12-Lead ECG Generation via a PDE-Based GAN

Yakir Yehuda, Kira Radinsky

Keywords: 12-Lead ECG Classification, Generative Models, Clinical Multivariate Time Series, Partial Differential Equations

Abstract: Synthesizing realistic 12-lead electrocardiogram (ECG) data is a complex task due to the intricate spatial and temporal dynamics of cardiac electrophysiology. Traditional generative models often struggle to capture the nuanced interdependencies among ECG leads, which are essential for accurate medical analysis. In this paper, we introduce a novel method that integrates partial differential equations (PDEs) into a generative adversarial network (GAN) framework to model the spatiotemporal behavior of the heart's electrical activity. By embedding PDE-based representations directly into the generative process, our approach effectively captures both the temporal evolution and spatial relationships between ECG leads. This results in the production of high-fidelity synthetic 12-lead ECG data that closely mirrors real physiological signals. We conduct extensive experiments to evaluate the efficacy of our PDECGAN model, demonstrating that classifiers trained on our synthetic data outperform those trained on data generated by conventional methods in detecting cardiac abnormalities, with statistically significant improvements. Our work highlights the potential of combining PDE-driven cardiac models with advanced generative techniques to enhance the quality and utility of synthetic biomedical datasets.

Primary Area: other topics in machine learning (i.e., none of the above)

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 9709