心电图大语言模型：基于心电图的心脏推理基础模型

中文摘要 AI 辅助

心电图（ECG）是一种用于心脏症状的低成本标准护理测试，但一线分诊往往无法立即获得诸如超声心动图（ECHO）或心脏磁共振（CMR）等确定性成像。此外，大多数现有心电图人工智能系统仅限于固定诊断标签或自动报告，限制了其在特定患者临床推理中的应用。为填补这一空白，我们引入了ECG-LLM，这是一个跨四个队列训练的心电图条件大语言模型，包含来自186409名患者的679112份心电图研究。使用一种新颖的多模态到语言监督策略，ECG-LLM在从心电图信号、临床背景、CMR和ECHO导出的临床结构化问答对上进行训练。这种统一方法使模型能够仅从12导联心电图回答各种心血管问题，涵盖传统解释和标准心电图上不可直接见的表型。ECG-LLM成功恢复了传统心电图测量值，如心率，并强烈预测了复杂的CMR衍生表型，包括心室和心房容积以及心室功能。至关重要的是，它检测到了重要的超声心动图表型，包括左心室壁厚度增加、主动脉狭窄和右心室收缩功能障碍。在标准心电图理解任务上，ECG-LLM在诊断报告生成和心电图问答基准方面与现有基线匹配或超越。通过超越固定标签预测，这个多模态框架提供了具有临床价值的、问题驱动的心血管推理，以在专科医生审查延迟时支持全科医生和一线分诊决策。

英文摘要

Electrocardiography (ECG) is an inexpensive, standard-of-care test for cardiac symptoms, but front-line triage often lacks immediate access to definitive imaging such as echocardiography (ECHO) or cardiac magnetic resonance (CMR). Furthermore, most existing ECGAI systems are limited to fixed diagnostic labels or automated reports, constraining their use for patient-specific clinical reasoning. To address this gap, we introduce ECG-LLM, an ECG-conditioned large language model trained across four cohorts comprising 679,112 ECG studies from 186,409 patients. Using a novel multimodal-to-language supervision strategy, ECG-LLM is trained on clinically structured question-answer pairs derived from ECG signals, clinical context, CMR, and ECHO. This unified approach enables the model to answer diverse cardiovascular questions from a 12-lead ECG alone, spanning both conventional interpretation and phenotypes not directly visible on standard ECGs. ECG-LLM successfully recovers conventional ECG measurements, such as heart rate, and strongly predicts complex CMR-derived phenotypes, including ventricular and atrial volumes and ventricular function. Crucially, it detects vital echocardiographic phenotypes, including increased LV wall thickness, aortic stenosis, and right-ventricular systolic dysfunction. On standard ECG understanding tasks, ECG-LLM matches or exceeds existing baselines for diagnostic report generation and the ECG-QA benchmark. By moving beyond fixed-label prediction, this multimodal framework provides clinically valuable, question-driven cardiovascular reasoning to support general practitioner and front-line triage decisions when specialist review is delayed.

发表机构

• Technical University of Munich (TUM)（慕尼黑工业大学）
• TUM University Hospital（慕尼黑工业大学附属医院）
• Imperial College London（帝国理工学院）
• Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）

机构由 AI 辅助整理，请以论文原文为准。