Related Experiment Videos
From ICD9-CM to MeSH using the UMLS: a how-to guide
J J Cimino1, S B Johnson, P Peng
1Center for Medical Informatics, Columbia Presbyterian Medical Center, New York 10032.
Proceedings. Symposium on Computer Applications in Medical Care
|January 1, 1993
Summary
The Unified Medical Language System (UMLS) can map International Classification of Diseases, 9th Edition, Clinical Modifications (ICD9-CM) to Medical Subject Headings (MeSH). This method successfully translated over 90% of the mapped terms for improved database retrieval.
Area of Science:
- Medical Informatics
- Health Terminology Management
- Biomedical Data Standards
Background:
- Controlled vocabularies are essential for organizing and retrieving medical information.
- The Unified Medical Language System (UMLS) aims to integrate diverse biomedical vocabularies.
- Interoperability between coding systems like ICD9-CM and MeSH is crucial for data exchange.
Purpose of the Study:
- To evaluate the effectiveness of the UMLS in converting International Classification of Diseases, 9th Edition, Clinical Modifications (ICD9-CM) terms to Medical Subject Headings (MeSH).
- To assess the feasibility of using UMLS-based translations for information retrieval in MeSH-indexed databases.
Main Methods:
- A systematic method was developed to map ICD9-CM codes to the UMLS Metathesaurus.
- The study analyzed the linkage rate of ICD9-CM terms to MeSH within the UMLS.
- The straightforwardness of the resulting translations was quantified.
Main Results:
- The developed method successfully mapped 30.4% of ICD9-CM terms to the UMLS.
- Of the mapped terms, 95.0% were successfully linked to MeSH.
- Translation was straightforward for 90.4% of the ICD9-CM to MeSH links.
Conclusions:
- The UMLS provides a viable tool for converting ICD9-CM to MeSH, facilitating cross-vocabulary mapping.
- The high rate of straightforward translations suggests potential for effective use in information retrieval systems.
- These findings support the utility of UMLS in enhancing data interoperability and search capabilities in biomedical databases like Medline.