Towards the development of a conceptual distance metric for the UMLS

Jorge Caviedes, James J. Cimino

Research output: Contribution to journalArticle

66 Citations (Scopus)

Abstract

The objective of this work is to investigate the feasibility of conceptual similarity metrics in the framework of the Unified Medical Language System (UMLS). We have investigated an approach based on the minimum number of parent links between concepts, and evaluated its performance relative to human expert estimates on three sets of concepts for three terminologies within the UMLS (i.e., MeSH, ICD9CM, and SNOMED). The resulting quantitative metric enables computer-based applications that use decision thresholds and approximate matching criteria. The proposed conceptual matching supports problem solving and inferencing (using high-level, generic concepts) based on readily available data (typically represented as low-level, specific concepts). Through the identification of semantically similar concepts, conceptual matching also enables reasoning in the absence of exact, or even approximate, lexical matching. Finally, conceptual matching is relevant for terminology development and maintenance, machine learning research, decision support system development, and data mining research in biomedical informatics and other fields.

Original languageEnglish (US)
Pages (from-to)77-85
Number of pages9
JournalJournal of Biomedical Informatics
Volume37
Issue number2
DOIs
StatePublished - Apr 1 2004
Externally publishedYes

Fingerprint

Unified Medical Language System
Terminology
Systematized Nomenclature of Medicine
Informatics
Data Mining
Decision support systems
Data mining
Learning systems
Biomedical Research
Maintenance
Research

Keywords

  • Conceptual metrics
  • Medical terminology
  • Semantic distance
  • Similarity metrics
  • UMLS

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

Towards the development of a conceptual distance metric for the UMLS. / Caviedes, Jorge; Cimino, James J.

In: Journal of Biomedical Informatics, Vol. 37, No. 2, 01.04.2004, p. 77-85.

Research output: Contribution to journalArticle

@article{4832f3ea563f4e43ae787778606c3ec8,
title = "Towards the development of a conceptual distance metric for the UMLS",
abstract = "The objective of this work is to investigate the feasibility of conceptual similarity metrics in the framework of the Unified Medical Language System (UMLS). We have investigated an approach based on the minimum number of parent links between concepts, and evaluated its performance relative to human expert estimates on three sets of concepts for three terminologies within the UMLS (i.e., MeSH, ICD9CM, and SNOMED). The resulting quantitative metric enables computer-based applications that use decision thresholds and approximate matching criteria. The proposed conceptual matching supports problem solving and inferencing (using high-level, generic concepts) based on readily available data (typically represented as low-level, specific concepts). Through the identification of semantically similar concepts, conceptual matching also enables reasoning in the absence of exact, or even approximate, lexical matching. Finally, conceptual matching is relevant for terminology development and maintenance, machine learning research, decision support system development, and data mining research in biomedical informatics and other fields.",
keywords = "Conceptual metrics, Medical terminology, Semantic distance, Similarity metrics, UMLS",
author = "Jorge Caviedes and Cimino, {James J.}",
year = "2004",
month = "4",
day = "1",
doi = "10.1016/j.jbi.2004.02.001",
language = "English (US)",
volume = "37",
pages = "77--85",
journal = "Journal of Biomedical Informatics",
issn = "1532-0464",
publisher = "Academic Press Inc.",
number = "2",

}

TY - JOUR

T1 - Towards the development of a conceptual distance metric for the UMLS

AU - Caviedes, Jorge

AU - Cimino, James J.

PY - 2004/4/1

Y1 - 2004/4/1

N2 - The objective of this work is to investigate the feasibility of conceptual similarity metrics in the framework of the Unified Medical Language System (UMLS). We have investigated an approach based on the minimum number of parent links between concepts, and evaluated its performance relative to human expert estimates on three sets of concepts for three terminologies within the UMLS (i.e., MeSH, ICD9CM, and SNOMED). The resulting quantitative metric enables computer-based applications that use decision thresholds and approximate matching criteria. The proposed conceptual matching supports problem solving and inferencing (using high-level, generic concepts) based on readily available data (typically represented as low-level, specific concepts). Through the identification of semantically similar concepts, conceptual matching also enables reasoning in the absence of exact, or even approximate, lexical matching. Finally, conceptual matching is relevant for terminology development and maintenance, machine learning research, decision support system development, and data mining research in biomedical informatics and other fields.

AB - The objective of this work is to investigate the feasibility of conceptual similarity metrics in the framework of the Unified Medical Language System (UMLS). We have investigated an approach based on the minimum number of parent links between concepts, and evaluated its performance relative to human expert estimates on three sets of concepts for three terminologies within the UMLS (i.e., MeSH, ICD9CM, and SNOMED). The resulting quantitative metric enables computer-based applications that use decision thresholds and approximate matching criteria. The proposed conceptual matching supports problem solving and inferencing (using high-level, generic concepts) based on readily available data (typically represented as low-level, specific concepts). Through the identification of semantically similar concepts, conceptual matching also enables reasoning in the absence of exact, or even approximate, lexical matching. Finally, conceptual matching is relevant for terminology development and maintenance, machine learning research, decision support system development, and data mining research in biomedical informatics and other fields.

KW - Conceptual metrics

KW - Medical terminology

KW - Semantic distance

KW - Similarity metrics

KW - UMLS

UR - http://www.scopus.com/inward/record.url?scp=2342596419&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2342596419&partnerID=8YFLogxK

U2 - 10.1016/j.jbi.2004.02.001

DO - 10.1016/j.jbi.2004.02.001

M3 - Article

C2 - 15120654

AN - SCOPUS:2342596419

VL - 37

SP - 77

EP - 85

JO - Journal of Biomedical Informatics

JF - Journal of Biomedical Informatics

SN - 1532-0464

IS - 2

ER -