arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2603.04589cs.AI

ECG-MoE:混合专家心电图基础模型

ECG-MoE: Mixture-of-Expert Electrocardiogram Foundation Model

Department of Computer Science(计算机科学系);Emory University(埃默里大学);School of Computer Science(计算机科学学院);University of Oklahoma(俄克拉荷马大学);Center of Data Science(数据科学中心)

Yuhao Xu, Xiaoda Wang, Yi Wu, Wei Jin, Xiao Hu, Carl Yang

AI总结:

ECG-MoE通过混合专家架构融合多模型时间特征与心脏周期感知模块,实现高效心电图分析,在多个临床任务中取得最佳性能。

摘要:

心电图(ECG)分析对心脏诊断至关重要,但现有基础模型往往难以捕捉用于各种临床任务所需的周期性和多样的特征。我们提出了ECG-MoE,一种融合多模型时间特征与心脏周期感知专家模块的混合架构。我们的方法采用双路径混合专家模型,分别建模心搏水平形态和节律,并结合使用LoRA的分层融合网络实现高效推理。在五个公开临床任务上评估,ECG-MoE实现了最先进的性能,推理速度比多任务基线快40%。

英文摘要:

Electrocardiography (ECG) analysis is crucial for cardiac diagnosis, yet existing foundation models often fail to capture the periodicity and diverse features required for varied clinical tasks. We propose ECG-MoE, a hybrid architecture that integrates multi-model temporal features with a cardiac period-aware expert module. Our approach uses a dual-path Mixture-of-Experts to separately model beat-level morphology and rhythm, combined with a hierarchical fusion network using LoRA for efficient inference. Evaluated on five public clinical tasks, ECG-MoE achieves state-of-the-art performance with 40% faster inference than multi-task baselines.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑