Saved in:
Bibliographic Details
Main Authors: Han, Yu, Murino, Vittorio, Liu, Xiaofeng, Zhang, Xiang, Ding, Cheng
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.19877
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915547186200576
author Han, Yu
Murino, Vittorio
Liu, Xiaofeng
Zhang, Xiang
Ding, Cheng
author_facet Han, Yu
Murino, Vittorio
Liu, Xiaofeng
Zhang, Xiang
Ding, Cheng
contents Electrocardiogram (ECG) is widely used in healthcare applications, such as arrhythmia detection and sleep monitoring, making accurate ECG analysis critically essential. Traditional deep learning models for ECG are task-specific, with limited generalization and narrow functionality. Foundation models (FMs), or large pre-training models, have recently advanced representation learning, enabling strong performance across diverse tasks and motivating their adoption for ECG analysis. Here, we present the first comprehensive review dedicated to ECG foundation models (ECG-FMs). We map the current landscape of architectures, pre-training paradigms, and adaptation strategies, and critically examine their strengths, limitations, and clinical potential. By consolidating this emerging field, we aim to accelerate the development of robust, generalizable ECG-FMs and chart future directions for their integration into healthcare practice.
format Preprint
id arxiv_https___arxiv_org_abs_2410_19877
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Systematic Review on Foundation Models for Electrocardiogram Analysis: Initial Strides and Expansive Horizons
Han, Yu
Murino, Vittorio
Liu, Xiaofeng
Zhang, Xiang
Ding, Cheng
Signal Processing
Electrocardiogram (ECG) is widely used in healthcare applications, such as arrhythmia detection and sleep monitoring, making accurate ECG analysis critically essential. Traditional deep learning models for ECG are task-specific, with limited generalization and narrow functionality. Foundation models (FMs), or large pre-training models, have recently advanced representation learning, enabling strong performance across diverse tasks and motivating their adoption for ECG analysis. Here, we present the first comprehensive review dedicated to ECG foundation models (ECG-FMs). We map the current landscape of architectures, pre-training paradigms, and adaptation strategies, and critically examine their strengths, limitations, and clinical potential. By consolidating this emerging field, we aim to accelerate the development of robust, generalizable ECG-FMs and chart future directions for their integration into healthcare practice.
title A Systematic Review on Foundation Models for Electrocardiogram Analysis: Initial Strides and Expansive Horizons
topic Signal Processing
url https://arxiv.org/abs/2410.19877