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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Yue, Cao, Xu, Hu, Yaojun, Ying, Haochao, Xu, Hongxia, Wu, Ruijia, Rehg, James Matthew, Sun, Jimeng, Wu, Jian, Chen, Jintai
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929739484102656
author Wang, Yue
Cao, Xu
Hu, Yaojun
Ying, Haochao
Xu, Hongxia
Wu, Ruijia
Rehg, James Matthew
Sun, Jimeng
Wu, Jian
Chen, Jintai
author_facet Wang, Yue
Cao, Xu
Hu, Yaojun
Ying, Haochao
Xu, Hongxia
Wu, Ruijia
Rehg, James Matthew
Sun, Jimeng
Wu, Jian
Chen, Jintai
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17711
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AnyECG: Foundational Models for Multitask Cardiac Analysis in Real-World Settings
Wang, Yue
Cao, Xu
Hu, Yaojun
Ying, Haochao
Xu, Hongxia
Wu, Ruijia
Rehg, James Matthew
Sun, Jimeng
Wu, Jian
Chen, Jintai
Signal Processing
Artificial Intelligence
Machine Learning
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.
title AnyECG: Foundational Models for Multitask Cardiac Analysis in Real-World Settings
topic Signal Processing
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2411.17711