added dataset details

docs/source/background.rst

@@ -0,0 +1,5 @@
+.. _background:
+
+Clinical Background
+===================
+

docs/source/datasets.rst

@@ -12,15 +12,64 @@ In addition, bespoke datasets can be analysed by creating a bespoke `dataset_cur
 MUSIC
 -----
 
-The `MUSIC (Sudden Cardiac Death in Chronic Heart Failure) <https://doi.org/10.13026/fa8p-he52>`_ dataset contains data from chronic heart failure patients attending heart failure clinics, including 24-hour Holter ECG recordings, additional clinical measurements such as LVEF, and long-term outcomes.
+The `MUSIC (Sudden Cardiac Death in Chronic Heart Failure) dataset <https://doi.org/10.13026/fa8p-he52>`_ contains data from chronic heart failure patients attending heart failure clinics, including 24-hour Holter ECG recordings, additional clinical measurements such as left-ventricular ejection fraction (LVEF), and long-term outcomes. The original publication describing the dataset is `Martin et al. <https://www.cinc.org/archives/2024/pdf/CinC2024-355.pdf>`_.
 
+Participant Characteristics
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Considering those patients with Holter ECG data available, the following table shows the numbers of patients found to meet various criteria:
+
+.. list-table:: The number of MUSIC patients with Holter ECG data available who met certain criteria. Bold indicates >= 100 per group.
+   :widths: 20 40 40
+   :header-rows: 1
+
+   * - Outcome
+     - No. with ECG available
+     - No. with prior MI and ECG available
+   * - Any
+     - 936
+     - 397
+   * - Any-cause Death: Yes, No
+     - **253, 683**
+     - **141, 256**
+   * - Sudden cardiac death: Yes, survived
+     - 88, 683
+     - 53, 256
+   * - Pump-failure death: Yes, survived
+     - **108, 683**
+     - 58, 256
+   * - Non-cardiac death: Yes, survived
+     - 57, 683
+     - 30, 256
 
 .. _mc-med-dataset:
 
 MC-MED
 ------
 
-The `MC-MED (Multimodal Clinical Monitoring in the Emergency Department) <https://doi.org/10.13026/jz99-4j81>`_ dataset contains data collected in the emergency department, including ECG signals, and short-term outcomes.
+The `MC-MED (Multimodal Clinical Monitoring in the Emergency Department) dataset <https://doi.org/10.13026/jz99-4j81>`_ contains physiological signals from patients soon after arrival at the Emergency Department (ED), alongside short-term health outcomes. The original publication describing the dataset is `Kansal et al. <https://doi.org/10.1038/s41597-025-05419-5>`_.
+
+Participant Characteristics
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The entire dataset contains data from 118,385 ED visits by 70,545 patients. According to our analysis, physiological signals were recorded in 83,590 visits by 53,109 patients.
+
+Considering for instance those patients who had a primary diagnosis of a myocardial infarction (an MI), the following table shows the numbers of patients found to meet various criteria:
 
+.. list-table:: The number of MC-MED patients with a primary diagnosis of MI and ECG signals available who met certain criteria. Bold indicates >= 100 per group. NB: Some patients appear in multiple groups due to multiple visits.
+   :widths: 20 80
+   :header-rows: 1
 
+   * - Outcome
+     - No. patients with MI diagnosis and ECG signal available
+   * - Any (all were admitted)
+     - **542**
+   * - Any-cause Death in Hospital: Yes, No
+     - 11, 531
+   * - Any-cause Rehospitalisation: Yes, No
+     - **214, 352**
+   * - CV Rehospitalisation: Yes, No
+     - 88, 484
+   * - Cardiac Rehospitalisation: Yes, No
+     - 81, 491
 

docs/source/index.rst

@@ -61,6 +61,7 @@ Further details of this example are provided in the :ref:`Running demo analysis
    :caption: Contents:
 
    overview
+   background
    datasets
    examples
    variables

docs/source/overview.rst

@@ -28,3 +28,18 @@ The **Longitudinal ECG Analysis** package performs the following steps:
 #. :ref:`Derive signal features <deriving-signal-features>`: *derive features from ECG signals*
 #. :ref:`Compile for stats <compiling-for-stats>`: *compile features ready for statistical analysis*
 #. :ref:`Perform statistical analysis <statistical_analysis>`: *investigate the associations between features and health outcomes*
+
+.. _methods:
+
+Methods
+-------
+
+The toolbox builds on previous research to provide a robust pipeline for investigating associations between ECG features and health outcomes.
+
+First, the toolbox is designed to be compatible with the Heart Hospital dataset, as well as two relevant publicly available datasets: the MUSIC and MC-MED datasets (described :ref:`here <datasets>`). This enables investigations in different patient populations, different clinical scenarios, and short- and long-term health outcomes. Furthermore, it enables possible future extension into multimodal approaches for risk assessment, since the MC-MED dataset contains not only ECG signals, but other physiological signals too.
+
+Second, the toolbox utilises the NeuroKit toolbox to extract features from ECG signals. NeuroKit is perhaps the most widely used open-source toolbox for physiological signal processing. Using NeuroKit not only enables the extraction of many ECG features, but also future-proofs the toolbox by enabling integration with future ECG features which may be implemented in NeuroKit.
+
+Third, the toolbox utilises statistical analysis techniques previously presented in the literature. The statistical analysis was based primarily on that used in `Ramirez et al. <https://doi.org/10.1371/journal.pone.0186152>`_ . This design choice was made for two reasons: the analysis presented in Ramirez et al. was robust, and this enables direct comparison of results between those provided by the toolbox and those reported in the literature (since Ramirez et al. analysed the MUSIC dataset).
+
+Fourth, the toolbox extracts not only ECG features, but also risk markers currently used in clinical practice. This enables the direct comparison of the performance of ECG features to the methods available in current practice. This is particularly valuable for evaluating the potential utility of ECG features.

docs/source/use.rst

@@ -5,6 +5,6 @@ Use in Publications
 
 The toolbox has been used in the following work:
 
-Shu Y, Charlton PH, Kawsar F, Hernesniemi J, and Malekzadeh M, `CLEF: Clinically-Guided Contrastive Learning for Electrocardiogram Foundation Models <https://doi.org/10.48550/arXiv.2512.02180>`. arXiv preprint arXiv:2512.02180. 2025.
+Shu Y, Charlton PH, Kawsar F, Hernesniemi J, and Malekzadeh M, `CLEF: Clinically-Guided Contrastive Learning for Electrocardiogram Foundation Models <https://doi.org/10.48550/arXiv.2512.02180>`_. arXiv preprint arXiv:2512.02180. 2025.
 
 See the related toolbox also used in this work: `ecg-foundation-model <https://github.com/Nokia-Bell-Labs/ecg-foundation-model>`_