Search:
Match:
1 results

ECG Representation Learning with Cardiac Conduction Focus

Published:Dec 30, 2025 05:46
1 min read
ArXiv

Analysis

This paper addresses limitations in existing ECG self-supervised learning (eSSL) methods by focusing on cardiac conduction processes and aligning with ECG diagnostic guidelines. It proposes a two-stage framework, CLEAR-HUG, to capture subtle variations in cardiac conduction across leads, improving performance on downstream tasks.
Reference

Experimental results across six tasks show a 6.84% improvement, validating the effectiveness of CLEAR-HUG.