Key result
Open ECG and PPG foundation models offer data efficiency but lack prospective workflow-integrated validation.
Why the study?
Foundation models offer promising approaches for ECG and PPG analysis across tasks, but challenges remain regarding homogeneous pretraining datasets and a lack of standardized evaluation frameworks.
This review highlights the potential of open foundation models to improve data efficiency and generalizability in ECG and PPG analysis, while identifying key translational gaps such as the need for standardized evaluation and prospective clinical validation.
Foundation models may improve ECG/PPG data efficiency; leaves open standardized evaluation and diverse pretraining datasets before clinical use.
Foundation models (FMs) offer a promising approach for electrocardiography (ECG) and photoplethysmography (PPG) analysis, enabling reusable representations across tasks without large labeled datasets or task-specific training. We review open ECG/PPG FMs and datasets, outlining cardiovascular applications. Advantages include data efficiency and generalizability, though challenges remain, particularly reliance on homogeneous pretraining datasets and the absence of standardized evaluation frameworks. This review guides clinicians in understanding and applying FMs in cardiovascular research.
No takes yet. Share an insight, caveat, or question.
Han et al. (2026) conducted a review in Cardiovascular disease. Foundation models for ECG and PPG was evaluated. Open foundation models for ECG and PPG waveforms offer data efficiency and generalizability for cardiovascular applications, though they currently lack prospective, workflow-integrated validation.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: