Longitudinal ECG Analysis: Predicting Health Outcomes from Wearable Data

The Longitudinal ECG Analysis toolbox is designed to investigate associations between ECG features and future health outcomes. It provides a processing pipeline to curate longitudinal ECG datasets (e.g. Holter ECG datasets), extract features from ECG signals, and then perform statistical analyses to identify significant associations between ECG features and health outcomes.

The documentation is available here.

Use of the toolbox

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'. arXiv preprint arXiv:2512.02180. 2025. DOI: 10.48550/arXiv.2512.02180.

See the related toolbox used in this work: ecg-foundation-model.