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:
-
-
(Preview, Version of record, pdf, 4.2MB, Terms of use)
-
- Publisher copy:
- 10.1038/s42256-026-01180-5
Authors
- 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
- Copyright holder:
- Gu et al.
- Copyright date:
- 2026
- Rights statement:
- Copyright © 2026, The Author(s). This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
- Licence:
- CC Attribution (CC BY)
If you are the owner of this record, you can report an update to it here: Report update to this record