AnyECG: Foundational Models for Multitask Cardiac Analysis in Real-World Settings

作     者：Wang, Yue Cao, Xu Hu, Yaojun Ying, Haochao Xu, Hongxia Wu, Ruijia Rehg, James Matthew Sun, Jimeng Wu, Jian Chen, Jintai 

作者机构：The College of Computer Science and Technology Zhejiang University Hangzhou310012 China State Key Laboratory of Transvascular Implantation Devices The Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou310009 China Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence Hangzhou310058 China Department of Computer Science University of Illinois at Urbana-Champaign UrbanaIL United States Antai College of Economics and Management Shanghai Jiao Tong University Shanghai China School of Computer Science University of Illinois at Urbana-Champaign UrbanaIL United States  Guangzhou511458 China University of Illinois at Urbana-Champaign UrbanaIL United States The School of Public Health Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou310058 China 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2024年

核心收录：

主　　题：Heart 

摘      要：Electrocardiogram (ECG), a non-invasive and affordable tool for cardiac monitoring, is highly sensitive in detecting acute heart attacks. However, due to the lengthy nature of ECG recordings, numerous machine learning methods have been developed for automated heart disease detection to reduce human workload. Despite these efforts, performance remains suboptimal. A key obstacle is the inherent complexity of ECG data, which includes heterogeneity (e.g., varying sampling rates), high levels of noise, demographic-related pattern shifts, and intricate rhythm-event associations. To overcome these challenges, this paper introduces AnyECG, a foundational model designed to extract robust representations from any real-world ECG data. Specifically, a tailored ECG Tokenizer encodes each fixed-duration ECG fragment into a token and, guided by proxy tasks, converts noisy, continuous ECG features into discrete, compact, and clinically meaningful local rhythm codes. These codes encapsulate basic morphological, frequency, and demographic information (e.g., sex), effectively mitigating signal noise. We further pre-train the AnyECG to learn rhythmic pattern associations across ECG tokens, enabling the capture of cardiac event semantics. By being jointly pre-trained on diverse ECG data sources, AnyECG is capable of generalizing across a wide range of downstream tasks where ECG signals are recorded from various devices and scenarios. The experimental results show that AnyECG achieves an average performance improvement of 6% across four critical tasks—anomaly detection, arrhythmia classification, corrupted lead generation, and ultra-long ECG recognition. AnyECG learns common ECG rhythm from data and significantly outperforms state-of-the-art methods in each of these tasks. Copyright © 2024, The Authors. All rights reserved.