大型语言模型在医学时间序列分析中的应用
Large language models in medical time series analysis
- Istituto Italiano di Tecnologia（意大利技术研究院）
- University of Genoa（热那亚大学）
- University of Verona（维罗纳大学）
- University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）
- Yale University（耶鲁大学）
- National University of Singapore（新加坡国立大学）
- University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
- Keiji AI（Keiji人工智能公司）
- Peking University（北京大学）
- Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文综述了大型语言模型在医学时间序列分析中的应用，涵盖方法、架构、数据、提示策略及应用，旨在为开发、评估和部署MedTSLLMs提供清晰基础。
AI中文摘要：
医学时间序列（MedTS），包括心电图（ECG）、脑电图（EEG）、光电容积脉搏波（PPG）和生命体征记录，是临床诊断和健康监测的核心。随着大型语言模型（LLMs）的进步，越来越多的研究探讨了其推理、生成和知识整合能力如何支持MedTS分析。然而，现有研究仍然分散，该领域对于如何设计这些模型、将其整合到临床工作流程中并进行评估，仍缺乏清晰的认识。本综述综合了近期关于医学时间序列分析的大型语言模型（MedTSLLMs）的研究，涵盖了方法论进展和与实际部署相关的问题。我们回顾了模型架构、数据资源和处理流程，以及为不同临床场景设计的提示词策略。我们进一步整理了现有的MedTS应用，从诊断解释和报告生成到纵向健康监测和生理信号合成，强调了任务特定的设计选择、常见的评估协议和研究中报告的实证结果。通过汇集当前实践和开放挑战，本综述旨在为在医疗保健中负责任地开发、评估和部署MedTSLLMs提供更清晰的基础。我们还维护一个定期更新的MedTSLLM研究和资源列表，网址为：此https URL。
英文摘要：
Medical time series (MedTS), including electrocardiograms (ECG), electroencephalograms (EEG), photoplethysmography (PPG), and vital-sign recordings, are central to clinical diagnosis and health monitoring. As large language models (LLMs) have advanced, a growing body of work has examined how their reasoning, generation, and knowledge-integration capabilities can support MedTS analysis. Yet existing studies remain scattered, and the field still lacks a clear view of how these models should be designed, integrated into clinical workflows, and evaluated. This review synthesizes recent work on large language models for medical time series analysis (MedTSLLMs), covering both methodological progress and issues related to real-world deployment. We review model architectures, data resources, and processing pipelines, and prompt design strategies adapted for diverse clinical scenarios. We further organize existing MedTS applications, ranging from diagnostic interpretation and report generation to longitudinal health monitoring and physiological signal synthesis, highlighting task-specific design choices, common evaluation protocols, and empirical findings reported across studies. By bringing together current practices and open challenges, this review aims to provide a clearer foundation for developing, evaluating, and deploying MedTSLLMs responsibly in healthcare. We also maintain a regularly updated list of MedTSLLM studies and resources at: https://github.com/hy727/MedTSLLM-Review.
