Journal article icon

Journal article

Cardiac health assessment across scenarios and devices using a multimodal foundation model pretrained on data from 1.7 million individuals

Abstract:

Cardiovascular diseases remain a major contributor to the global burden of healthcare, highlighting the importance of accurate and scalable methods for cardiac monitoring. Cardiac biosignals, most notably electrocardiograms (ECG) and photoplethysmograms (PPG), are essential for diagnosing, preventing, and managing cardiovascular conditions across clinical and home settings. However, their acquisition varies substantially across scenarios and devices, while existing analytical models often rely on homogeneous datasets and static bespoke models, limiting their robustness and generalizability in diverse real-world contexts. In this study, we present a cardiac sensing foundation model (CSFM) that leverages transformer architectures and a generative masked pretraining strategy to learn unified representations from heterogeneous health records. CSFM is pretrained on a multimodal integration of data from various large-scale datasets, comprising cardiac signals from approximately 1.7 million individuals and their corresponding clinical or machine-generated text reports. The embeddings derived from CSFM act as effective, transferable features across diverse cardiac sensing scenarios, supporting seamless adaptation to varied input configurations and sensor modalities. Extensive evaluations across diagnostic tasks, demographic recognition, vital sign measurement, clinical outcome prediction, and ECG question answering demonstrate that CSFM consistently outperforms traditional one-modal-one-task approaches. Notably, CSFM maintains favorable performance across both 12-lead and single-lead ECGs, as well as in scenarios involving ECG only, PPG only, or a combination of both. This highlights its potential as a versatile and scalable foundation for comprehensive cardiac monitoring.

Publication status:
Published
Peer review status:
Peer reviewed

Actions

Access Document

Files:
Publisher copy:
10.1038/s42256-026-01180-5

Authors

More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author


Publisher:
Springer Nature
Journal:
Nature Machine Intelligence More from this journal
Volume:
8
Issue:
2
Pages:
220-233
Publication date:
2026-02-24
Acceptance date:
2026-01-08
DOI:
EISSN:
2522-5839


Language:
English
Keywords:
Pubs id:
2358117
Local pid:
pubs:2358117
Deposit date:
2026-01-13
ARK identifier:

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP