Fan Hao, Rossetti Sarah C, Thate Jennifer, Mugoya Rosemary, Lai Albert M, Yen Po-Yin
Institute for Informatics, Data Science and Biostatistics, Washington University School of Medicine, Saint Louis, MO 63110, United States.
Department of Biomedical Informatics, Columbia University Medical Center, New York, NY 10032, United States.
J Am Med Inform Assoc. 2025 Jul 1;32(7):1140-1148. doi: 10.1093/jamia/ocaf076.
Health-care institutions customize electronic health record (EHR) configurations to reflect their unique workflows and patient care priorities. Ensuring EHR alignment across sites facilitates seamless information exchange. We developed a pipeline for EHR flowsheet alignment between health-care organizations. The pipeline is augmented by mapping flowsheet data fields to concepts in the Clinical Care Classification (CCC) nursing terminology.
Flowsheet templates and measures from 2 study sites were transformed into template-measure (T-M) pairs. They were aligned through exact, lexical, or semantic matching. Lexical matches were assessed using Jaccard similarity and fuzzy matching methods. Semantic alignment was determined using cosine similarity between large language model-generated embeddings of T-M pairs and CCC concepts to rank and recommend the top n concepts in CCC. Concept mappings were evaluated based on whether concepts were mapped consistently within the CCC hierarchy.
We totally aligned 31 255 unique T-M pairs in acute care units and 27 012 T-M pairs in intensive care units from 2 study sites. When restricted to the top-ranked CCC concept (n = 1), we achieved a 63% flowsheet alignment rate with a 53% concept mapping rate. Expanding to the top 3 concepts (n = 3) improved alignment to 96.5% and concept mapping to 96%.
Electronic health record data field alignment with concept mapping offers opportunities to standardize data elements presented in flowsheets across health-care sites. We demonstrated the feasibility of leveraging a semi-automated pipeline to streamline the EHR flowsheet alignment and accelerate the manual concept mapping process.
医疗机构定制电子健康记录（EHR）配置，以反映其独特的工作流程和患者护理重点。确保各站点间的EHR一致性有助于实现无缝信息交换。我们开发了一种用于医疗机构间EHR流程图一致性的流程。该流程通过将流程图数据字段映射到临床护理分类（CCC）护理术语中的概念来增强。
将来自2个研究站点的流程图模板和指标转换为模板 - 指标（T - M）对。通过精确匹配、词汇匹配或语义匹配进行对齐。使用杰卡德相似度和模糊匹配方法评估词汇匹配。通过T - M对的大语言模型生成的嵌入与CCC概念之间的余弦相似度来确定语义对齐，以对CCC中的前n个概念进行排名和推荐。基于概念在CCC层次结构中是否一致映射来评估概念映射。
我们在2个研究站点的急性护理单元中总共对齐了31255个独特的T - M对，在重症监护单元中对齐了27012个T - M对。当限制为排名第一的CCC概念（n = 1）时，我们实现了63%的流程图对齐率和53%的概念映射率。扩展到前3个概念（n = 3）时，对齐率提高到96.5%，概念映射率提高到96%。
电子健康记录数据字段与概念映射的对齐为跨医疗机构标准化流程图中呈现的数据元素提供了机会。我们证明了利用半自动流程来简化EHR流程图对齐并加速手动概念映射过程的可行性。
