An evaluation of hybrid methods for matching biomedical terminologies: Mapping the gene ontology to the UMLS®

M. N. Cantor, I. N. Sarkar, R. Gelman, F. Hartel, O. Bodenreider, Yves A Lussier

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Integration of disparate biomedical terminologies is becoming increasingly important as links between biological science and clinical medicine grow. Mapping concepts in the Gene OntologyTM(GO) to the UMLS may help further this integration and allow for more efficient information exchange among researchers. Using a gold standard of GO term - UMLS concept mappings provided by the NCI, we examined the performance of various published and combined mapping techniques, in order to maximize precision and recall. We found that for the previously published techniques precision varied between (0.61-0.95), and recall varied from (0.65-0.90), whereas for the hybrid techniques, precision varied between (0.66-0.97), and recall from (0.59-0.93). Our study reveals the benefits of using mapping techniques that incorporate domain knowledge, and provides a basis for future approaches to mapping between distinct biomedical vocabularies.

Original languageEnglish (US)
Title of host publicationStudies in Health Technology and Informatics
Pages62-67
Number of pages6
Volume95
DOIs
StatePublished - 2003
Externally publishedYes
Event18th International Congress of the European Federation for Medical Informatics, MIE 2003 - St. Malo, France
Duration: May 4 2003May 7 2003

Other

Other18th International Congress of the European Federation for Medical Informatics, MIE 2003
CountryFrance
CitySt. Malo
Period5/4/035/7/03

Fingerprint

Unified Medical Language System
Gene Ontology
Terminology
Ontology
Genes
Biological Science Disciplines
Vocabulary
Clinical Medicine
Research Personnel
Medicine

Keywords

  • Bioinformatics
  • Gene Ontology
  • Mapping Terminologies
  • Medical Informatics
  • Unified Medical Language System

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Cite this

Cantor, M. N., Sarkar, I. N., Gelman, R., Hartel, F., Bodenreider, O., & Lussier, Y. A. (2003). An evaluation of hybrid methods for matching biomedical terminologies: Mapping the gene ontology to the UMLS®. In Studies in Health Technology and Informatics (Vol. 95, pp. 62-67) https://doi.org/10.3233/978-1-60750-939-4-62

An evaluation of hybrid methods for matching biomedical terminologies : Mapping the gene ontology to the UMLS®. / Cantor, M. N.; Sarkar, I. N.; Gelman, R.; Hartel, F.; Bodenreider, O.; Lussier, Yves A.

Studies in Health Technology and Informatics. Vol. 95 2003. p. 62-67.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Cantor, MN, Sarkar, IN, Gelman, R, Hartel, F, Bodenreider, O & Lussier, YA 2003, An evaluation of hybrid methods for matching biomedical terminologies: Mapping the gene ontology to the UMLS®. in Studies in Health Technology and Informatics. vol. 95, pp. 62-67, 18th International Congress of the European Federation for Medical Informatics, MIE 2003, St. Malo, France, 5/4/03. https://doi.org/10.3233/978-1-60750-939-4-62
Cantor MN, Sarkar IN, Gelman R, Hartel F, Bodenreider O, Lussier YA. An evaluation of hybrid methods for matching biomedical terminologies: Mapping the gene ontology to the UMLS®. In Studies in Health Technology and Informatics. Vol. 95. 2003. p. 62-67 https://doi.org/10.3233/978-1-60750-939-4-62
Cantor, M. N. ; Sarkar, I. N. ; Gelman, R. ; Hartel, F. ; Bodenreider, O. ; Lussier, Yves A. / An evaluation of hybrid methods for matching biomedical terminologies : Mapping the gene ontology to the UMLS®. Studies in Health Technology and Informatics. Vol. 95 2003. pp. 62-67
@inproceedings{1cf8d82b8b354311a8ac69fb68ba4a8d,
title = "An evaluation of hybrid methods for matching biomedical terminologies: Mapping the gene ontology to the UMLS{\circledR}",
abstract = "Integration of disparate biomedical terminologies is becoming increasingly important as links between biological science and clinical medicine grow. Mapping concepts in the Gene OntologyTM(GO) to the UMLS may help further this integration and allow for more efficient information exchange among researchers. Using a gold standard of GO term - UMLS concept mappings provided by the NCI, we examined the performance of various published and combined mapping techniques, in order to maximize precision and recall. We found that for the previously published techniques precision varied between (0.61-0.95), and recall varied from (0.65-0.90), whereas for the hybrid techniques, precision varied between (0.66-0.97), and recall from (0.59-0.93). Our study reveals the benefits of using mapping techniques that incorporate domain knowledge, and provides a basis for future approaches to mapping between distinct biomedical vocabularies.",
keywords = "Bioinformatics, Gene Ontology, Mapping Terminologies, Medical Informatics, Unified Medical Language System",
author = "Cantor, {M. N.} and Sarkar, {I. N.} and R. Gelman and F. Hartel and O. Bodenreider and Lussier, {Yves A}",
year = "2003",
doi = "10.3233/978-1-60750-939-4-62",
language = "English (US)",
isbn = "1586033476",
volume = "95",
pages = "62--67",
booktitle = "Studies in Health Technology and Informatics",

}

TY - GEN

T1 - An evaluation of hybrid methods for matching biomedical terminologies

T2 - Mapping the gene ontology to the UMLS®

AU - Cantor, M. N.

AU - Sarkar, I. N.

AU - Gelman, R.

AU - Hartel, F.

AU - Bodenreider, O.

AU - Lussier, Yves A

PY - 2003

Y1 - 2003

N2 - Integration of disparate biomedical terminologies is becoming increasingly important as links between biological science and clinical medicine grow. Mapping concepts in the Gene OntologyTM(GO) to the UMLS may help further this integration and allow for more efficient information exchange among researchers. Using a gold standard of GO term - UMLS concept mappings provided by the NCI, we examined the performance of various published and combined mapping techniques, in order to maximize precision and recall. We found that for the previously published techniques precision varied between (0.61-0.95), and recall varied from (0.65-0.90), whereas for the hybrid techniques, precision varied between (0.66-0.97), and recall from (0.59-0.93). Our study reveals the benefits of using mapping techniques that incorporate domain knowledge, and provides a basis for future approaches to mapping between distinct biomedical vocabularies.

AB - Integration of disparate biomedical terminologies is becoming increasingly important as links between biological science and clinical medicine grow. Mapping concepts in the Gene OntologyTM(GO) to the UMLS may help further this integration and allow for more efficient information exchange among researchers. Using a gold standard of GO term - UMLS concept mappings provided by the NCI, we examined the performance of various published and combined mapping techniques, in order to maximize precision and recall. We found that for the previously published techniques precision varied between (0.61-0.95), and recall varied from (0.65-0.90), whereas for the hybrid techniques, precision varied between (0.66-0.97), and recall from (0.59-0.93). Our study reveals the benefits of using mapping techniques that incorporate domain knowledge, and provides a basis for future approaches to mapping between distinct biomedical vocabularies.

KW - Bioinformatics

KW - Gene Ontology

KW - Mapping Terminologies

KW - Medical Informatics

KW - Unified Medical Language System

UR - http://www.scopus.com/inward/record.url?scp=33645193063&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33645193063&partnerID=8YFLogxK

U2 - 10.3233/978-1-60750-939-4-62

DO - 10.3233/978-1-60750-939-4-62

M3 - Conference contribution

AN - SCOPUS:33645193063

SN - 1586033476

SN - 9781586033477

VL - 95

SP - 62

EP - 67

BT - Studies in Health Technology and Informatics

ER -