用大模型提升病历与电子病历用药信息对齐，减少因术语和时间差异导致的误判。
Characterizing Treatment-Context Medication Evidence Across Clinic Notes and Structured EHR Medication History
- 通过大模型构建参考标准，结合人工审核与语义时序比对，统一病历与结构化用药数据
- 规范化后匹配准确率从72.3%提升至84.3%，有效用药条目语义重合率达90.3%
- 发现仅16.4%的用药记录在同就诊期内完全一致，但多数可通过时间或语义补全
临床笔记与结构化电子健康记录（EHR）用药信息常不一致。同一就诊期内的差异可能源于笔记端归一化错误、术语或时间不同，或实际记录差异。本文提出一种基于笔记的对齐方法，结合大语言模型辅助参考构建、定向与随机人工审核、确定性用药归一化，以及与结构化用药记录的语义和时间对比。在5,403条独立测试集用药提及中，规范后精确匹配率从0.7226升至0.8429。在未审计条目随机抽查中，规范标签一致率达0.9210，但治疗动作归属仅为0.5326。全队列分析显示，仅16.44%的笔记用药与结构化记录同就诊期完全重合，55.17%存在语义重合，90.34%在±30天内有重合，严格无结构化重合项仅占3.97%。基于本体的敏感性分析表明，经过开发阶段补充的别名映射后，持有严格无重合的OMOP标准项从43.99%降至36.68%。结果表明，笔记与结构化用药不一致主要源于归一化误差、术语差异及记录时间差。
原文摘要 · Abstract (English)
Clinic notes and structured electronic health record (EHR) medication history often contain different medication information. Same-visit disagreement between these sources may result from note-side normalization errors, differences in terminology or timing, or actual differences in documentation. We developed a note-grounded approach that uses large language model (LLM) assisted reference construction, targeted and random human review, deterministic medication normalization, and semantic and temporal comparisons with structured medication history. We evaluated all normalization results on a patient-level held-out test set to limit adaptation to the study cohort. On 5,403 held-out mention rows, exact canonical agreement improved from 0.7226 with surface-exact matching to 0.8429 after lexical cleanup and curated alias mapping. In a random audit of previously unaudited rows, canonical-label agreement was 0.9210 among evaluable valid medication mentions, whereas treatment-action attribution was lower at 0.5326. In the full-cohort characterization analysis, only 16.44% of note-derived rows had same-visit exact overlap with structured medication history, but 55.17% had same-visit semantic overlap, 90.34% had same-visit or +/-30-day overlap, and only 3.97% remained in the strict no-structured-overlap bucket under broad project-level mapping. An ontology-backed sensitivity analysis further showed that held-out strict Observational Medical Outcomes Partnership (OMOP)-backed no-overlap fell from 43.99% to 36.68% after a development-derived alias supplement. These results show that note-to-structured-medication mismatch can arise from normalization errors, differences in terminology, and differences in documentation timing.
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。