Related Experiment Videos
Ambiguity resolution while mapping free text to the UMLS Metathesaurus
1National Library of Medicine, Bethesda, MD 20894.
Proceedings. Symposium on Computer Applications in Medical Care
|January 1, 1994
Summary
We developed a new method to resolve ambiguities when mapping free text to the Unified Medical Language System (UMLS) Metathesaurus. This approach successfully reduces mapping errors by approximately 80%.
Area of Science:
- Medical Informatics
- Natural Language Processing
- Biomedical Knowledge Representation
Background:
- Processing free text is crucial in medical informatics research.
- The Unified Medical Language System (UMLS) Metathesaurus is a key resource for managing biomedical information.
- Mapping free text to standardized terminologies like the UMLS Metathesaurus often results in ambiguities.
Purpose of the Study:
- To propose and evaluate a novel method for resolving ambiguities in free text to UMLS Metathesaurus mapping.
- To leverage semantic types from the UMLS Metathesaurus to improve mapping accuracy.
Main Methods:
- Developed a rule-based system to eliminate mapping ambiguities.
- Rules utilize the context of the ambiguity and semantic types from the UMLS Metathesaurus.
- Conducted a preliminary test of the proposed methodology.
Main Results:
- The developed rules successfully resolved ambiguities in free text to UMLS Metathesaurus mapping.
- Preliminary testing indicated an approximate 80% success rate in ambiguity resolution.
Conclusions:
- The proposed method offers a viable solution for improving the accuracy of mapping free text to the UMLS Metathesaurus.
- Contextual information and semantic types are essential for disambiguating medical text.
- Further validation is warranted to confirm the generalizability of the findings.