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. Code and models are available at https://github.com/cheliu-computation/MERL

翻译：心电图（ECG）是临床实践中用于检测心律失常疾病的关键无创诊断工具。尽管心电图自监督学习（eSSL）方法在从未标注的心电图数据中学习表征方面展现出潜力，但它们往往忽略了报告中蕴含的临床知识。这一疏忽以及对下游任务需要标注样本的要求，限制了eSSL的通用性。在本研究中，我们通过多模态心电图表征学习（MERL）框架来解决这些问题。通过对心电图记录及相关报告进行多模态学习，MERL能够基于文本提示执行零样本心电图分类，从而无需下游任务的训练数据。在测试阶段，我们提出了临床知识增强提示工程（CKEPE）方法，该方法利用大型语言模型（LLMs）挖掘外部专家验证的临床知识数据库，生成更具描述性的提示，并减少LLM生成内容中的幻觉，从而提升零样本分类性能。基于MERL，我们在六个公开心电图数据集上进行了首次基准测试，结果表明MERL相比eSSL方法具有优越性能。值得注意的是，MERL在零样本分类（无需训练数据）中平均AUC得分达到75.2%，比使用10%标注训练数据的线性探测eSSL方法平均高出3.2%（所有六个数据集的平均值）。代码与模型可在https://github.com/cheliu-computation/MERL获取。