文献速递医学人工智能与信息学真实世界研究与卫生经济流行病学与生物统计

从结构化与非结构化电子健康记录中构建可计算纵向患者旅程

Computable longitudinal patient journeys from structured and unstructured EHR data.
PubMed 文献 · Nat Med · 2026-09-10

研究提出利用大型预训练语言模型从非结构化电子健康记录文本中准确提取可计算临床数据,经医生裁定验证准确性后,将提取实体与结构化数据整合并嵌入医学本体构建知识图谱,实现个体与群体层面变量关系查询。在GLP-1受体激动剂治疗分析中,高置信度识别大量起始治疗患者,重建患者轨迹并建模体重与血红蛋白A1c纵向变化,揭示其与治疗反应的关联。

要点

  • 预训练语言模型可从非结构化电子健康记录文本中准确提取可计算临床数据。
  • 提取数据与结构化数据整合构建知识图谱,支持个体与群体层面快速查询分析。
  • 在GLP-1受体激动剂治疗分析中重建患者轨迹并建模体重与血红蛋白A1c变化。

核心结论

  • 利用大型预训练语言模型从非结构化电子健康记录文本中提取可计算临床数据,经医生裁定确认高准确性。
  • 整合提取数据与结构化数据构建知识图谱,支持快速、低成本的分析与假设检验。
  • 在GLP-1受体激动剂治疗分析中高置信度识别大量起始治疗患者,并揭示体重与血红蛋白A1c变化与治疗反应的关联。

研究设计与样本

  • 研究采用大型预训练语言模型从非结构化电子健康记录文本中提取临床数据,并以医生裁定对照盲法专家参考标准验证准确性。
  • 框架与疾病无关,可扩展至所有临床状况的大型患者数据集,提取实体与结构化数据整合并嵌入医学本体构建知识图谱。
  • 通过程序化接口导航知识图谱数据,在研究者控制下进行探索与假设检验。
  • 以GLP-1受体激动剂起始治疗患者为例进行大规模纵向分析,重建患者轨迹并建模体重与血红蛋白A1c纵向变化。

主要发现

  • 医生裁定确认提取准确性高,且专家医生审阅者间一致性高。
  • 高置信度识别大量起始GLP-1受体激动剂治疗的患者,并重建患者层面轨迹。
  • 建模GLP-1受体激动剂起始后体重与血红蛋白A1c的纵向变化,揭示这些参数与治疗反应的关联。
  • 表征仅记录于非结构化临床笔记中的结局,展示时间至事件结局,超越固定时间点终点。

临床怎么用

  • 可利用该框架从非结构化电子健康记录文本中提取可计算临床数据,补充结构化字段的不足。
  • 通过知识图谱与程序化接口,在研究者控制研究设计、分析决策与解释的前提下加速劳动密集型任务。
  • 在真实世界证据研究中,可基于提取数据重建患者纵向轨迹并建模治疗反应,包括时间至事件结局。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

Most electronic health record (EHR) data reside in unstructured text, recorded in encounters between healthcare providers and patients. These encounters capture symptom narratives, adverse effects, treatment rationales, adherence challenges, family history and other nuances that are not coded or only partially reflected in structured fields such as diagnosis and procedures codes. Yet the majority of real-world evidence studies rely on structured data fields. Here we present a new approach that uses large, pretrained language models to accurately extract computable clinical data from unstructured EHR text. Physician adjudication confirmed high accuracy against a blinded expert reference standard, with high expert physician inter-reviewer agreement. The framework is disease-agnostic and scales to large patient datasets across all clinical conditions. The extracted clinical entities are integrated with structured EHR data, embedded with medical ontologies, and organized into a knowledge graph, allowing all relationships between variables to be interrogated at the level of individual patients or at scale. An agentic-friendly programmatic interface navigates large-scale knowledge graph data, making analyses rapid, easy and cost-effective, both for exploration and hypothesis testing. This human-guided query environment enables acceleration of labor-intensive tasks, while study design, analytic decisions and interpretation remain under investigator control. To demonstrate clinical utility, we conducted a large-scale longitudinal analysis of treatment responses among individuals initiating glucagon-like peptide-1 receptor agonists (GLP-1 RAs) therapy. We identify large numbers of patients initiating GLP-1 RAs with high confidence, reconstruct patient-level trajectories, and model longitudinal changes in weight and hemoglobin A1c following GLP-1 RA initiation, revealing association between these parameters and response to therapy. Further, we characterize outcomes captured only in unstructured clinical notes and show time-to-event outcomes, moving beyond fixed-timepoint end points to provide a comprehensive understanding of real-world treatment responses.

来源:Nat Med,查看原文。版权归原作者所有。

引用

  1. Kim E, Foty R, Thakor AS, et al. Computable longitudinal patient journeys from structured and unstructured EHR data. Nat Med. 2026. PMID: 42742184. doi:10.1038/s41591-026-04695-x

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。