用大模型生成标注，让心电图模型零样本识别106种心脏病。
SuPreME: A Supervised Pre-training Framework for Multimodal ECG Representation Learning
- 用大模型从报告中提取结构化诊断标签，统一标准术语。
- 零样本分类AUC达77.20%，比现有方法高4.98%。
- 适合医疗AI研究者和需要少标注训练的临床场景。
心血管疾病是全球致死致残的主要原因。心电图（ECG）对心脏健康诊断与监测至关重要，但大规模标注的ECG数据集获取成本高。现有无监督预训练方法虽减少标签依赖，却难以捕捉精细临床语义，且需大量微调。为此，我们提出SuPreME：一种基于结构化诊断标签的多模态心电图表示学习监督预训练框架。通过一次离线处理，利用大语言模型（LLMs）从心电图报告中提取并清洗、标准化心脏概念，构建高质量标签。该框架融合心电信号与文本查询，实现无需微调的零样本分类。在覆盖106种心脏疾病的六个下游数据集上，其零样本AUC达77.20%，显著优于当前最优的eSSL方法（提升4.98%）。结果证明，结合结构化临床知识可有效提升心电图表征质量。
原文摘要 · Abstract (English)
Cardiovascular diseases are a leading cause of death and disability worldwide. Electrocardiogram (ECG) is critical for diagnosing and monitoring cardiac health, but obtaining large-scale annotated ECG datasets is labor-intensive and time-consuming. Recent ECG Self-Supervised Learning (eSSL) methods mitigate this by learning features without extensive labels but fail to capture fine-grained clinical semantics and require extensive task-specific fine-tuning. To address these challenges, we propose $\textbf{SuPreME}$, a $\textbf{Su}$pervised $\textbf{Pre}$-training framework for $\textbf{M}$ultimodal $\textbf{E}$CG representation learning. SuPreME is pre-trained using structured diagnostic labels derived from ECG report entities through a one-time offline extraction with Large Language Models (LLMs), which help denoise, standardize cardiac concepts, and improve clinical representation learning. By fusing ECG signals with textual cardiac queries instead of fixed labels, SuPreME enables zero-shot classification of unseen conditions without further fine-tuning. We evaluate SuPreME on six downstream datasets covering 106 cardiac conditions, achieving superior zero-shot AUC performance of $77.20\%$, surpassing state-of-the-art eSSLs by $4.98\%$. Results demonstrate SuPreME's effectiveness in leveraging structured, clinically relevant knowledge for high-quality ECG representations.
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。