Electrocardiograms (ECGs) are non-invasive diagnostic tools crucial for detecting cardiac arrhythmic diseases in clinical practice. While ECG Self-supervised Learning (eSSL) methods show promise in representation learning from unannotated ECG data, they often overlook the clinical knowledge that can be found in reports. This oversight and the requirement for annotated samples for downstream tasks limit eSSL's versatility. In this work, we address these issues with the Multimodal ECG Representation Learning (MERL}) framework. Through multimodal learning on ECG records and associated reports, MERL is capable of performing zero-shot ECG classification with text prompts, eliminating the need for training data in downstream tasks. At test time, we propose the Clinical Knowledge Enhanced Prompt Engineering (CKEPE) approach, which uses Large Language Models (LLMs) to exploit external expert-verified clinical knowledge databases, generating more descriptive prompts and reducing hallucinations in LLM-generated content to boost zero-shot classification. Based on MERL, we perform the first benchmark across six public ECG datasets, showing the superior performance of MERL compared against eSSL methods. Notably, MERL achieves an average AUC score of 75.2% in zero-shot classification (without training data), 3.2% higher than linear probed eSSL methods with 10\% annotated training data, averaged across all six datasets.

翻译：心电图（ECG）作为临床检测心律失常疾病的非侵入性诊断工具至关重要。现有心电图自监督学习方法虽能从未标注心电数据中学习表征，但常忽视报告中的临床知识，且下游任务需依赖标注样本，从而限制了其通用性。本研究提出多模态心电图表征学习框架（MERL），通过心电记录与关联报告的多模态学习，实现基于文本提示的零样本心电图分类，无需下游任务训练数据。在测试阶段，我们提出临床知识增强提示工程（CKEPE）方法，利用大语言模型（LLM）调用外部专家验证的临床知识库，生成更具描述性的提示，抑制LLM生成内容中的幻觉现象，提升零样本分类性能。基于MERL，我们首次在六个公开心电数据集上建立基准评估，结果显示MERL性能优于现有eSSL方法。值得关注的是，MERL在零样本分类（无训练数据）中平均AUC达75.2%，较使用10%标注训练数据的线性探测eSSL方法提升3.2%（六数据集均值）。