Utilizing the UMLS for semantic mapping between terminologies
K. Fung, and O. Bodenreider. AMIA Annu Symp Proc, (2005)Fung, Kin Wah Bodenreider, Olivier Evaluation Studies Research Support, N.I.H., Extramural United States AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium.
Abstract
An algorithm was derived to find candidate mappings between any two terminologies inside the UMLS, making use of synonymy, explicit mapping relations and hierarchical relationships among UMLS concepts. Using an existing set of mappings from SNOMED CT to ICD9CM as our gold standard, we managed to find candidate mappings for 86% of SNOMED CT terms, with recall of 42% and precision of 20%. Among the various methods used, mapping by UMLS synonymy was particularly accurate and could potentially be useful as a quality assurance tool in the creation of mapping sets or in the UMLS editing process. Other strengths and weaknesses of the algorithm are discussed.
%0 Journal Article
%1 Fung:2005ci
%A Fung, K. W.
%A Bodenreider, O.
%D 2005
%J AMIA Annu Symp Proc
%K Algorithms Classification Diseases International Language Medical Medicine Nomenclature Semantics System Systematized Unified of
%P 266-70
%T Utilizing the UMLS for semantic mapping between terminologies
%X An algorithm was derived to find candidate mappings between any two terminologies inside the UMLS, making use of synonymy, explicit mapping relations and hierarchical relationships among UMLS concepts. Using an existing set of mappings from SNOMED CT to ICD9CM as our gold standard, we managed to find candidate mappings for 86% of SNOMED CT terms, with recall of 42% and precision of 20%. Among the various methods used, mapping by UMLS synonymy was particularly accurate and could potentially be useful as a quality assurance tool in the creation of mapping sets or in the UMLS editing process. Other strengths and weaknesses of the algorithm are discussed.
@article{Fung:2005ci,
abstract = {An algorithm was derived to find candidate mappings between any two terminologies inside the UMLS, making use of synonymy, explicit mapping relations and hierarchical relationships among UMLS concepts. Using an existing set of mappings from SNOMED CT to ICD9CM as our gold standard, we managed to find candidate mappings for 86% of SNOMED CT terms, with recall of 42% and precision of 20%. Among the various methods used, mapping by UMLS synonymy was particularly accurate and could potentially be useful as a quality assurance tool in the creation of mapping sets or in the UMLS editing process. Other strengths and weaknesses of the algorithm are discussed.},
added-at = {2012-06-02T05:59:56.000+0200},
author = {Fung, K. W. and Bodenreider, O.},
biburl = {https://www.bibsonomy.org/bibtex/20f7f5df3a5ec70a1c13251ceeb3a53fd/ozborn},
date-added = {2012-06-01 16:59:33 -0500},
date-modified = {2012-06-01 16:59:49 -0500},
interhash = {96666b5eea09d329f3b220daf9a3dccf},
intrahash = {0f7f5df3a5ec70a1c13251ceeb3a53fd},
journal = {AMIA Annu Symp Proc},
keywords = {Algorithms Classification Diseases International Language Medical Medicine Nomenclature Semantics System Systematized Unified of},
note = {Fung, Kin Wah Bodenreider, Olivier Evaluation Studies Research Support, N.I.H., Extramural United States AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium},
pages = {266-70},
timestamp = {2012-06-03T07:20:35.000+0200},
title = {Utilizing the UMLS for semantic mapping between terminologies},
year = 2005
}