Reconstructing 12-lead ECG from 3-lead ECG using variational autoencoder to improve cardiac disease detection of wearable ECG devices
PLOS Digital Health · 22.05.2026 · 5 (5) · e0001335
DOI: 10.1371/journal.pdig.0001335 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 22.05.2026. Verfasst von Xinyan Guan und 11 weiteren Autor:innen. Beteiligte Einrichtung: National Institute of Health Data Science, Peking University, Beijing, China. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, CCF-Tencent Rhino-Bird Open Research Fund, CCF-Zhipu Large Model Innovation Fund.
Abstract (Originalsprache)
Twelve-lead electrocardiograms (ECGs) are the clinical gold standard for cardiac diagnosis, offering comprehensive spatial coverage of the heart necessary for detecting conditions such as myocardial infarction (MI). However, their lack of portability limits continuous and large-scale deployment. In contrast, three-lead ECG systems are widely used in wearable devices due to their simplicity and mobility, but they often fail to capture pathologies localized in unmeasured regions. To bridge this gap, we propose WearECG, a Variational Autoencoder (VAE) method that reconstructs 12-lead ECGs from three leads (II, V1, V5). Our model includes architectural improvements to better capture temporal and spatial dependencies in ECG signals. We evaluate generation quality using MSE, MAE, and Fréchet Inception Distance (FID), and assess clinical validity via a Turing test with expert cardiologists. To further validate the diagnostic utility, we fine-tune ECGFounder—a large-scale pretrained ECG model—on a multi-label classification task involving over 40 cardiac conditions, including 6 different myocardial infarction locations using both real and generated signals. Experiments on the MIMIC and PTB-XL datasets show that our method produces physiologically realistic and diagnostically informative signals, with robust performance in downstream tasks. This work demonstrates the potential of generative modeling for ECG reconstruction and its implications for scalable, low-cost cardiac screening.
Autor:innen und Institutionen
- National Institute of Health Data Science, Peking University, Beijing, China.
- University of Chinese Academy of Sciences, Beijing, China.
- State Key Laboratory of General Artificial Intelligence, Beijing, China.
- School of Intelligence Science and Technology, Peking University, Beijing, China.
- Department of Cardiology, Peking University People's Hospital, Beijing, China.
- HeartVoice Medical Technology, Hefei, China.
ORCID-Profile: Deyun Zhang, Shenda Hong
Förderung
- National Natural Science Foundation of China
- CCF-Tencent Rhino-Bird Open Research Fund
- CCF-Zhipu Large Model Innovation Fund
- PKU-OPPO Fund
- Research Project of Peking University in the State Key Laboratory of Vascular Homeostasis and Remodeling
Zitieren
APA
Guan, X., Wang, H., Lai, Y., Jin, J., Li, J., Zhao, Q., Zhang, D., Geng, S., Mu, G., Wang, Y., Wu, R., & Hong, S. (2026). Reconstructing 12-lead ECG from 3-lead ECG using variational autoencoder to improve cardiac disease detection of wearable ECG devices. PLOS Digital Health, 5(5), e0001335. https://doi.org/10.1371/journal.pdig.0001335
Vancouver
Guan X, Wang H, Lai Y, Jin J, Li J, Zhao Q, et al. Reconstructing 12-lead ECG from 3-lead ECG using variational autoencoder to improve cardiac disease detection of wearable ECG devices. PLOS Digital Health. 2026;5(5):e0001335. doi:10.1371/journal.pdig.0001335
BibTeX
@article{Guan2026,
author = {Guan, Xinyan and Wang, Haoyu and Lai, Yongfan and Jin, Jiarui and Li, Jun and Zhao, Qinghao and Zhang, Deyun and Geng, Shijia and Mu, Guanyu and Wang, Yiping and Wu, Rui and Hong, Shenda},
title = {Reconstructing 12-lead ECG from 3-lead ECG using variational autoencoder to improve cardiac disease detection of wearable ECG devices},
journal = {PLOS Digital Health},
year = {2026},
volume = {5},
number = {5},
pages = {e0001335},
doi = {10.1371/journal.pdig.0001335}
}
EUVIMED