Standardizing Multi-site Clinical Note Titles to LOINC Document Ontology: A Transformer-based Approach.

Autor:	Zuo X; University of Texas Health Science Center at Houston, Houston, TX, USA., Zhou Y; University of Texas Health Science Center at Houston, Houston, TX, USA., Duke J; Georgia Institute of Technology, Atlanta, GA, USA.; OHDSI Consortium, Natural Language Processing Working Group., Hripcsak G; Columbia University, New York City, NY, USA.; OHDSI Consortium, Natural Language Processing Working Group., Shah N; Stanford University, Stanford, CA, USA.; OHDSI Consortium, Natural Language Processing Working Group., Banda JM; Georgia State University, Atlanta, GA, USA.; OHDSI Consortium, Natural Language Processing Working Group., Reeves R; Vanderbilt University Medical Center, Nashville, TN, USA.; OHDSI Consortium, Natural Language Processing Working Group., Miller T; Boston Children's Hospital, Boston, MA, USA.; OHDSI Consortium, Natural Language Processing Working Group., Waitman LR; University of Missouri, Columbia, MO, USA., Natarajan K; Columbia University, New York City, NY, USA.; OHDSI Consortium, Natural Language Processing Working Group., Xu H; Yale University, New Haven, CT, USA.; OHDSI Consortium, Natural Language Processing Working Group.
Jazyk:	angličtina
Zdroj:	AMIA ... Annual Symposium proceedings. AMIA Symposium [AMIA Annu Symp Proc] 2024 Jan 11; Vol. 2023, pp. 834-843. Date of Electronic Publication: 2024 Jan 11 (Print Publication: 2023).
Abstrakt:	The types of clinical notes in electronic health records (EHRs) are diverse and it would be great to standardize them to ensure unified data retrieval, exchange, and integration. The LOINC Document Ontology (DO) is a subset of LOINC that is created specifically for naming and describing clinical documents. Despite the efforts of promoting and improving this ontology, how to efficiently deploy it in real-world clinical settings has yet to be explored. In this study we evaluated the utility of LOINC DO by mapping clinical note titles collected from five institutions to the LOINC DO and classifying the mapping into three classes based on semantic similarity between note t itl es and LOINC DO codes. Additionally, we developed a standardization pipeline that automatically maps clinical note titles from multiple sites to suitable LOINC DO codes, without accessing the content of clinical notes. The pipeline can be initialized with different large language models, and we compared the performances between them. The results showed that our automated pipeline achieved an accuracy of 0.90. By comparing the manual and automated mapping results, we analyzed the coverage of LOINC DO in describing multi-site clinical note titles and summarized the potential scope for extension. Competing Interests: Dr. Hua Xu has research-related financial interests in Melax Technologies, Inc. (©2023 AMIA - All rights reserved.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu