who aim to widely disseminate their work, as well as to readers who find it challenging to keep up with the onslaught of new research ideas. In this paper, we describe a workflow for creating a spectrum of machine learning research communication artifacts optimized to maximize the clarity of scientific communication, advance the fronts of explainability and interpretability, as well as empower the community to reproduce research software. The workflow describes creating a spectrum of communication artifacts including visuals, animations, interactive explorables, reproducible notebooks, open-source software, and software packages. The articles produced by this workflow have explained cutting-edge-ML research to a large audience and were read over three million times.},
	language = {en},
	author = {Alammar, J},
	year = {2021},
	file = {PDF:/Users/dkapitan/Zotero/storage/53S3SRYE/Alammar - 2021 - MACHINE LEARNING RESEARCH COMMUNICATION VIA ILLUSTRATED AND INTERACTIVE WEB ARTICLES.pdf:application/pdf},
}

@misc{frei2025infherno,
	title = {Infherno: {End}-to-end {Agent}-based {FHIR} {Resource} {Synthesis} from {Free}-form {Clinical} {Notes}},
	shorttitle = {Infherno},
	url = {http://arxiv.org/abs/2507.12261},
	doi = {10.48550/arXiv.2507.12261},
	abstract = {For clinical data integration and healthcare services, the HL7 FHIR standard has established itself as a desirable format for interoperability between complex health data. Previous attempts at automating the translation from free-form clinical notes into structured FHIR resources rely on modular, rule-based systems or LLMs with instruction tuning and constrained decoding. Since they frequently suffer from limited generalizability and structural inconformity, we propose an end-to-end framework powered by LLM agents, code execution, and healthcare terminology database tools to address these issues. Our solution, called Infherno, is designed to adhere to the FHIR document schema and competes well with a human baseline in predicting FHIR resources from unstructured text. The implementation features a front end for custom and synthetic data and both local and proprietary models, supporting clinical data integration processes and interoperability across institutions.},
	urldate = {2025-08-12},
	publisher = {arXiv},
	author = {Frei, Johann and Feldhus, Nils and Raithel, Lisa and Roller, Roland and Meyer, Alexander and Kramer, Frank},
	month = jul,
	year = {2025},
	note = {arXiv:2507.12261 [cs]},
	keywords = {Computer Science - Computation and Language, Computer Science - Artificial Intelligence},
	file = {Preprint PDF:/Users/dkapitan/Zotero/storage/UHH25EZY/Frei et al. - 2025 - Infherno End-to-end Agent-based FHIR Resource Synthesis from Free-form Clinical Notes.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/F3PPEP2C/2507.html:text/html},
}

@book{spillner2012operating,
	title = {Operating {Systems} and {Infrastructure} in {Data} {Science}},
	isbn = {978-3-7281-4168-2},
	url = {https://vdf.ch/operating-systems-and-infrastructure-in-data-science-e-book.html},
	doi = {10.3218/4168-2},
	abstract = {Modern data scientists work with a number of tools and operating system facilities in addition to online platforms. Mastering these in combination to manage their data and to deploy software, models and data as ready-to-use online services as well as to perform data science and analysis tasks is in the focus of Operating Systems and Infrastructure in Data Science. Readers will come to understand the fundamental concepts of operating systems and to explore plenty of tools in hands-on tasks and thus gradually develop the skills necessary to compose them for programming in the large, an essential capability in their later career. The book guides students through semester studies, acts as reference knowledge base and aids in acquiring the necessary knowledge, skills and competences especially in self-study settings. A unique feature of the book is the associated access to Edushell, a live environment to practice operating systems and infrastructure tasks.},
	language = {en},
	urldate = {2025-09-04},
	publisher = {vdf Hochschulverlag AG an der ETH Zürich},
	author = {Spillner, Josef},
	month = sep,
	year = {2012},
	file = {PDF:/Users/dkapitan/Zotero/storage/R4CCS6EH/Spillner - 2012 - Operating Systems and Infrastructure in Data Science.pdf:application/pdf},
}

@article{sana2025advancing,
	title = {Advancing {Federated} {Learning}: {A} {Systematic} {Literature} {Review} of {Methods}, {Challenges}, and {Applications}},
	volume = {13},
	issn = {2169-3536},
	shorttitle = {Advancing {Federated} {Learning}},
	url = {https://ieeexplore.ieee.org/document/11146653},
	doi = {10.1109/ACCESS.2025.3605165},
	abstract = {Federated Learning (FL) has emerged as a cutting-edge paradigm in machine learning, showcasing remarkable advancements in recent years. This research paper delves into the dynamic landscape of FL by addressing four pivotal research questions. The study investigates the most recent advancements in implementing FL and explores additional applications that could benefit from this decentralized learning paradigm. This inquiry aims to provide an up-to-date overview of the evolving FL field and its potential cross-industry impact. The paper explores the integration of FL with various machine learning approaches to ensure optimal performance, privacy preservation, and scalability. By unraveling the collaborative aspects of FL with other machine learning paradigms, the research seeks to unveil novel strategies for enhancing efficiency in FL scenarios. The third research question focuses on the repercussions of scalability challenges and resource constraints in federated learning. This investigation aims to uncover the practical difficulties of implementing FL across diverse sectors, shedding light on potential barriers to its widespread adoption. The research probes into the future of federated learning by examining how it will be utilized in upcoming technological advancements and industries. This exploration aims to provide insights into the long-term viability and applicability of FL, anticipating its role in shaping the technological landscape across various sectors. Through a comprehensive analysis of these research questions, this paper contributes to the understanding of FL, providing valuable insights for researchers, practitioners, and decision-makers navigating the intricate intersection of FL, machine learning, and emerging technologies. This research paper aspires to provide a holistic overview of the advancements, integration possibilities, challenges, and prospects associated with federated learning, contributing to the ongoing discourse on the intersection of FL and machine learning in contemporary technological landscapes.},
	urldate = {2025-09-11},
	journal = {IEEE Access},
	author = {Sana, Tamanna Zubairi and Abdulla, Shahab and Nag, Anindya and Das, Ayontika and Hassan, Md. Mehedi and Fiza, Zoya Zubairi and Karim, Asif and Kabir, Sheikh Ridwan Raihan},
	year = {2025},
	keywords = {Privacy, Medical services, security, Machine learning, machine learning, blockchain, Databases, Systematic literature review, Federated learning, Internet of Things, Scalability, Collaboration, Australia, Libraries, systematic literature review},
	pages = {153817--153844},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/E725JX27/Sana et al. - 2025 - Advancing Federated Learning A Systematic Literature Review of Methods, Challenges, and Application.pdf:application/pdf},
}

@inproceedings{esterhuyse2022exploring,
	title = {Exploring the {Enforcement} of {Private}, {Dynamic} {Policies} on {Medical} {Workflow} {Execution}},
	url = {https://ieeexplore.ieee.org/document/9973688},
	doi = {10.1109/eScience55777.2022.00086},
	abstract = {We report on the ideas and experiences of adapting Brane, a workflow execution framework, for use cases involving medical data exchange and processing. These use cases impose new requirements on the system to enforce policies encoding safety properties, ranging from access control to legal regulations pertaining to data privacy. Our approach emphasizes users' control over the extent to which they cooperate in distributed execution, at the cost of revealing information about their policies.},
	urldate = {2025-09-12},
	booktitle = {2022 {IEEE} 18th {International} {Conference} on e-{Science} (e-{Science})},
	author = {Esterhuyse, Christopher A. and Müller, Tim and Van Binsbergen, L. Thomas and Belloum, Adam S. Z.},
	month = oct,
	year = {2022},
	keywords = {Data privacy, Privacy, Access control, Policy, Law, Costs, Distance measurement, Multi-Agent, Process control, Safety, Workflow},
	pages = {481--486},
	file = {PDF:/Users/dkapitan/Zotero/storage/JC8EDYTW/Esterhuyse et al. - 2022 - Exploring the Enforcement of Private, Dynamic Policies on Medical Workflow Execution.pdf:application/pdf},
}

@article{gouthamchand2024making,
	title = {Making head and neck cancer clinical data {Findable}-{Accessible}-{Interoperable}-{Reusable} to support multi-institutional collaboration and federated learning},
	volume = {1},
	issn = {2976-8705},
	url = {https://doi.org/10.1093/bjrai/ubae005},
	doi = {10.1093/bjrai/ubae005},
	abstract = {Federated learning (FL) is a group of methodologies where statistical modelling can be performed without exchanging identifiable patient data between cooperating institutions. To realize its potential for AI development on clinical data, a number of bottlenecks need to be addressed. One of these is making data Findable-Accessible-Interoperable-Reusable (FAIR). The primary aim of this work is to show that tools making data FAIR allow consortia to collaborate on privacy-aware data exploration, data visualization, and training of models on each other’s original data.We propose a “Schema-on-Read” FAIR-ification method that adapts for different (re)analyses without needing to change the underlying original data. The procedure involves (1) decoupling the contents of the data from its schema and database structure, (2) annotation with semantic ontologies as a metadata layer, and (3) readout using semantic queries. Open-source tools are given as Docker containers to help local investigators prepare their data on-premises.We created a federated privacy-preserving visualization dashboard for case mix exploration of 5 distributed datasets with no common schema at the point of origin. We demonstrated robust and flexible prognostication model development and validation, linking together different data sources—clinical risk factors and radiomics.Our procedure leads to successful (re)use of data in FL-based consortia without the need to impose a common schema at every point of origin of data.This work supports the adoption of FL within the healthcare AI community by sharing means to make data more FAIR.},
	number = {1},
	urldate = {2025-09-15},
	journal = {BJR{\textbar}Artificial Intelligence},
	author = {Gouthamchand, Varsha and Choudhury, Ananya and Hoebers, Frank J P and Wesseling, Frederik W R and Welch, Mattea and Kim, Sejin and Kazmierska, Joanna and Dekker, Andre and Haibe-Kains, Benjamin and van Soest, Johan and Wee, Leonard},
	month = mar,
	year = {2024},
	pages = {ubae005},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/LR6B9UBN/Gouthamchand et al. - 2024 - Making head and neck cancer clinical data Findable-Accessible-Interoperable-Reusable to support mult.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/IJZDIRFR/ubae005.html:text/html},
}

@article{sadoughi2025breaking,
	series = {Advances in {Database} {Technology} - {EDBT}},
	title = {Breaking {Down} the {Data}-{Metadata} {Barrier} for {Effective} {Property} {Graph} {Data} {Management}: 28th {International} {Conference} on {Extending} {Database} {Technology}, {EDBT} 2025},
	shorttitle = {Breaking {Down} the {Data}-{Metadata} {Barrier} for {Effective} {Property} {Graph} {Data} {Management}},
	url = {https://www.scopus.com/pages/publications/105007897768},
	doi = {10.48786/edbt.2025.80},
	abstract = {The ISO standard Property Graph model has become increasingly popular for representing complex, interconnected data. However,
it lacks native support for querying metadata and reification, which limits its abilities to deal with the demands of modern
applications. We introduce the vision of Meta-Property Graph, a backwards compatible extension of the property graph model addressing these limitations. Our approach enables first-class treatment of labels and properties as queryable objects and supports
reification of substructures in a graph. We propose MetaGPML, a backwards compatible extension of the Graph Pattern Matching
Language forming the core of the ISO standard GQL, to query these enhanced graphs. We demonstrate how these foundations
pave the way for advanced data analytics and governance tasks that are challenging or impossible with current property graph
systems.},
	urldate = {2025-09-16},
	journal = {Proceedings 28th International Conference on Extending Database Technology ( EDBT 2025 ) Barcelona, Spain, March 25 - March 28},
	publisher = {OpenProceedings.org},
	author = {Sadoughi, Sepehr and Yakovets, Nikolay and Fletcher, George H.L.},
	month = mar,
	year = {2025},
	keywords = {Graph data management, Graph data models, Knowledge graphs, Property graphs},
	pages = {978--984},
}

@incollection{vansoest2025governance,
	title = {A {Governance} {Framework} for {Federated} {Learning} {Projects} in {Healthcare}},
	copyright = {https://creativecommons.org/licenses/by-nc/4.0/},
	isbn = {978-1-64368-596-0},
	url = {https://ebooks.iospress.nl/doi/10.3233/SHTI250324},
	doi = {10.3233/SHTI250324},
	abstract = {Federated Learning is becoming more widely used. However, a governance framework is needed to make sure this technology is used safely. In this work, we present a governance framework for Federated Learning project and show how often we have applied the accompanying agreements. Finally, we have shown that Federated Learning is not a solution to circumvent privacy regulations, however that our governance framework provides means to implement the technology within current regulations.},
	language = {en},
	urldate = {2025-09-17},
	booktitle = {Studies in {Health} {Technology} and {Informatics}},
	publisher = {IOS Press},
	author = {Van Soest, Johan and Sanchez Gomez, Luis and Wee, Leonard and Dekker, Andre},
	editor = {Andrikopoulou, Elisavet and Gallos, Parisis and Arvanitis, Theodoros N. and Austin, Rosalynn and Benis, Arriel and Cornet, Ronald and Chatzistergos, Panagiotis and Dejaco, Alexander and Dusseljee-Peute, Linda and Mohasseb, Alaa and Natsiavas, Pantelis and Nakkas, Haythem and Scott, Philip},
	month = may,
	year = {2025},
	file = {PDF:/Users/dkapitan/Zotero/storage/FV3ND22I/Van Soest et al. - 2025 - A Governance Framework for Federated Learning Projects in Healthcare.pdf:application/pdf},
}

@article{teo2024federated,
	title = {Federated machine learning in healthcare: {A} systematic review on clinical applications and technical architecture},
	volume = {5},
	issn = {2666-3791},
	shorttitle = {Federated machine learning in healthcare},
	url = {https://www.sciencedirect.com/science/article/pii/S2666379124000429},
	doi = {10.1016/j.xcrm.2024.101419},
	abstract = {Federated learning (FL) is a distributed machine learning framework that is gaining traction in view of increasing health data privacy protection needs. By conducting a systematic review of FL applications in healthcare, we identify relevant articles in scientific, engineering, and medical journals in English up to August 31st, 2023. Out of a total of 22,693 articles under review, 612 articles are included in the final analysis. The majority of articles are proof-of-concepts studies, and only 5.2\% are studies with real-life application of FL. Radiology and internal medicine are the most common specialties involved in FL. FL is robust to a variety of machine learning models and data types, with neural networks and medical imaging being the most common, respectively. We highlight the need to address the barriers to clinical translation and to assess its real-world impact in this new digital data-driven healthcare scene.},
	number = {2},
	urldate = {2025-09-17},
	journal = {Cell Reports Medicine},
	author = {Teo, Zhen Ling and Jin, Liyuan and Liu, Nan and Li, Siqi and Miao, Di and Zhang, Xiaoman and Ng, Wei Yan and Tan, Ting Fang and Lee, Deborah Meixuan and Chua, Kai Jie and Heng, John and Liu, Yong and Goh, Rick Siow Mong and Ting, Daniel Shu Wei},
	month = feb,
	year = {2024},
	keywords = {artificial intelligence, healthcare, federated learning, systematic review},
	pages = {101419},
	file = {Full Text:/Users/dkapitan/Zotero/storage/4YMGW38U/Teo et al. - 2024 - Federated machine learning in healthcare A systematic review on clinical applications and technical.pdf:application/pdf;ScienceDirect Snapshot:/Users/dkapitan/Zotero/storage/U264DK7C/S2666379124000429.html:text/html},
}

@misc{margfmartel162023revolutionizing,
	title = {Revolutionizing {Data} {Management}: {The} {Era} of {Distributed} {Data} {Lakes} and {Federated} {Solutions}},
	shorttitle = {Revolutionizing {Data} {Management}},
	url = {https://teadal.eu/2023/11/16/revolutionizing-data-management-the-era-of-distributed-data-lakes-and-federated-solutions/},
	abstract = {In today's fast-paced and data-driven business landscape, the need for efficient and scalable data management solutions has never been more critical.},
	language = {en-US},
	urldate = {2025-09-17},
	journal = {TEADAL},
	author = {margfmartel16},
	month = nov,
	year = {2023},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/T4AMKGW4/revolutionizing-data-management-the-era-of-distributed-data-lakes-and-federated-solutions.html:text/html},
}

@misc{c0c0n3,
	title = {c0c0n3/teadal.proto: {Messing} around with cloud infra for https://www.teadal.eu.},
	url = {https://github.com/c0c0n3/teadal.proto},
	urldate = {2025-09-17},
	file = {c0c0n3/teadal.proto\: Messing around with cloud infra for https\://www.teadal.eu.:/Users/dkapitan/Zotero/storage/FECTQA3E/teadal.html:text/html},
}

@incollection{anastasakis2023analysis,
	address = {New York},
	edition = {1},
	title = {Analysis of {Privacy} {Preservation} {Enhancements} in {Federated} {Learning} {Frameworks}},
	copyright = {http://creativecommons.org/licenses/by-nc/4.0},
	isbn = {978-1-032-63240-7},
	url = {https://www.taylorfrancis.com/books/9781032632407/chapters/10.1201/9781032632407-8},
	doi = {10.1201/9781032632407-8},
	language = {en},
	urldate = {2025-09-17},
	booktitle = {Shaping the {Future} of {IoT} with {Edge} {Intelligence}},
	publisher = {River Publishers},
	author = {Anastasakis, Z. and Bourou, S. and Velivasaki, T. H. and Voulkidis, A. and Skias, D.},
	collaborator = {Sofia, Rute C. and Soldatos, John},
	month = nov,
	year = {2023},
	pages = {117--133},
	file = {PDF:/Users/dkapitan/Zotero/storage/TCQQZZ54/Anastasakis et al. - 2023 - Analysis of Privacy Preservation Enhancements in Federated Learning Frameworks.pdf:application/pdf},
}

@article{vansoest2019annotation,
	title = {Annotation of existing databases using {Semantic} {Web} technologies: making data more {FAIR}},
	url = {https://ceur-ws.org/Vol-2849/paper-11.pdf},
	abstract = {Making data FAIR is an elaborate task. Hospitals and/or departments have to invest into technologies usually unknown and often do not have the resources to make data FAIR. Our work aims to provide a framework and tooling where users can easily make their data (more) FAIR. This framework uses RDF and OWL-based inferencing to annotate existing databases or comma-separated files. For every database, a custom ontology is build based on the database schema, which can be annotated to describe matching standardized terminologies. In this work, we describe the tooling developed, and the current implementation in an institutional datawarehouse pertaining over 3000 rectal cancer patients. We report on the performance (time) of the extraction and annotation process by the developed tooling. Furthermore, we do show that annotation of existing databases using OWL2-based reasoning is possible. Furthermore, we show that the ontology extracted from existing databases can provide a description framework to describe and annotate existing data sources. This would target mostly the “Interoperable” aspect of FAIR.},
	language = {en},
	author = {van Soest, Johan and Choudhury, Ananya and Gaikwad, Nikhil and Sloep, Matthijs and Dekker, Andre},
	year = {2019},
	file = {PDF:/Users/dkapitan/Zotero/storage/VKRX3FMN/van Soest et al. - Annotation of existing databases using Semantic Web technologies making data more FAIR.pdf:application/pdf},
}

@article{cadman2024molgenis,
	title = {{MOLGENIS} {Armadillo}: a lightweight server for federated analysis using {DataSHIELD}},
	volume = {41},
	copyright = {https://creativecommons.org/licenses/by/4.0/},
	issn = {1367-4811},
	shorttitle = {{MOLGENIS} {Armadillo}},
	url = {https://academic.oup.com/bioinformatics/article/doi/10.1093/bioinformatics/btae726/7914926},
	doi = {10.1093/bioinformatics/btae726},
	abstract = {Abstract
            
              Summary
              Extensive human health data from cohort studies, national registries, and biobanks can reveal lifecourse risk factors impacting health. Combining these sources offers increased statistical power, rare outcome detection, replication of findings, and extended study periods. Traditionally, this required data transfer to a central location or separate partner analyses with pooled summary statistics, posing ethical, legal, and time constraints. Federated analysis—which involves remote data analysis without sharing individual-level data—is a promising alternative. One promising solution is DataSHIELD (https://datashield.org/), an open-source R based implementation. To enable federated analysis, data owners need a user-friendly way to install the federated infrastructure and manage users and data. Here, we present MOLGENIS Armadillo: a lightweight server for federated analysis solutions such as DataSHIELD.
            
            
              Availability and implementation
              Armadillo is implemented as a collection of three packages freely available under the open source licence LGPLv3: two R packages downloadable from the Comprehensive R Archive Network (CRAN) (“MolgenisArmadillo” and “DSMolgenisArmdillo”) and one Java application (“ArmadilloService”) as jar and docker images via Github (https://github.com/molgenis/molgenis-service-armadillo).},
	language = {en},
	number = {1},
	urldate = {2025-09-22},
	journal = {Bioinformatics},
	author = {Cadman, Tim and Slofstra, Mariska K and Van Der Geest, Marije A and Avraam, Demetris and Bishop, Tom R P and De Boer, Tommy and Duijts, Liesbeth and Haakma, Sido and Hyde, Eleanor and Jaddoe, Vincent and Karramass, Tarik and Kelpin, Fleur and Marcon, Yannick and Pinot De Moira, Angela and Postma, Dick and Tolboom, Clemens and Veenstra, Ruben L and Wheater, Stuart and Welten, Marieke and Wilson, Rebecca C and Zwart, Erik and Swertz, Morris},
	editor = {Martelli, Pier Luigi},
	month = dec,
	year = {2024},
	pages = {btae726},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/LC5V24LU/Cadman et al. - 2024 - MOLGENIS Armadillo a lightweight server for federated analysis using DataSHIELD.pdf:application/pdf},
}

@article{weisedatavisiting,
	title = {A data-visiting infrastructure for providing access to preserved databases that cannot be shared or made publicly accessible},
	language = {en},
	author = {Weise, Martin and Rauber, Andreas},
	file = {PDF:/Users/dkapitan/Zotero/storage/6B7NI5WL/Weise and Rauber - A data-visiting infrastructure for providing access to preserved databases that cannot be shared or.pdf:application/pdf},
}

@article{weise2022ossdip,
	title = {{OSSDIP}: {Open} {Source} {Secure} {Data} {Infrastructure} and {Processes} {Supporting} {Data} {Visiting}},
	volume = {21},
	issn = {1683-1470},
	shorttitle = {{OSSDIP}},
	url = {https://datascience.codata.org/articles/dsj-2022-004},
	doi = {10.5334/dsj-2022-004},
	abstract = {Meeting the conflicting goals of protecting and maintaining control over sensitive data while also allowing access by third parties constitutes a significant challenge. Secure data infrastructures support data visiting in a highly controlled and monitored environment which, if properly set-up and operated, provide high security guarantees through a combination of technical, legal and procedural mechanisms. To ease the process of deploying such a secure data infrastructure, we present a detailed documentation of the architecture and processes of such an infrastructure and provide a pre-configured reference implementation based entirely on open source software that can be flexibly configured to meet differing security requirements and deployment scenarios.We combine mechanisms for data visiting on secured infrastructure components with optional components of data anonymization and fingerprinting, covered by extensive logging and monitoring functions and embedded in defined processes and contractual frameworks. The set-up is based upon the experience of operating such a secure infrastructure in the medical domain for almost ten years, addressing the emerging need to make such a solution available to a larger set of stakeholders. We show that our system significantly enhances data visiting, offers a higher level of data isolation and present our open source reference implementation thereof.},
	language = {en},
	number = {1},
	urldate = {2025-09-29},
	journal = {Data Science Journal},
	author = {Weise, Martin and Kovacevic, Filip and Popper, Nikolas and Rauber, Andreas},
	month = feb,
	year = {2022},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/NIEAKQYF/Weise et al. - 2022 - OSSDIP Open Source Secure Data Infrastructure and Processes Supporting Data Visiting.pdf:application/pdf},
}

@article{david2023be,
	title = {“{Be} sustainable”: {EOSC}‐{Life} recommendations for implementation of {FAIR} principles in life science data handling},
	volume = {42},
	issn = {0261-4189},
	shorttitle = {“{Be} sustainable”},
	url = {https://www.embopress.org/doi/full/10.15252/embj.2023115008},
	doi = {10.15252/embj.2023115008},
	abstract = {The main goals and challenges for the life science communities in the Open Science framework are to increase reuse and sustainability of data resources, software tools, and workflows, especially in large‐scale data‐driven research and computational analyses. Here, we present key findings, procedures, effective measures and recommendations for generating and establishing sustainable life science resources based on the collaborative, cross‐disciplinary work done within the EOSC‐Life (European Open Science Cloud for Life Sciences) consortium. Bringing together 13 European life science research infrastructures, it has laid the foundation for an open, digital space to support biological and medical research. Using lessons learned from 27 selected projects, we describe the organisational, technical, financial and legal/ethical challenges that represent the main barriers to sustainability in the life sciences. We show how EOSC‐Life provides a model for sustainable data management according to FAIR (findability, accessibility, interoperability, and reusability) principles, including solutions for sensitive‐ and industry‐related resources, by means of cross‐disciplinary training and best practices sharing. Finally, we illustrate how data harmonisation and collaborative work facilitate interoperability of tools, data, solutions and lead to a better understanding of concepts, semantics and functionalities in the life sciences.},
	number = {23},
	urldate = {2025-09-29},
	journal = {The EMBO Journal},
	publisher = {John Wiley \& Sons, Ltd},
	author = {David, Romain and Rybina, Arina and Burel, Jean‐Marie and Heriche, Jean‐Karim and Audergon, Pauline and Boiten, Jan‐Willem and Coppens, Frederik and Crockett, Sara and Exter, Katrina and Fahrner, Sven and Fratelli, Maddalena and Goble, Carole and Gormanns, Philipp and Grantner, Tobias and Grüning, Björn and Gurwitz, Kim Tamara and Hancock, John M and Harmse, Henriette and Holub, Petr and Juty, Nick and Karnbach, Geoffrey and Karoune, Emma and Keppler, Antje and Klemeier, Jessica and Lancelotti, Carla and Legras, Jean‐Luc and Lister, Allyson L and Longo, Dario Livio and Ludwig, Rebecca and Madon, Bénédicte and Massimi, Marzia and Matser, Vera and Matteoni, Rafaele and Mayrhofer, Michaela Th and Ohmann, Christian and Panagiotopoulou, Maria and Parkinson, Helen and Perseil, Isabelle and Pfander, Claudia and Pieruschka, Roland and Raess, Michael and Rauber, Andreas and Richard, Audrey S and Romano, Paolo and Rosato, Antonio and Sánchez‐Pla, Alex and Sansone, Susanna‐Assunta and Sarkans, Ugis and Serrano‐Solano, Beatriz and Tang, Jing and Tanoli, Ziaurrehman and Tedds, Jonathan and Wagener, Harald and Weise, Martin and Westerhoff, Hans V and Wittner, Rudolf and Ewbank, Jonathan and Blomberg, Niklas and Gribbon, Philip},
	month = dec,
	year = {2023},
	pages = {e115008},
}

@article{gonzalez-garcia2024phiri,
	title = {{PHIRI}: lessons for an extensive reuse of sensitive data in federated health research},
	volume = {34},
	issn = {1464-360X},
	shorttitle = {{PHIRI}},
	url = {https://doi.org/10.1093/eurpub/ckae036},
	doi = {10.1093/eurpub/ckae036},
	abstract = {The extensive and continuous reuse of sensitive health data could enhance the role of population health research on public decisions. This paper describes the design principles and the different building blocks that have supported the implementation and deployment of Population Health Information Research Infrastructure (PHIRI), the strengths and challenges of the approach and some future developments.The design and implementation of PHIRI have been developed upon: (i) the data visiting principle—data does not move but code moves; (ii) the orchestration of the research question throughout a workflow that ensured legal, organizational, semantic and technological interoperability and (iii) a ‘master–worker’ federated computational architecture that supported the development of four uses cases.Nine participants nodes and 28 Euro-Peristat members completed the deployment of the infrastructure according to the expected outputs. As a consequence, each use case produced and published their own common data model, the analytical pipeline and the corresponding research outputs. All the digital objects were developed and published according to Open Science and FAIR principles.PHIRI has successfully supported the development of four use cases in a federated manner, overcoming limitations for the reuse of sensitive health data and providing a methodology to achieve interoperability in multiple research nodes.},
	number = {Supplement\_1},
	urldate = {2025-09-29},
	journal = {European Journal of Public Health},
	author = {González-García, Juan and González-Galindo, Javier and Estupiñán-Romero, Francisco and Thißen, Martin and Lyons, Ronan A and Telleria-Orriols, Carlos and Bernal-Delgado, Enrique and {Population Health Information Research Infrastructure}},
	month = jul,
	year = {2024},
	pages = {i43--i49},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/ZP69ESTY/González-García et al. - 2024 - PHIRI lessons for an extensive reuse of sensitive data in federated health research.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/XA48XTGW/ckae036.html:text/html},
}

@inproceedings{bacco2024federated,
	title = {Federated {Learning} for {Data} {Spaces}: a {Privacy}-{Enhancing} {Strategy} {Based} on {Data} {Visiting}},
	shorttitle = {Federated {Learning} for {Data} {Spaces}},
	url = {https://ieeexplore.ieee.org/abstract/document/10948754},
	doi = {10.1109/MetroAgriFor63043.2024.10948754},
	abstract = {This work explores the paradigm of data visiting that, through privacy-enhancing technologies, shows the potential to access and use data otherwise inaccessible. Building on the ongoing EU initiative to design, implement, and run sectorial data spaces, we consider federated learning as one the most promising approaches for the objective above. We propose a domain-agnostic strategy that can be extended and adapted to different needs. We conclude by analysing the limitations and challenges of the approach we propose.},
	urldate = {2025-09-29},
	booktitle = {2024 {IEEE} {International} {Workshop} on {Metrology} for {Agriculture} and {Forestry} ({MetroAgriFor})},
	author = {Bacco, Manlio and Di Leo, Margherita and Kona, Albana and Santoro, Mattia and Mazzetti, Paolo},
	month = oct,
	year = {2024},
	keywords = {Data privacy, Data models, Conferences, Buildings, Technology, Federated learning, federated learning, privacy-enhancing technologies, data spaces, data visiting, Forestry, Green products, Identification of persons, Metrology},
	pages = {592--597},
	file = {PDF:/Users/dkapitan/Zotero/storage/4H2S479A/Bacco et al. - 2024 - Federated Learning for Data Spaces a Privacy-Enhancing Strategy Based on Data Visiting.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/5HR8ZCWN/10948754.html:text/html},
}

@article{hagestedt2024tipping,
	title = {Toward a tipping point in federated learning in healthcare and life sciences},
	volume = {5},
	issn = {2666-3899},
	url = {https://www.sciencedirect.com/science/article/pii/S2666389924002368},
	doi = {10.1016/j.patter.2024.101077},
	abstract = {We discuss the real-world application of federated learning (FL) in the healthcare and life sciences industry, noting a tipping point in its adoption beyond academia. Sharing our experiences with multi-hospital and multi-pharma collaborations, we highlight the importance of involving key stakeholders to develop production-grade FL solutions that are fully compliant with stringent privacy and security standards.},
	number = {11},
	urldate = {2025-10-06},
	journal = {Patterns},
	author = {Hagestedt, Inken and Hales, Ian and Boernert, Eric and Roth, Holger R. and Hoeh, Michael A. and Röhm, Robin and Dobson, Ellie and Prieto, José Tomás},
	month = nov,
	year = {2024},
	pages = {101077},
	file = {PDF:/Users/dkapitan/Zotero/storage/R9C8RAMQ/Hagestedt et al. - 2024 - Toward a tipping point in federated learning in healthcare and life sciences.pdf:application/pdf;ScienceDirect Snapshot:/Users/dkapitan/Zotero/storage/D2GGEPAD/S2666389924002368.html:text/html},
}

@article{yang2024federateda,
	title = {Federated learning as a catalyst for digital healthcare innovations},
	volume = {5},
	issn = {26663899},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2666389924001594},
	doi = {10.1016/j.patter.2024.101026},
	language = {en},
	number = {7},
	urldate = {2025-10-06},
	journal = {Patterns},
	author = {Yang, Guang and Edwards, Brandon and Bakas, Spyridon and Dou, Qi and Xu, Daguang and Li, Xiaoxiao and Wang, Wanying},
	month = jul,
	year = {2024},
	pages = {101026},
	file = {PDF:/Users/dkapitan/Zotero/storage/48R6QZQU/Yang et al. - 2024 - Federated learning as a catalyst for digital healthcare innovations.pdf:application/pdf},
}

@article{yan2024fedeye,
	title = {{FedEYE}: {A} scalable and flexible end-to-end federated learning platform for ophthalmology},
	volume = {5},
	issn = {26663899},
	shorttitle = {{FedEYE}},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2666389924000199},
	doi = {10.1016/j.patter.2024.100928},
	abstract = {Data-driven machine learning, as a promising approach, possesses the capability to build high-quality, exact, and robust models from ophthalmic medical data. Ophthalmic medical data, however, presently exist across disparate data silos with privacy limitations, making centralized training challenging. While ophthalmologists may not specialize in machine learning and artificial intelligence (AI), considerable impediments arise in the associated realm of research. To address these issues, we design and develop FedEYE, a scalable and flexible end-to-end ophthalmic federated learning platform. During FedEYE design, we adhere to four fundamental design principles, ensuring that ophthalmologists can effortlessly create independent and federated AI research tasks. Benefiting from the design principles and architecture of FedEYE, it encloses numerous key features, including rich and customizable capabilities, separation of concerns, scalability, and flexible deployment. We also validated the applicability of FedEYE by employing several prevalent neural networks on ophthalmic disease image classification tasks.},
	language = {en},
	number = {2},
	urldate = {2025-10-06},
	journal = {Patterns},
	author = {Yan, Bingjie and Cao, Danmin and Jiang, Xinlong and Chen, Yiqiang and Dai, Weiwei and Dong, Fan and Huang, Wuliang and Zhang, Teng and Gao, Chenlong and Chen, Qian and Yan, Zhen and Wang, Zhirui},
	month = feb,
	year = {2024},
	pages = {100928},
	file = {PDF:/Users/dkapitan/Zotero/storage/T5HYGAV8/Yan et al. - 2024 - FedEYE A scalable and flexible end-to-end federated learning platform for ophthalmology.pdf:application/pdf},
}

@article{zhang2024recent,
	title = {Recent methodological advances in federated learning for healthcare},
	volume = {5},
	issn = {26663899},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2666389924001314},
	doi = {10.1016/j.patter.2024.101006},
	abstract = {For healthcare datasets, it is often impossible to combine data samples from multiple sites due to ethical, privacy, or logistical concerns. Federated learning allows for the utilization of powerful machine learning algorithms without requiring the pooling of data. Healthcare data have many simultaneous challenges, such as highly siloed data, class imbalance, missing data, distribution shifts, and non-standardized variables, that require new methodologies to address. Federated learning adds significant methodological complexity to conventional centralized machine learning, requiring distributed optimization, communication between nodes, aggregation of models, and redistribution of models. In this systematic review, we consider all papers on Scopus published between January 2015 and February 2023 that describe new federated learning methodologies for addressing challenges with healthcare data. We reviewed 89 papers meeting these criteria. Significant systemic issues were identified throughout the literature, compromising many methodologies reviewed. We give detailed recommendations to help improve methodology development for federated learning in healthcare.},
	language = {en},
	number = {6},
	urldate = {2025-10-06},
	journal = {Patterns},
	author = {Zhang, Fan and Kreuter, Daniel and Chen, Yichen and Dittmer, Sören and Tull, Samuel and Shadbahr, Tolou and Schut, Martijn and Asselbergs, Folkert and Kar, Sujoy and Sivapalaratnam, Suthesh and Williams, Sophie and Koh, Mickey and Henskens, Yvonne and De Wit, Bart and D’Alessandro, Umberto and Bah, Bubacarr and Secka, Ousman and Nachev, Parashkev and Gupta, Rajeev and Trompeter, Sara and Boeckx, Nancy and Van Laer, Christine and Awandare, Gordon A. and Sarpong, Kwabena and Amenga-Etego, Lucas and Leers, Mathie and Huijskens, Mirelle and McDermott, Samuel and Ouwehand, Willem H. and Rudd, James and Schӧnlieb, Carola-Bibiane and Gleadall, Nicholas and Roberts, Michael and Preller, Jacobus and Rudd, James H.F. and Aston, John A.D. and Schönlieb, Carola-Bibiane and Gleadall, Nicholas and Roberts, Michael},
	month = jun,
	year = {2024},
	pages = {101006},
	file = {PDF:/Users/dkapitan/Zotero/storage/5SQJ4CF4/Zhang et al. - 2024 - Recent methodological advances in federated learning for healthcare.pdf:application/pdf},
}

@article{jiang2024ufps,
	title = {{UFPS}: {A} unified framework for partially annotated federated segmentation in heterogeneous data distribution},
	volume = {5},
	issn = {26663899},
	shorttitle = {{UFPS}},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2666389924000011},
	doi = {10.1016/j.patter.2024.100917},
	abstract = {Partially supervised segmentation is a label-saving method based on datasets with fractional classes labeled and intersectant. Its practical application in real-world medical scenarios is, however, hindered by privacy concerns and data heterogeneity. To address these issues without compromising privacy, federated partially supervised segmentation (FPSS) is formulated in this work. The primary challenges for FPSS are class heterogeneity and client drift. We propose a unified federated partially labeled segmentation (UFPS) framework to segment pixels within all classes for partially annotated datasets by training a comprehensive global model that avoids class collision. Our framework includes unified label learning (ULL) and sparse unified sharpness aware minimization (sUSAM) for class and feature space unification, respectively. Through empirical studies, we find that traditional methods in partially supervised segmentation and federated learning often struggle with class collision when combined. Our extensive experiments on real medical datasets demonstrate better deconflicting and generalization capabilities of UFPS.},
	language = {en},
	number = {2},
	urldate = {2025-10-06},
	journal = {Patterns},
	author = {Jiang, Le and Ma, Li Yan and Zeng, Tie Yong and Ying, Shi Hui},
	month = feb,
	year = {2024},
	pages = {100917},
	file = {PDF:/Users/dkapitan/Zotero/storage/YS3QHI8J/Jiang et al. - 2024 - UFPS A unified framework for partially annotated federated segmentation in heterogeneous data distr.pdf:application/pdf},
}

@article{zhang2024unified,
	title = {Unified fair federated learning for digital healthcare},
	volume = {5},
	issn = {26663899},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2666389923003148},
	doi = {10.1016/j.patter.2023.100907},
	abstract = {Federated learning (FL) is a promising approach for healthcare institutions to train high-quality medical models collaboratively while protecting sensitive data privacy. However, FL models encounter fairness issues at diverse levels, leading to performance disparities across different subpopulations. To address this, we propose Federated Learning with Unified Fairness Objective (FedUFO), a unified framework consolidating diverse fairness levels within FL. By leveraging distributionally robust optimization and a unified uncertainty set, it ensures consistent performance across all subpopulations and enhances the overall efficacy of FL in healthcare and other domains while maintaining accuracy levels comparable with those of existing methods. Our model was validated by applying it to four digital healthcare tasks using real-world datasets in federated settings. Our collaborative machine learning paradigm not only promotes artificial intelligence in digital healthcare but also fosters social equity by embodying fairness.},
	language = {en},
	number = {1},
	urldate = {2025-10-06},
	journal = {Patterns},
	author = {Zhang, Fengda and Shuai, Zitao and Kuang, Kun and Wu, Fei and Zhuang, Yueting and Xiao, Jun},
	month = jan,
	year = {2024},
	pages = {100907},
	file = {PDF:/Users/dkapitan/Zotero/storage/2P8WL49A/Zhang et al. - 2024 - Unified fair federated learning for digital healthcare.pdf:application/pdf},
}

@article{stripelis2024federated,
	title = {A federated learning architecture for secure and private neuroimaging analysis},
	volume = {5},
	issn = {26663899},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2666389924001648},
	doi = {10.1016/j.patter.2024.101031},
	abstract = {The amount of biomedical data continues to grow rapidly. However, collecting data from multiple sites for joint analysis remains challenging due to security, privacy, and regulatory concerns. To overcome this challenge, we use federated learning, which enables distributed training of neural network models over multiple data sources without sharing data. Each site trains the neural network over its private data for some time and then shares the neural network parameters (i.e., weights and/or gradients) with a federation controller, which in turn aggregates the local models and sends the resulting community model back to each site, and the process repeats. Our federated learning architecture, MetisFL, provides strong security and privacy. First, sample data never leave a site. Second, neural network parameters are encrypted before transmission and the global neural model is computed under fully homomorphic encryption. Finally, we use information-theoretic methods to limit information leakage from the neural model to prevent a ‘‘curious’’ site from performing model inversion or membership attacks. We present a thorough evaluation of the performance of secure, private federated learning in neuroimaging tasks, including for predicting Alzheimer’s disease and for brain age gap estimation (BrainAGE) from magnetic resonance imaging (MRI) studies in challenging, heterogeneous federated environments where sites have different amounts of data and statistical distributions.},
	language = {en},
	number = {8},
	urldate = {2025-10-06},
	journal = {Patterns},
	author = {Stripelis, Dimitris and Gupta, Umang and Saleem, Hamza and Dhinagar, Nikhil and Ghai, Tanmay and Anastasiou, Chrysovalantis and Sánchez, Rafael and Steeg, Greg Ver and Ravi, Srivatsan and Naveed, Muhammad and Thompson, Paul M. and Ambite, José Luis},
	month = aug,
	year = {2024},
	pages = {101031},
	file = {PDF:/Users/dkapitan/Zotero/storage/RR9EPZ6Y/Stripelis et al. - 2024 - A federated learning architecture for secure and private neuroimaging analysis.pdf:application/pdf},
}

@article{pan2024adaptive,
	title = {An adaptive federated learning framework for clinical risk prediction with electronic health records from multiple hospitals},
	volume = {5},
	issn = {26663899},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2666389923003008},
	doi = {10.1016/j.patter.2023.100898},
	abstract = {Clinical risk prediction with electronic health records (EHR) using machine learning has attracted lots of attentions in recent years, where one of the key challenges is how to protect data privacy. Federated learning (FL) provides a promising framework for building predictive models by leveraging the data from multiple institutions without sharing them. However, data distribution drift across different institutions greatly impacts the performance of FL. In this paper, an adaptive FL framework was proposed to address this challenge. Our framework separated the input features into stable, domain-specific, and conditional-irrelevant parts according to their relationships to clinical outcomes. We evaluate this framework on the tasks of predicting the onset risk of sepsis and acute kidney injury (AKI) for patients in the intensive care unit (ICU) from multiple clinical institutions. The results showed that our framework can achieve better prediction performance compared with existing FL baselines and provide reasonable feature interpretations.},
	language = {en},
	number = {1},
	urldate = {2025-10-06},
	journal = {Patterns},
	author = {Pan, Weishen and Xu, Zhenxing and Rajendran, Suraj and Wang, Fei},
	month = jan,
	year = {2024},
	pages = {100898},
	file = {PDF:/Users/dkapitan/Zotero/storage/LDPC5HX8/Pan et al. - 2024 - An adaptive federated learning framework for clinical risk prediction with electronic health records.pdf:application/pdf},
}

@article{rootes-murdy2024cortical,
	title = {Cortical similarities in psychiatric and mood disorders identified in federated {VBM} analysis via {COINSTAC}},
	volume = {5},
	issn = {26663899},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2666389924001028},
	doi = {10.1016/j.patter.2024.100987},
	abstract = {Structural neuroimaging studies have identified a combination of shared and disorder-specific patterns of gray matter (GM) deficits across psychiatric disorders. Pooling large data allows for examination of a possible common neuroanatomical basis that may identify a certain vulnerability for mental illness. Large-scale collaborative research is already facilitated by data repositories, institutionally supported databases, and data archives. However, these data-sharing methodologies can suffer from significant barriers. Federated approaches augment these approaches by enabling access or more sophisticated, shareable and scaled-up analyses of large-scale data. We examined GM alterations using Collaborative Informatics and Neuroimaging Suite Toolkit for Anonymous Computation, an open-source, decentralized analysis application. Through federated analysis of eight sites, we identified significant overlap in the GM patterns (n = 4,102) of individuals with schizophrenia, major depressive disorder, and autism spectrum disorder. These results show cortical and subcortical regions that may indicate a shared vulnerability to psychiatric disorders.},
	language = {en},
	number = {7},
	urldate = {2025-10-06},
	journal = {Patterns},
	author = {Rootes-Murdy, Kelly and Panta, Sandeep and Kelly, Ross and Romero, Javier and Quidé, Yann and Cairns, Murray J. and Loughland, Carmel and Carr, Vaughan J. and Catts, Stanley V. and Jablensky, Assen and Green, Melissa J. and Henskens, Frans and Kiltschewskij, Dylan and Michie, Patricia T. and Mowry, Bryan and Pantelis, Christos and Rasser, Paul E. and Reay, William R. and Schall, Ulrich and Scott, Rodney J. and Watkeys, Oliver J. and Roberts, Gloria and Mitchell, Philip B. and Fullerton, Janice M. and Overs, Bronwyn J. and Kikuchi, Masataka and Hashimoto, Ryota and Matsumoto, Junya and Fukunaga, Masaki and Sachdev, Perminder S. and Brodaty, Henry and Wen, Wei and Jiang, Jiyang and Fani, Negar and Ely, Timothy D. and Lorio, Adriana and Stevens, Jennifer S. and Ressler, Kerry and Jovanovic, Tanja and Van Rooij, Sanne J.H. and Federmann, Lydia M. and Jockwitz, Christiane and Teumer, Alexander and Forstner, Andreas J. and Caspers, Svenja and Cichon, Sven and Plis, Sergey M. and Sarwate, Anand D. and Calhoun, Vince D.},
	month = jul,
	year = {2024},
	pages = {100987},
	file = {PDF:/Users/dkapitan/Zotero/storage/4Z7RC8HP/Rootes-Murdy et al. - 2024 - Cortical similarities in psychiatric and mood disorders identified in federated VBM analysis via COI.pdf:application/pdf},
}

@article{danek2024federated,
	title = {Federated learning for multi-omics: {A} performance evaluation in {Parkinson}’s disease},
	volume = {5},
	issn = {26663899},
	shorttitle = {Federated learning for multi-omics},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2666389924000448},
	doi = {10.1016/j.patter.2024.100945},
	abstract = {While machine learning (ML) research has recently grown more in popularity, its application in the omics domain is constrained by access to sufficiently large, high-quality datasets needed to train ML models. Federated learning (FL) represents an opportunity to enable collaborative curation of such datasets among participating institutions. We compare the simulated performance of several models trained using FL against classically trained ML models on the task of multi-omics Parkinson’s disease prediction. We find that FL model performance tracks centrally trained ML models, where the most performant FL model achieves an AUC-PR of 0.876 ± 0.009, 0.014 ± 0.003 less than its centrally trained variation. We also determine that the dispersion of samples within a federation plays a meaningful role in model performance. Our study implements several open-source FL frameworks and aims to highlight some of the challenges and opportunities when applying these collaborative methods in multi-omics studies.},
	language = {en},
	number = {3},
	urldate = {2025-10-06},
	journal = {Patterns},
	author = {Danek, Benjamin P. and Makarious, Mary B. and Dadu, Anant and Vitale, Dan and Lee, Paul Suhwan and Singleton, Andrew B. and Nalls, Mike A. and Sun, Jimeng and Faghri, Faraz},
	month = mar,
	year = {2024},
	pages = {100945},
	file = {PDF:/Users/dkapitan/Zotero/storage/5BB28HBQ/Danek et al. - 2024 - Federated learning for multi-omics A performance evaluation in Parkinson’s disease.pdf:application/pdf},
}

@article{khalil2024federated,
	title = {Federated learning for privacy-preserving depression detection with multilingual language models in social media posts},
	volume = {5},
	issn = {26663899},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2666389924001053},
	doi = {10.1016/j.patter.2024.100990},
	abstract = {The incidences of mental health illnesses, such as suicidal ideation and depression, are increasing, which highlights the urgent need for early detection methods. There is a growing interest in using natural language processing (NLP) models to analyze textual data from patients, but accessing patients’ data for research purposes can be challenging due to privacy concerns. Federated learning (FL) is a promising approach that can balance the need for centralized learning with data ownership sensitivity. In this study, we examine the effectiveness of FL models in detecting depression by using a simulated multilingual dataset. We analyzed social media posts in five different languages with varying sample sizes. Our findings indicate that FL achieves strong performance in most cases while maintaining clients’ privacy for both independent and non-independent client partitioning.},
	language = {en},
	number = {7},
	urldate = {2025-10-06},
	journal = {Patterns},
	author = {Khalil, Samar Samir and Tawfik, Noha S. and Spruit, Marco},
	month = jul,
	year = {2024},
	pages = {100990},
	file = {PDF:/Users/dkapitan/Zotero/storage/72PC9U88/Khalil et al. - 2024 - Federated learning for privacy-preserving depression detection with multilingual language models in.pdf:application/pdf},
}

@article{chen2024integration,
	title = {Integration of large language models and federated learning},
	volume = {5},
	issn = {26663899},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2666389924002708},
	doi = {10.1016/j.patter.2024.101098},
	abstract = {As the parameter size of large language models (LLMs) continues to expand, there is an urgent need to address the scarcity of high-quality data. In response, existing research has attempted to make a breakthrough by incorporating federated learning (FL) into LLMs. Conversely, considering the outstanding performance of LLMs in task generalization, researchers have also tried applying LLMs within FL to tackle challenges in relevant domains. The complementarity between LLMs and FL has already ignited widespread research interest. In this review, we aim to deeply explore the integration of LLMs and FL. We propose a research framework dividing the fusion of LLMs and FL into three parts: the combination of LLM sub-technologies with FL, the integration of FL sub-technologies with LLMs, and the overall merger of LLMs and FL. We first provide a comprehensive review of the current state of research in the domain of LLMs combined with FL, including their typical applications, integration advantages, challenges faced, and future directions for resolution. Subsequently, we discuss the practical applications of the combination of LLMs and FL in critical scenarios such as healthcare, finance, and education and provide new perspectives and insights into future research directions for LLMs and FL.},
	language = {en},
	number = {12},
	urldate = {2025-10-06},
	journal = {Patterns},
	author = {Chen, Chaochao and Feng, Xiaohua and Li, Yuyuan and Lyu, Lingjuan and Zhou, Jun and Zheng, Xiaolin and Yin, Jianwei},
	month = dec,
	year = {2024},
	pages = {101098},
	file = {PDF:/Users/dkapitan/Zotero/storage/F9FYM8TV/Chen et al. - 2024 - Integration of large language models and federated learning.pdf:application/pdf},
}

@article{casella2023merge,
	title = {{MERGE}: {A} model for multi-input biomedical federated learning},
	volume = {4},
	issn = {26663899},
	shorttitle = {{MERGE}},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2666389923002404},
	doi = {10.1016/j.patter.2023.100856},
	abstract = {Driven by the deep learning (DL) revolution, artificial intelligence (AI) has become a fundamental tool for many biomedical tasks, including analyzing and classifying diagnostic images. Imaging, however, is not the only source of information. Tabular data, such as personal and genomic data and blood test results, are routinely collected but rarely considered in DL pipelines. Nevertheless, DL requires large datasets that often must be pooled from different institutions, raising non-trivial privacy concerns. Federated learning (FL) is a cooperative learning paradigm that aims to address these issues by moving models instead of data across different institutions. Here, we present a federated multi-input architecture using images and tabular data as a methodology to enhance model performance while preserving data privacy. We evaluated it on two showcases: the prognosis of COVID-19 and patients’ stratification in Alzheimer’s disease, providing evidence of enhanced accuracy and F1 scores against single-input models and improved generalizability against nonfederated models.},
	language = {en},
	number = {11},
	urldate = {2025-10-06},
	journal = {Patterns},
	author = {Casella, Bruno and Riviera, Walter and Aldinucci, Marco and Menegaz, Gloria},
	month = nov,
	year = {2023},
	pages = {100856},
	file = {PDF:/Users/dkapitan/Zotero/storage/VB4G567Y/Casella et al. - 2023 - MERGE A model for multi-input biomedical federated learning.pdf:application/pdf},
}

@article{pezoulas2024fhbf,
	title = {{FHBF}: {Federated} hybrid boosted forests with dropout rates for supervised learning tasks across highly imbalanced clinical datasets},
	volume = {5},
	issn = {26663899},
	shorttitle = {{FHBF}},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2666389923002957},
	doi = {10.1016/j.patter.2023.100893},
	abstract = {Although several studies have deployed gradient boosting trees (GBT) as a robust classifier for federated learning tasks (federated GBT [FGBT]), even with dropout rates (federated gradient boosting trees with dropout rate [FDART]), none of them have investigated the overfitting effects of FGBT across heterogeneous and highly imbalanced datasets within federated environments nor the effect of dropouts in the loss function. In this work, we present the federated hybrid boosted forests (FHBF) algorithm, which incorporates a hybrid weight update approach to overcome ill-posed problems that arise from overfitting effects during the training across highly imbalanced datasets in the cloud. Eight case studies were conducted to stress the performance of FHBF against existing algorithms toward the development of robust AI models for lymphoma development across 18 European federated databases. Our results highlight the robustness of FHBF, yielding an average loss of 0.527 compared with FGBT (0.611) and FDART (0.584) with increased classification performance (0.938 sensitivity, 0.732 specificity).},
	language = {en},
	number = {1},
	urldate = {2025-10-06},
	journal = {Patterns},
	author = {Pezoulas, Vasileios C. and Kalatzis, Fanis and Exarchos, Themis P. and Goules, Andreas and Tzioufas, Athanasios G. and Fotiadis, Dimitrios I.},
	month = jan,
	year = {2024},
	pages = {100893},
	file = {PDF:/Users/dkapitan/Zotero/storage/RYI4DHXX/Pezoulas et al. - 2024 - FHBF Federated hybrid boosted forests with dropout rates for supervised learning tasks across highl.pdf:application/pdf},
}

@article{rajendran2024learning,
	title = {Learning across diverse biomedical data modalities and cohorts: {Challenges} and opportunities for innovation},
	volume = {5},
	issn = {26663899},
	shorttitle = {Learning across diverse biomedical data modalities and cohorts},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2666389923003227},
	doi = {10.1016/j.patter.2023.100913},
	abstract = {In healthcare, machine learning (ML) shows significant potential to augment patient care, improve population health, and streamline healthcare workflows. Realizing its full potential is, however, often hampered by concerns about data privacy, diversity in data sources, and suboptimal utilization of different data modalities. This review studies the utility of cross-cohort cross-category (C4) integration in such contexts: the process of combining information from diverse datasets distributed across distinct, secure sites. We argue that C4 approaches could pave the way for ML models that are both holistic and widely applicable. This paper provides a comprehensive overview of C4 in health care, including its present stage, potential opportunities, and associated challenges.},
	language = {en},
	number = {2},
	urldate = {2025-10-06},
	journal = {Patterns},
	author = {Rajendran, Suraj and Pan, Weishen and Sabuncu, Mert R. and Chen, Yong and Zhou, Jiayu and Wang, Fei},
	month = feb,
	year = {2024},
	pages = {100913},
	file = {PDF:/Users/dkapitan/Zotero/storage/S7EESWPB/Rajendran et al. - 2024 - Learning across diverse biomedical data modalities and cohorts Challenges and opportunities for inn.pdf:application/pdf},
}

@article{pati2024privacy,
	title = {Privacy preservation for federated learning in health care},
	volume = {5},
	issn = {26663899},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2666389924000825},
	doi = {10.1016/j.patter.2024.100974},
	abstract = {Artificial intelligence (AI) shows potential to improve health care by leveraging data to build models that can inform clinical workflows. However, access to large quantities of diverse data is needed to develop robust generalizable models. Data sharing across institutions is not always feasible due to legal, security, and privacy concerns. Federated learning (FL) allows for multi-institutional training of AI models, obviating data sharing, albeit with different security and privacy concerns. Specifically, insights exchanged during FL can leak information about institutional data. In addition, FL can introduce issues when there is limited trust among the entities performing the compute. With the growing adoption of FL in health care, it is imperative to elucidate the potential risks. We thus summarize privacy-preserving FL literature in this work with special regard to health care. We draw attention to threats and review mitigation approaches. We anticipate this review to become a health-care researcher’s guide to security and privacy in FL.},
	language = {en},
	number = {7},
	urldate = {2025-10-06},
	journal = {Patterns},
	author = {Pati, Sarthak and Kumar, Sourav and Varma, Amokh and Edwards, Brandon and Lu, Charles and Qu, Liangqiong and Wang, Justin J. and Lakshminarayanan, Anantharaman and Wang, Shih-han and Sheller, Micah J. and Chang, Ken and Singh, Praveer and Rubin, Daniel L. and Kalpathy-Cramer, Jayashree and Bakas, Spyridon},
	month = jul,
	year = {2024},
	pages = {100974},
	file = {PDF:/Users/dkapitan/Zotero/storage/K73C22MV/Pati et al. - 2024 - Privacy preservation for federated learning in health care.pdf:application/pdf},
}

@misc{dehghanidata,
	title = {Data {Mesh} {Principles} and {Logical} {Architecture}},
	url = {https://martinfowler.com/articles/data-mesh-principles.html},
	abstract = {Four principles that drive a logical architecture for a data mesh.},
	urldate = {2025-10-09},
	journal = {martinfowler.com},
	author = {Dehghani, Zhamak},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/F892QFXK/data-mesh-principles.html:text/html},
}

@misc{dehghanihow,
	title = {How to {Move} {Beyond} a {Monolithic} {Data} {Lake} to a {Distributed} {Data} {Mesh}},
	url = {https://martinfowler.com/articles/data-monolith-to-mesh.html},
	abstract = {There are problems with the centralized data lake. A future data mesh needs domains, self-service platforms, and product thinking.},
	urldate = {2025-10-09},
	journal = {martinfowler.com},
	author = {Dehghani, Zhamak},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/VEE64RBZ/data-monolith-to-mesh.html:text/html},
}

@book{slokenberga2025european,
	address = {London},
	edition = {1},
	title = {The {European} {Health} {Data} {Space}: {Examining} {A} {New} {Era} in {Data} {Protection}},
	isbn = {978-1-003-54411-1},
	shorttitle = {The {European} {Health} {Data} {Space}},
	url = {https://www.taylorfrancis.com/books/9781003544111},
	doi = {10.4324/9781003544111},
	language = {en},
	urldate = {2025-10-13},
	publisher = {Routledge},
	author = {Slokenberga, Santa and Ó Cathaoir, Katharina and Shabani, Mahsa},
	month = feb,
	year = {2025},
	file = {Ebook:/Users/dkapitan/Zotero/storage/88VV66K3/Slokenberga et al. - 2025 - The European Health Data Space examining a new era in data protection.epub:application/epub+zip;PDF:/Users/dkapitan/Zotero/storage/W94GEF3U/Slokenberga et al. - 2025 - The European Health Data Space Examining A New Era in Data Protection.pdf:application/pdf},
}

@misc{federatedc,
	title = {Federated database systems for managing distributed, heterogeneous, and autonomous databases - {Google} {Search}},
	url = {https://www.google.com/search?q=Federated+database+systems+for+managing%0Adistributed,+heterogeneous,+and+autonomous+databases},
	urldate = {2025-10-13},
	file = {Federated database systems for managing distributed, heterogeneous, and autonomous databases - Google Search:/Users/dkapitan/Zotero/storage/EN974FTL/search.html:text/html},
}

@article{witsenburgnodetonode,
	title = {Node-to-node secure multiparty computation on {Vantage6}},
	abstract = {This study investigated the possibilities to create node to node communication between Vantage6 algorithm containers without the interposition of the Vantage6 server. Three infrastructures are created: an overlay network in swarm mode, an overlay network with an external key-value store, and a VPN network. The performance of these setups are tested on throughput with iperf3 and on the duration to perform a secure sum algorithm script between three nodes. Throughput is higher on the overlay networks and running a secure sum algorithm on the overlay network is faster than running this algorithm in the VPN setup. A swarm and an overlay network are manually created on the Vantage6 server virtual machine. The docker-manager Python script of the Vantage6 node is changed to join the swarm and connect the algorithm containers to the overlay network. To achieve this new feature a workaround is needed, since the Docker API does not support overlay networks.},
	language = {en},
	author = {Witsenburg, Renee},
	file = {PDF:/Users/dkapitan/Zotero/storage/98FSU542/Witsenburg - Node-to-node secure multiparty computation on Vantage6.pdf:application/pdf},
}

@misc{gouthamchand2025federated,
	title = {Federated {Prediction} {Models} and {External} {Validation} for {Radiotherapy} {Outcomes} in {Oropharyngeal} {Cancer} using {F}.{A}.{I}.{R}. {Clinical} and {Radiomics} {Data}},
	copyright = {© 2025, Posted by Cold Spring Harbor Laboratory. This pre-print is available under a Creative Commons License (Attribution 4.0 International), CC BY 4.0, as described at http://creativecommons.org/licenses/by/4.0/},
	url = {https://www.medrxiv.org/content/10.1101/2025.01.29.25321214v1},
	doi = {10.1101/2025.01.29.25321214},
	abstract = {Development and validation of outcome prediction models in multi-centric cancer datasets are essential to ensure their applicability and accuracy across diverse populations. This study addresses the challenges of model generalizability in Head and Neck cancer research by utilizing combined clinical and radiomics data from centers in India and the Netherlands, following Findable-Accessible-Interoperable-Reusable (F.A.I.R.) data principles. We use Vantage6, a federated learning software infrastructure that implements the Personal Health Train (PHT) paradigm to ensure data privacy and security during collaborative research. Correlation-based Feature Selection (CFS) and LASSO regularized Cox regression were used to identify key features in training Cox proportional hazards models to predict Overall Survival (OS), Distant Metastasis (DM), and Locoregional Recurrence (LRR) in six datasets totaling 1131 oropharyngeal cancer patients. Our results highlight the efficacy of federated learning in providing a secure environment for multi-centric cancer research, enabling the development and validation of predictive models while upholding patient data confidentiality.},
	language = {en},
	urldate = {2025-10-13},
	publisher = {medRxiv},
	author = {Gouthamchand, Varsha and Gottardelli, Benedetta and Kulkarni, Gauri and Sherkhane, Umesh B. and Hogenboom, Joshi and Subramanian, Rajamenakshi and Jha, Ashish Kumar and Mithun, Sneha and Purandare, Nilendu C. and Agarwal, Jai Prakash and Sekar, Krithikaa and Lohith, G. and Laskar, Sarbani G. and Sinha, Shwetabh and Hoebers, Frank JP and Rangarajan, Venkatesh and Sunder, Gaur and Dekker, Andre and Soest, Johan van and Wee, Leonard},
	month = jan,
	year = {2025},
	note = {Pages: 2025.01.29.25321214},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/66TXDTSR/Gouthamchand et al. - 2025 - Federated Prediction Models and External Validation for Radiotherapy Outcomes in Oropharyngeal Cance.pdf:application/pdf},
}

@article{palaciobetter,
	title = {{BETTER}: {Better} {rEal}-world {healTh}-{DaTa} {distributEd} analytics {Research} platform⋆},
	abstract = {Over the last few years, data-driven medicine has gained increasing importance in terms of diagnosis, treatment, and research due to the exponential growth of healthcare data. The linkage of cross-border health data from various sources, including genomics, and analysis via innovative Artificial Intelligence (AI) approaches will allow a better understanding of risk factors, causes, and the development of optimal treatment in different disease areas. However, the reuse of patient data is often limited to data sets available in a single medical center. The main reasons why health data are not shared across institutional boundaries rely on ethical, legal, and privacy aspects and rules. Therefore, in order to (1) enable the sharing of health data across national borders, (2) fully comply with the current GDPR privacy guidelines/regulations, and (3) innovate by pushing research beyond state of the art, BETTER proposes a robust decentralized privacy preservation infrastructure which will empower researchers, innovators, and healthcare professionals to exploit the full potential of larger sets of multisource health data through tailored AI tools useful to compare, integrate, and analyze in a secure, cost-effective fashion; with the end goal of supporting the improvement of citizen health outcomes. In detail, this interdisciplinary project proposes the co-creation of three clinical use cases involving seven medical centers located in the EU and beyond, where sensitive patient data, including genomics, are made available and analyzed in a GDPR-compliant mechanism via a Distributed Analytics (DA) paradigm called the Personal Health Train (PHT). The main principle of the PHT is that the analytical task is brought to the data provider (medical center), and the data instances remain in their original location. In this project, two mature implementations of the PHT (PADME and Vantage6), already validated in real-world scenarios, will be fused to build the BETTER platform.},
	language = {en},
	author = {Palacio, Ana León and Román, José F Reyes and Pastor, Oscar},
	file = {PDF:/Users/dkapitan/Zotero/storage/SK3SHGFB/Palacio et al. - BETTER Better rEal-world healTh-DaTa distributEd analytics Research platform⋆.pdf:application/pdf},
}

@article{ankolekar2025advancing,
	title = {Advancing breast, lung and prostate cancer research with federated learning. {A} systematic review},
	volume = {8},
	copyright = {2025 The Author(s)},
	issn = {2398-6352},
	url = {https://www.nature.com/articles/s41746-025-01591-5},
	doi = {10.1038/s41746-025-01591-5},
	abstract = {Federated learning (FL) is advancing cancer research by enabling privacy-preserving collaborative training of machine learning (ML) models on diverse, multi-centre data. This systematic review synthesises current knowledge on state-of-the-art FL in oncology, focusing on breast, lung, and prostate cancer. Unlike previous surveys, we critically evaluate FL’s real-world implementation and impact, demonstrating its effectiveness in enhancing ML generalisability and performance in clinical settings. Our analysis reveals that FL outperformed centralised ML in 15 out of 25 studies, spanning diverse models and clinical applications, including multi-modal integration for precision medicine. Despite challenges identified in reproducibility and standardisation, FL demonstrates substantial potential for advancing cancer research. We propose future research focus on addressing these limitations and investigating advanced FL methods to fully harness data diversity and realise the transformative power of cutting-edge FL in cancer care.},
	language = {en},
	number = {1},
	urldate = {2025-10-13},
	journal = {npj Digital Medicine},
	publisher = {Nature Publishing Group},
	author = {Ankolekar, Anshu and Boie, Sebastian and Abdollahyan, Maryam and Gadaleta, Emanuela and Hasheminasab, Seyed Alireza and Yang, Guang and Beauville, Charles and Dikaios, Nikolaos and Kastis, George Anthony and Bussmann, Michael and Chelala, Claude and Khalid, Sara and Kruger, Hagen and Lambin, Philippe and Papanastasiou, Giorgos},
	month = may,
	year = {2025},
	keywords = {Breast cancer, Lung cancer, Urological cancer},
	pages = {314},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/WL3DIBWB/Ankolekar et al. - 2025 - Advancing breast, lung and prostate cancer research with federated learning. A systematic review.pdf:application/pdf},
}

@article{sheth1990federateda,
	title = {Federated database systems for managing distributed, heterogeneous, and autonomous databases},
	volume = {22},
	issn = {0360-0300, 1557-7341},
	url = {https://dl.acm.org/doi/10.1145/96602.96604},
	doi = {10.1145/96602.96604},
	abstract = {A federated database system (FDBS) is a collection of cooperating database systems that are autonomous and possibly heterogeneous. In this paper, we define a reference architecture for distributed database management systems from system and schema viewpoints and show how various FDBS architectures can be developed. We then define a methodology for developing one of the popular architectures of an FDBS. Finally, we discuss critical issues related to developing and operating an FDBS.},
	language = {en},
	number = {3},
	urldate = {2025-12-05},
	journal = {ACM Computing Surveys},
	author = {Sheth, Amit P. and Larson, James A.},
	month = sep,
	year = {1990},
	pages = {183--236},
	file = {PDF:/Users/dkapitan/Zotero/storage/4T5BWHC3/Sheth and Larson - 1990 - Federated database systems for managing distributed, heterogeneous, and autonomous databases.pdf:application/pdf},
}

@article{kalendralis2020faircompliant,
	title = {{FAIR}-compliant clinical, radiomics and {DICOM} metadata of {RIDER}, interobserver, {Lung1} and head-{Neck1} {TCIA} collections},
	volume = {47},
	copyright = {© 2020 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.},
	issn = {2473-4209},
	url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/mp.14322},
	doi = {10.1002/mp.14322},
	abstract = {Purpose One of the most frequently cited radiomics investigations showed that features automatically extracted from routine clinical images could be used in prognostic modeling. These images have been made publicly accessible via The Cancer Imaging Archive (TCIA). There have been numerous requests for additional explanatory metadata on the following datasets — RIDER, Interobserver, Lung1, and Head–Neck1. To support repeatability, reproducibility, generalizability, and transparency in radiomics research, we publish the subjects’ clinical data, extracted radiomics features, and digital imaging and communications in medicine (DICOM) headers of these four datasets with descriptive metadata, in order to be more compliant with findable, accessible, interoperable, and reusable (FAIR) data management principles. Acquisition and validation methods Overall survival time intervals were updated using a national citizens registry after internal ethics board approval. Spatial offsets of the primary gross tumor volume (GTV) regions of interest (ROIs) associated with the Lung1 CT series were improved on the TCIA. GTV radiomics features were extracted using the open-source Ontology-Guided Radiomics Analysis Workflow (O-RAW). We reshaped the output of O-RAW to map features and extraction settings to the latest version of Radiomics Ontology, so as to be consistent with the Image Biomarker Standardization Initiative (IBSI). Digital imaging and communications in medicine metadata was extracted using a research version of Semantic DICOM (SOHARD, GmbH, Fuerth; Germany). Subjects’ clinical data were described with metadata using the Radiation Oncology Ontology. All of the above were published in Resource Descriptor Format (RDF), that is, triples. Example SPARQL queries are shared with the reader to use on the online triples archive, which are intended to illustrate how to exploit this data submission. Data format The accumulated RDF data are publicly accessible through a SPARQL endpoint where the triples are archived. The endpoint is remotely queried through a graph database web application at http://sparql.cancerdata.org. SPARQL queries are intrinsically federated, such that we can efficiently cross-reference clinical, DICOM, and radiomics data within a single query, while being agnostic to the original data format and coding system. The federated queries work in the same way even if the RDF data were partitioned across multiple servers and dispersed physical locations. Potential applications The public availability of these data resources is intended to support radiomics features replication, repeatability, and reproducibility studies by the academic community. The example SPARQL queries may be freely used and modified by readers depending on their research question. Data interoperability and reusability are supported by referencing existing public ontologies. The RDF data are readily findable and accessible through the aforementioned link. Scripts used to create the RDF are made available at a code repository linked to this submission: https://gitlab.com/UM-CDS/FAIR-compliant\_clinical\_radiomics\_and\_DICOM\_metadata.},
	language = {en},
	number = {11},
	urldate = {2026-01-09},
	journal = {Medical Physics},
	author = {Kalendralis, Petros and Shi, Zhenwei and Traverso, Alberto and Choudhury, Ananya and Sloep, Matthijs and Zhovannik, Ivan and Starmans, Martijn P.A. and Grittner, Detlef and Feltens, Peter and Monshouwer, Rene and Klein, Stefan and Fijten, Rianne and Aerts, Hugo and Dekker, Andre and van Soest, Johan and Wee, Leonard},
	year = {2020},
	note = {\_eprint: https://aapm.onlinelibrary.wiley.com/doi/pdf/10.1002/mp.14322},
	keywords = {FAIR, reproducibility, datasets, radiomics, repeatability},
	pages = {5931--5940},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/YXT45L4H/Kalendralis et al. - 2020 - FAIR-compliant clinical, radiomics and DICOM metadata of RIDER, interobserver, Lung1 and head-Neck1.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/7L7QGKNV/mp.html:text/html},
}

@article{gouthamchand2024makinga,
	title = {Making head and neck cancer clinical data {Findable}-{Accessible}-{Interoperable}-{Reusable} to support multi-institutional collaboration and federated learning},
	volume = {1},
	issn = {2976-8705},
	url = {https://doi.org/10.1093/bjrai/ubae005},
	doi = {10.1093/bjrai/ubae005},
	abstract = {Federated learning (FL) is a group of methodologies where statistical modelling can be performed without exchanging identifiable patient data between cooperating institutions. To realize its potential for AI development on clinical data, a number of bottlenecks need to be addressed. One of these is making data Findable-Accessible-Interoperable-Reusable (FAIR). The primary aim of this work is to show that tools making data FAIR allow consortia to collaborate on privacy-aware data exploration, data visualization, and training of models on each other’s original data.We propose a “Schema-on-Read” FAIR-ification method that adapts for different (re)analyses without needing to change the underlying original data. The procedure involves (1) decoupling the contents of the data from its schema and database structure, (2) annotation with semantic ontologies as a metadata layer, and (3) readout using semantic queries. Open-source tools are given as Docker containers to help local investigators prepare their data on-premises.We created a federated privacy-preserving visualization dashboard for case mix exploration of 5 distributed datasets with no common schema at the point of origin. We demonstrated robust and flexible prognostication model development and validation, linking together different data sources—clinical risk factors and radiomics.Our procedure leads to successful (re)use of data in FL-based consortia without the need to impose a common schema at every point of origin of data.This work supports the adoption of FL within the healthcare AI community by sharing means to make data more FAIR.},
	number = {1},
	urldate = {2026-01-09},
	journal = {BJR{\textbar}Artificial Intelligence},
	author = {Gouthamchand, Varsha and Choudhury, Ananya and Hoebers, Frank J P and Wesseling, Frederik W R and Welch, Mattea and Kim, Sejin and Kazmierska, Joanna and Dekker, Andre and Haibe-Kains, Benjamin and van Soest, Johan and Wee, Leonard},
	month = mar,
	year = {2024},
	pages = {ubae005},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/M6Z3SBJP/Gouthamchand et al. - 2024 - Making head and neck cancer clinical data Findable-Accessible-Interoperable-Reusable to support mult.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/ENYX9Q9A/ubae005.html:text/html},
}

@inproceedings{short2021execution,
	title = {Execution of a {Federated} {Learning} process within a smart contract},
	issn = {2158-4001},
	url = {https://ieeexplore.ieee.org/document/9427734},
	doi = {10.1109/ICCE50685.2021.9427734},
	abstract = {High quality datasets have always been valuable for the creation of Machine Learning (ML) models. It therefore makes sense to provide rewards to users that participate in a Federated Learning (FL) process with such datasets. In this competitive scene, we design a solution that leverages a blockchain network, a smart contract and a model verification algorithm in order to coordinate the training process, record user performance and provide rewards in a transparent manner.},
	urldate = {2026-01-16},
	booktitle = {2021 {IEEE} {International} {Conference} on {Consumer} {Electronics} ({ICCE})},
	author = {Short, Andrew R. and Leligou, Helen C. and Theocharis, Efstathios},
	month = jan,
	year = {2021},
	note = {ISSN: 2158-4001},
	keywords = {Blockchain, Machine learning, Machine learning algorithms, Smart contracts, Training, Conferences, federated learning, Collaboration, Blockchains, smart contract, verification algorithms},
	pages = {1--4},
	file = {Snapshot:/Users/dkapitan/Zotero/storage/2NH8HRZW/9427734.html:text/html},
}

@misc{xia2023data,
	title = {Data {Station}: {Delegated}, {Trustworthy}, and {Auditable} {Computation} to {Enable} {Data}-{Sharing} {Consortia} with a {Data} {Escrow}},
	shorttitle = {Data {Station}},
	url = {http://arxiv.org/abs/2305.03842},
	doi = {10.48550/arXiv.2305.03842},
	abstract = {Pooling and sharing data increases and distributes its value. But since data cannot be revoked once shared, scenarios that require controlled release of data for regulatory, privacy, and legal reasons default to not sharing. Because selectively controlling what data to release is difficult, the few data-sharing consortia that exist are often built around data-sharing agreements resulting from long and tedious one-off negotiations. We introduce Data Station, a data escrow designed to enable the formation of data-sharing consortia. Data owners share data with the escrow knowing it will not be released without their consent. Data users delegate their computation to the escrow. The data escrow relies on delegated computation to execute queries without releasing the data first. Data Station leverages hardware enclaves to generate trust among participants, and exploits the centralization of data and computation to generate an audit log. We evaluate Data Station on machine learning and data-sharing applications while running on an untrusted intermediary. In addition to important qualitative advantages, we show that Data Station: i) outperforms federated learning baselines in accuracy and runtime for the machine learning application; ii) is orders of magnitude faster than alternative secure data-sharing frameworks; and iii) introduces small overhead on the critical path.},
	urldate = {2026-01-17},
	publisher = {arXiv},
	author = {Xia, Siyuan and Zhu, Zhiru and Zhu, Chris and Zhao, Jinjin and Chard, Kyle and Elmore, Aaron J. and Foster, Ian and Franklin, Michael and Krishnan, Sanjay and Fernandez, Raul Castro},
	month = may,
	year = {2023},
	note = {arXiv:2305.03842 [cs]},
	keywords = {Computer Science - Databases},
	file = {Preprint PDF:/Users/dkapitan/Zotero/storage/VL956HKT/Xia et al. - 2023 - Data Station Delegated, Trustworthy, and Auditable Computation to Enable Data-Sharing Consortia wit.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/TLUXTG25/2305.html:text/html},
}

@article{nijsse2023fair,
	title = {{FAIR} data station for lightweight metadata management and validation of omics studies},
	volume = {12},
	issn = {2047-217X},
	url = {https://doi.org/10.1093/gigascience/giad014},
	doi = {10.1093/gigascience/giad014},
	abstract = {The life sciences are one of the biggest suppliers of scientific data. Reusing and connecting these data can uncover hidden insights and lead to new concepts. Efficient reuse of these datasets is strongly promoted when they are interlinked with a sufficient amount of machine-actionable metadata. While the FAIR (Findable, Accessible, Interoperable, Reusable) guiding principles have been accepted by all stakeholders, in practice, there are only a limited number of easy-to-adopt implementations available that fulfill the needs of data producers.We developed the FAIR Data Station, a lightweight application written in Java, that aims to support researchers in managing research metadata according to the FAIR principles. It implements the ISA metadata framework and uses minimal information metadata standards to capture experiment metadata. The FAIR Data Station consists of 3 modules. Based on the minimal information model(s) selected by the user, the “form generation module” creates a metadata template Excel workbook with a header row of machine-actionable attribute names. The Excel workbook is subsequently used by the data producer(s) as a familiar environment for sample metadata registration. At any point during this process, the format of the recorded values can be checked using the “validation module.” Finally, the “resource module” can be used to convert the set of metadata recorded in the Excel workbook in RDF format, enabling (cross-project) (meta)data searches and, for publishing of sequence data, in an European Nucleotide Archive–compatible XML metadata file.Turning FAIR into reality requires the availability of easy-to-adopt data FAIRification workflows that are also of direct use for data producers. As such, the FAIR Data Station provides, in addition to the means to correctly FAIRify (omics) data, the means to build searchable metadata databases of similar projects and can assist in ENA metadata submission of sequence data. The FAIR Data Station is available at https://fairbydesign.nl.},
	urldate = {2026-01-17},
	journal = {GigaScience},
	author = {Nijsse, Bart and Schaap, Peter J and Koehorst, Jasper J},
	month = jan,
	year = {2023},
	pages = {giad014},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/K4IHDBLR/Nijsse et al. - 2023 - FAIR data station for lightweight metadata management and validation of omics studies.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/D6K9JYDZ/giad014.html:text/html},
}

@misc{fernandez2020data,
	title = {The {Data} {Station}: {Combining} {Data}, {Compute}, and {Market} {Forces}},
	shorttitle = {The {Data} {Station}},
	url = {http://arxiv.org/abs/2009.00035},
	doi = {10.48550/arXiv.2009.00035},
	abstract = {This paper introduces Data Stations, a new data architecture that we are designing to tackle some of the most challenging data problems that we face today: access to sensitive data; data discovery and integration; and governance and compliance. Data Stations depart from modern data lakes in that both data and derived data products, such as machine learning models, are sealed and cannot be directly seen, accessed, or downloaded by anyone. Data Stations do not deliver data to users; instead, users bring questions to data. This inversion of the usual relationship between data and compute mitigates many of the security risks that are otherwise associated with sharing and working with sensitive data. Data Stations are designed following the principle that many data problems require human involvement, and that incentives are the key to obtaining such involvement. To that end, Data Stations implement market designs to create, manage, and coordinate the use of incentives. We explain the motivation for this new kind of platform and its design.},
	urldate = {2026-01-17},
	publisher = {arXiv},
	author = {Fernandez, Raul Castro and Chard, Kyle and Blaiszik, Ben and Krishnan, Sanjay and Elmore, Aaron and Obermeyer, Ziad and Risley, Josh and Mullainathan, Sendhil and Franklin, Michael and Foster, Ian},
	month = aug,
	year = {2020},
	note = {arXiv:2009.00035 [cs]},
	keywords = {Computer Science - Databases},
	file = {Preprint PDF:/Users/dkapitan/Zotero/storage/STUN2VA7/Fernandez et al. - 2020 - The Data Station Combining Data, Compute, and Market Forces.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/ECVM97IR/2009.html:text/html},
}

@inproceedings{castrofernandez2018aurum,
	address = {Paris},
	title = {Aurum: {A} {Data} {Discovery} {System}},
	isbn = {978-1-5386-5520-7},
	shorttitle = {Aurum},
	url = {https://ieeexplore.ieee.org/document/8509315/},
	doi = {10.1109/ICDE.2018.00094},
	abstract = {Organizations face a data discovery problem when their analysts spend more time looking for relevant data than analyzing it. This problem has become commonplace in modern organizations as: i) data is stored across multiple storage systems, from databases to data lakes, to the cloud; ii) data scientists do not operate within the limits of well-defined schemas or a small number of data sources—instead, to answer complex questions they must access data spread across thousands of data sources. To address this problem, we capture relationships between datasets in an enterprise knowledge graph (EKG), which helps users to navigate among disparate sources. The contribution of this paper is AURUM, a system to build, maintain and query the EKG. To build the EKG, we introduce a Two-step process which scales to large datasets and requires only one-pass over the data, avoiding overloading the source systems. To maintain the EKG without re-reading all data every time, we introduce a resource-efficient sampling signature (RESS) method which works by only using a small sample of the data. Finally, to query the EKG, we introduce a collection of composable primitives, thus allowing users to define many different types of discovery queries. We describe our experience using AURUM in three corporate scenarios and do a performance evaluation of each component.},
	language = {en},
	urldate = {2026-01-17},
	booktitle = {2018 {IEEE} 34th {International} {Conference} on {Data} {Engineering} ({ICDE})},
	publisher = {IEEE},
	author = {Castro Fernandez, Raul and Abedjan, Ziawasch and Koko, Famien and Yuan, Gina and Madden, Samuel and Stonebraker, Michael},
	month = apr,
	year = {2018},
	pages = {1001--1012},
	file = {PDF:/Users/dkapitan/Zotero/storage/LEMH27HZ/Castro Fernandez et al. - 2018 - Aurum A Data Discovery System.pdf:application/pdf},
}

@article{bakker2025approach,
	title = {An approach to making life sciences {FAIR}—{FAIR}-{DS} as a tool for {Aspergillus} fumigatus},
	volume = {2025},
	issn = {1758-0463},
	url = {https://doi.org/10.1093/database/baaf082},
	doi = {10.1093/database/baaf082},
	abstract = {Adhering to Findable, Accessible, Interoperable, and Reusable (FAIR) principles ensures that data is shared in ways that maximize reusability. However, not all researchers in biological fields, particularly those that rely on manual data entry, have embraced these principles, particularly when it comes to adhering to relevant ontologies. This hampers data sharing due to missing metadata, limiting reuse. This study addresses the production of FAIR data for mycology, a field characterized by high manual data entry demands. For this field, we propose specific data standards to enhance reusability in the Aspergillus fumigatus field and beyond, emphasizing their importance for fostering collaboration and accelerating scientific progress. We adopted the FAIR-Data Station (FAIR-DS) solution to this new domain and demonstrated how to improve the FAIRification of new types of complex life science datasets. For individual researchers, FAIR-DS simplifies data uploads to repositories while ensuring critical metadata is preserved. Following our approach, we have converted two types of datasets—spore counts and a compost monitoring programme on Dutch farms—into FAIR ontology-compliant formats and published them as open data.},
	urldate = {2026-01-17},
	journal = {Database},
	author = {Bakker, Sibbe and Santos-Silva, Mariana and Rhodes, Johanna and Schoustra, Sijmen and Zwaan, Bas and Fensel, Anna},
	month = jan,
	year = {2025},
	pages = {baaf082},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/927PIH4E/Bakker et al. - 2025 - An approach to making life sciences FAIR—FAIR-DS as a tool for Aspergillus fumigatus.pdf:application/pdf},
}

@article{wijnbergen2025fair,
	title = {The {FAIR} data point populator: collaborative {FAIRification} and population of {FAIR} data points},
	volume = {25},
	issn = {1472-6947},
	shorttitle = {The {FAIR} data point populator},
	url = {https://doi.org/10.1186/s12911-025-03022-7},
	doi = {10.1186/s12911-025-03022-7},
	abstract = {Use of the FAIR principles (Findable, Accessible, Interoperable and Reusable) allows the rapidly growing number of biomedical datasets to be optimally (re)used. An important aspect of the FAIR principles is metadata. The FAIR Data Point specifications and reference implementation have been designed as an example on how to publish metadata according to the FAIR principles. Metadata can be added to a FAIR Data Point with the FDP’s web interface or through its API. However, these methods are either limited in scalability or only usable by users with a background in programming. We aim to provide a new tool for populating FDPs with metadata that addresses these limitations with the FAIR Data Point Populator.},
	language = {en},
	number = {1},
	urldate = {2026-01-17},
	journal = {BMC Medical Informatics and Decision Making},
	author = {Wijnbergen, Daphne and Kaliyaperumal, Rajaram and Burger, Kees and Bonino da Silva Santos, Luiz Olavo and Mons, Barend and Roos, Marco and Mina, Eleni},
	month = jun,
	year = {2025},
	keywords = {FAIR, Data sharing, Metadata, Semantic web, RDF, FAIR data point},
	pages = {211},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/IL3HJWKC/Wijnbergen et al. - 2025 - The FAIR data point populator collaborative FAIRification and population of FAIR data points.pdf:application/pdf},
}

@misc{jacob2024maggot,
	title = {Maggot : {An} ecosystem for sharing metadata within the web of {FAIR} {Data}},
	copyright = {© 2024, Posted by Cold Spring Harbor Laboratory. This pre-print is available under a Creative Commons License (Attribution-NoDerivs 4.0 International), CC BY-ND 4.0, as described at http://creativecommons.org/licenses/by-nd/4.0/},
	shorttitle = {Maggot},
	url = {https://www.biorxiv.org/content/10.1101/2024.05.24.595703v1},
	doi = {10.1101/2024.05.24.595703},
	abstract = {Background Descriptive metadata are crucial for the discovery, reporting and mobilisation of research datasets. Addressing all metadata issues within the Data Management Plan often poses challenges for data producers. Organising and documenting data within data storage entails creating various descriptive metadata. Subsequently, data sharing involves ensuring metadata interoperability in alignment with FAIR principles. Given the tangible nature of these challenges, a real need for management tools has to be addressed to assist data managers to the fullest extent. Moreover, these tools have to meet data producers requirements and be user-friendly as well with minimal training as prerequisites.
Results We developed Maggot which stands for Metadata Aggregation on Data Storage, specifically designed to annotate datasets by generating metadata files to be linked into storage spaces. Maggot enables users to seamlessly generate and attach comprehensible metadata to datasets within a collaborative environment. This approach seamlessly integrates into a data management plan, effectively tackling challenges related to data organisation, documentation, storage, and frictionless FAIR metadata sharing within the collaborative group and beyond. Furthermore, for enabling metadata crosswalk, metadata generated with Maggot can be converted for a specific data repository or configured to be exported into a suitable format for data harvesting by third-party applications.
Conclusion The primary feature of Maggot is to ease metadata capture based on a carefully selected schema and standards. Then, it greatly eases access to data through metadata as requested nowadays in projects funded by public institutions and entities such as Europe Commission. Thus, Maggot can be used on one hand to promote good local versus global data management with open data sharing in mind while respecting FAIR principles, and on the other hand to prepare the future EOSC FAIR Web of Data within the framework of the European Open Science Cloud.},
	language = {en},
	urldate = {2026-01-17},
	publisher = {bioRxiv},
	author = {Jacob, Daniel and Ehrenmann, François and David, Romain and Tran, Joseph and Mirande-Ney, Cathleen and Chaumeil, Philippe},
	month = may,
	year = {2024},
	note = {Pages: 2024.05.24.595703
Section: New Results},
	file = {PDF:/Users/dkapitan/Zotero/storage/LCFE3Y57/Jacob et al. - 2024 - Maggot  An ecosystem for sharing metadata within the web of FAIR Data.pdf:application/pdf},
}

@article{aksenova2024current,
	title = {Current state of data stewardship tools in life science},
	volume = {7},
	issn = {2624-909X},
	url = {https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024.1428568/full},
	doi = {10.3389/fdata.2024.1428568},
	abstract = {In today's data-centric landscape, effective data stewardship is critical for facilitating scientific research and innovation. This article provides an overview of essential tools and frameworks for modern data stewardship practices. Over 300 tools were analyzed in this study based on their description in the literature. We are assessing their utility, relevance to data stewardship, and applicability within the life sciences domain.},
	language = {English},
	urldate = {2026-01-17},
	journal = {Frontiers in Big Data},
	publisher = {Frontiers},
	author = {Aksenova, Anna and Johny, Anoop and Adams, Tim and Gribbon, Phil and Jacobs, Marc and Hofmann-Apitius, Martin},
	month = sep,
	year = {2024},
	keywords = {data interoperability6, data sharing4, data stewardship tools1, FAIR2, literature review5, mapping7, research data repositories3},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/9T5X66LA/Aksenova et al. - 2024 - Current state of data stewardship tools in life science.pdf:application/pdf},
}

@article{bossenko2024interoperability,
	title = {Interoperability of health data using {FHIR} {Mapping} {Language}: transforming {HL7} {CDA} to {FHIR} with reusable visual components},
	volume = {6},
	issn = {2673-253X},
	shorttitle = {Interoperability of health data using {FHIR} {Mapping} {Language}},
	url = {https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2024.1480600/full},
	doi = {10.3389/fdgth.2024.1480600},
	abstract = {IntroductionEcosystem-centered healthcare innovations, such as digital health platforms, patient-centric records, and mobile health applications, depend on the semantic interoperability of health data. This ensures efficient, patient-focused healthcare delivery in a mobile world where citizens frequently travel for work and leisure. Beyond healthcare delivery, semantic interoperability is crucial for secondary health data use. This paper introduces a tool and techniques for achieving health data semantic interoperability, using reusable visual transformation components to create and validate transformation rules and maps, making them usable for domain experts with minimal technical skills.MethodsThe tool and techniques for health data semantic interoperability have been developed and validated using Design Science, a common methodology for developing software artifacts, including tools and techniques.ResultsOur tool and techniques are designed to facilitate the interoperability of Electronic Health Records (EHRs) by enabling the seamless unification of various health data formats in real time, without the need for extensive physical data migrations. These tools simplify complex health data transformations, allowing domain experts to specify and validate intricate data transformation rules and maps. The need for such a solution arises from the ongoing transition of the Estonian National Health Information System (ENHIS) from Clinical Document Architecture (CDA) to Fast Healthcare Interoperability Resources (FHIR), but it is general enough to be used for other data transformation needs, including the European Health Data Space (EHDS) ecosystem.ConclusionThe proposed tool and techniques simplify health data transformation by allowing domain experts to specify and validate the necessary data transformation rules and maps. Evaluation by ENHIS domain experts demonstrated the usability, effectiveness, and business value of the tool and techniques.},
	language = {English},
	urldate = {2026-01-20},
	journal = {Frontiers in Digital Health},
	publisher = {Frontiers},
	author = {Bossenko, Igor and Randmaa, Rainer and Piho, Gunnar and Ross, Peeter},
	month = dec,
	year = {2024},
	keywords = {data transformation, FHIR Mapping Language (FML), HL7 Clinical Document Architecture (CDA), HL7 Fast Healthcare Interoperability Resources (FHIR), semantic interoperability, TermX},
	file = {Full Text PDF:/Users/dkapitan/Zotero/storage/YUBSKFN6/Bossenko et al. - 2024 - Interoperability of health data using FHIR Mapping Language transforming HL7 CDA to FHIR with reusa.pdf:application/pdf},
}

@article{bezroukov1999open,
	title = {Open source software development as a special type of academic research: {Critique} of vulgar {Raymondism}},
	copyright = {Copyright (c)},
	issn = {1396-0466},
	shorttitle = {Open source software development as a special type of academic research},
	url = {https://firstmonday.org/ojs/index.php/fm/article/view/696},
	doi = {10.5210/fm.v4i10.696},
	abstract = {Eric Raymond's bazaar model provides a too simplistic view of the open source software (OSS) development process. This paper tries to explore links between open source software development and academic research as a better paradigm for OSS development. Open source software development should better be viewed as a special case of academic research. Viewing OSS this way probably can lead to a better understanding of open source phenomena.},
	language = {en},
	urldate = {2026-01-20},
	journal = {First Monday},
	author = {Bezroukov, Nikolai},
	month = oct,
	year = {1999},
}

@inproceedings{azevedo2020modern,
	address = {Prague, Czech Republic},
	title = {Modern {Federated} {Database} {Systems}: {An} {Overview}:},
	isbn = {978-989-758-423-7},
	shorttitle = {Modern {Federated} {Database} {Systems}},
	url = {http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0009795402760283},
	doi = {10.5220/0009795402760283},
	abstract = {Usually, modern applications manipulate datasets with diverse models, usages, and storages. “One size fits all” approaches are not sufficient for heterogeneous data, storages, and schemes. The rise of new kinds of data stores and processing, like NoSQL data stores, distributed file systems, and new data processing frameworks, brought new possibilities to meet this scenario’s requirements. However, semantic, schema and storage heterogeneity, autonomy, and distributed processing are still among the main concerns when building data-driven applications. This work surveys the literature aiming at giving an overview of the state of the art of modern federated database systems. It presents the background, characterizes existing tools, depicts guidelines one should follow when creating solutions, and points out research challenges to consider in future work. This work gives fundamentals for researchers and practitioners in the area.},
	language = {en},
	urldate = {2026-01-23},
	booktitle = {Proceedings of the 22nd {International} {Conference} on {Enterprise} {Information} {Systems}},
	publisher = {SCITEPRESS - Science and Technology Publications},
	author = {Azevedo, Leonardo and Soares, Elton and Souza, Renan and Moreno, Marcio},
	year = {2020},
	pages = {276--283},
	file = {PDF:/Users/dkapitan/Zotero/storage/ZJ9ICHSG/Azevedo et al. - 2020 - Modern Federated Database Systems An Overview.pdf:application/pdf},
}

@misc{elliot2018future,
	title = {The future of statistical disclosure control},
	url = {http://arxiv.org/abs/1812.09204},
	doi = {10.48550/arXiv.1812.09204},
	abstract = {Statistical disclosure control (SDC) was not created in a single seminal paper nor following the invention of a new mathematical technique, rather it developed slowly in response to the practical challenges faced by data practitioners based at national statistical institutes (NSIs). SDC's subsequent emergence as a specialised academic field was an outcome of three interrelated socio-technical changes: (i) the advent of accessible computing as a research tool in the 1980s meant that it became possible - and then increasingly easy - for researchers to process larger quantities of data automatically; this naturally increased demand for such data; (ii) it became possible for data holders to process and disseminate detailed data as digital files and (iii) the number of organisations holding data about individuals proliferated. This also meant the number of potential adversaries with the resources to attack any given dataset increased exponentially. In this article, we describe the state of the art for SDC and then discuss the core issues and future challenges. In particular, we touch on SDC and big data, on SDC and machine learning, and on SDC and anti-discrimination.},
	urldate = {2026-01-27},
	publisher = {arXiv},
	author = {Elliot, Mark and Domingo-Ferrer, Josep},
	month = dec,
	year = {2018},
	note = {arXiv:1812.09204 [cs]},
	keywords = {Computer Science - Cryptography and Security},
	file = {Preprint PDF:/Users/dkapitan/Zotero/storage/GYVU5XE6/Elliot and Domingo-Ferrer - 2018 - The future of statistical disclosure control.pdf:application/pdf;Snapshot:/Users/dkapitan/Zotero/storage/EA4HXCYD/1812.html:text/html},
}