构建首个用于长期心电图分析的多模态基准，填补医疗大模型在动态信号理解上的空白。
Holtercare-Bench: A Multimodal Benchmark for Evaluating Long-Term Dynamic ECG Analysis
- 构建包含2.3万组问答的多模态心电数据集，融合信号、视频与文本三模态对齐
- 零样本测试显示主流大模型在超长病理序列处理上性能显著不足
- 适合关注长期生理信号分析、医学大模型评估的研究者使用
尽管多模态大语言模型（MLLMs）在医疗领域表现优异，但多数模型更擅长静态图像或短时信号。在动态心电图（ECG）这一关键领域，由于缺乏高质量数据集和评测基准，现有模型在复杂时间推理与诊断报告生成方面仍存在明显瓶颈。为此，我们提出（i）Holtercare-23K，一个大规模多模态动态心电数据集，包含从788份临床动态心电记录中提取的22,980组问答对，并引入新颖的信号-视频-文本三模态对齐机制。基于该数据集，我们构建（ii）Holtercare-Bench，一个涵盖时间定位、临床诊断与全局摘要的多模态评测基准。对领先MLLMs的零样本评估揭示其在处理超长病理序列时存在显著性能差距；而通过微调代表性模型则可带来显著提升。本工作揭示了当前MLLMs在心电生理学应用中的局限性，并为长期医疗多模态模型提供了基础评测基准。项目代码已开源：https://github.com/ZJU4HealthCare/Holtercare-Bench。
原文摘要 · Abstract (English)
While multimodal large language models (MLLMs) excel in medical applications, most of them favor static images or short-term signals. In the critical field of dynamic electrocardiograms (ECG), models struggle with complex temporal reasoning and diagnostic report generation due to a lack of high-quality datasets and benchmarks. To address this, we introduce (i) Holtercare-23K, a large-scale multimodal dynamic ECG dataset comprising 22,980 QA pairs derived from 788 clinical Holter records and featuring a novel signal-video-text tri-modal alignment. Based on this dataset, we present (ii) Holtercare-Bench, a multimodal benchmark that evaluates models on temporal localization, clinical diagnosis, and global summarization. Zero-shot evaluations of leading MLLMs reveal a significant performance gap in processing ultra-long pathological sequences. However, fine-tuning representative models yields substantial improvements. This work illuminates the limitations of current MLLMs in electrophysiology and provides a foundational benchmark for long-term medical MLLMs. Our project is available at https://github.com/ZJU4HealthCare/Holtercare-Bench.
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。