让心电图在噪声或缺导联时仍能准确诊断
TolerantECG: A Foundation Model for Imperfect Electrocardiogram
- 用对比学习与自监督方法训练，同时学信号和报告描述
- 在PTB-XL和MIT-BIH数据集上均表现最优或第二好
- 适合临床中信号质量差或导联不全的场景使用
心电图是诊断心脏病的重要工具，但噪声或标准12导联中部分导联缺失会降低其准确性，导致误诊或不确定性。为应对这些挑战，我们提出TolerantECG，一种对噪声鲁棒且能处理任意12导联子集的心电图基础模型。该模型通过结合对比学习与自监督学习框架，联合学习心电图信号表征、对应的知识检索文本报告及受损或缺导联信号。在PTB-XL数据集上，TolerantECG在多种信号条件和分类层级下始终位列最佳或第二佳；在MIT-BIH心律失常数据库上表现最优。
原文摘要 · Abstract (English)
The electrocardiogram (ECG) is an essential and effective tool for diagnosing heart diseases. However, its effectiveness can be compromised by noise or unavailability of one or more leads of the standard 12-lead recordings, resulting in diagnostic errors or uncertainty. To address these challenges, we propose TolerantECG, a foundation model for ECG signals that is robust to noise and capable of functioning with arbitrary subsets of the standard 12-lead ECG. TolerantECG training combines contrastive and self-supervised learning frameworks to jointly learn ECG signal representations alongside their corresponding knowledge-retrieval-based text report descriptions and corrupted or lead-missing signals. Comprehensive benchmarking results demonstrate that TolerantECG consistently ranks as the best or second-best performer across various ECG signal conditions and class levels in the PTB-XL dataset, and achieves the highest performance on the MIT-BIH Arrhythmia Database.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。