用大模型解析糖尿病病例报告中的时间线，挖掘用药风险
Temporally Phenotyping GLP-1RA Case Reports with Large Language Models: A Textual Time Series Corpus and Risk Modeling
- 构建136例病例的文本时间序列数据集，标注临床事件时间点
- GPT5模型事件覆盖率达87.1%，时间顺序准确率84.3%
- 发现使用GLP-1药物者呼吸系统后遗症风险降低74%（HR=0.259）
2型糖尿病病例报告描述了复杂的临床过程，但其时间线常以难以复用的语言表达。为填补这一空白，我们构建了一个包含136篇涉及胰高血糖素样肽-1受体激动剂（GLP-1RA）的单患者病例报告的文本时间序列语料库，将临床事件关联到最可能的时间参考点。评估了自动化LLM时间线提取效果，对比临床专家标注的金标准，结果表明最佳模型GPT5在事件覆盖率（0.871）和症状、诊断、治疗、检验及结局的时间顺序准确性（0.843）方面表现优异。作为下游应用示例，时间至事件分析显示，与非使用者相比，GLP-1使用者呼吸系统后遗症风险显著降低（HR=0.259，p<0.05），与既往研究中改善呼吸结局的结论一致。时间标注数据与代码将在论文接受后公开。
原文摘要 · Abstract (English)
Type 2 diabetes case reports describe complex clinical courses, but their timelines are often expressed in language that is difficult to reuse in longitudinal modeling. To address this gap, we developed a textual time-series corpus of 136 PubMed Open Access single-patient case reports involving glucagon-like peptide 1 receptor agonists, with clinical events associated with their most probable reference times. We evaluated automated LLM timeline extraction against gold-standard timelines annotated by clinical domain experts, assessing how well systems recovered clinical events and their timings. The best-performing LLM produced high event coverage (GPT5; 0.871) and reliable temporal sequencing across symptoms (GPT5; 0.843), diagnoses, treatments, laboratory tests, and outcomes. As a downstream demonstration, time-to-event analyses in diabetes suggested lower risk of respiratory sequelae among GLP-1 users versus non-users (HR=0.259, p<0.05), consistent with prior reports of improved respiratory outcomes. Temporal annotations and code will be released upon acceptance.
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。