EVALUATION OF THE UNIFIED-MEDICAL-LANGUAGE-SYSTEM AS A MEDICAL KNOWLEDGE SOURCE

Citation
O. Bodenreider et al., EVALUATION OF THE UNIFIED-MEDICAL-LANGUAGE-SYSTEM AS A MEDICAL KNOWLEDGE SOURCE, Journal of the American Medical Informatics Association, 5(1), 1998, pp. 76-87
Citations number
44
Categorie Soggetti
Information Science & Library Science","Computer Science Interdisciplinary Applications","Medical Informatics
ISSN journal
10675027
Volume
5
Issue
1
Year of publication
1998
Pages
76 - 87
Database
ISI
SICI code
1067-5027(1998)5:1<76:EOTUAA>2.0.ZU;2-O
Abstract
Objective: The authors evaluated the use of the Unified Medical Langua ge System (UMLS) as a medical knowledge source for the representation of medical procedures in the MAOUSSC system. Design: MAOUSSC, a multia xial coding system, was used for the representation of 1500 procedures from 15 clinical specialties, using UMLS concepts (augmented by full sources for three new vocabularies being added to the UMLS) and relati onships whenever possible. Evaluation criteria for the UMLS included ( 1) completeness of representation of concepts and of inter-concept rel ationships, (2) consistency in the categorization of both concepts and inter-concept relationships, and (3) usability, including adaptabilit y of the UMLS to a foreign language (French), its suitability to a geo graphic region with different medical practices than the USA, and issu es relative to the annual update changes in the test vocabularies. Res ults: During the MAOUSSC trial, the number of missing concepts or rela tionships identified in the augmented UMLS sources was deemed to be in consequential relative to overall project goals. ''Missing'' UMLS inte r-concept relationships were identified, although they were small. in number. Some inconsistencies in the UMLS were noted, especially in the area of hierarchic relationships. Conclusion: After UMLS was used for five years as a knowledge source for representing 1500 complex medica l procedures in MAOUSSC, its value is considered significant. Future e ditions of the UMLS are expected to improve representation of inter-co ncept relationships and global consistency.