Exploring the use of concept spaces to improve medical information retrieval

Andrea L. Houston, Hsinchun Chen, Bruce R. Schatz, Susan M. Hubbard, Robin R. Sewell, Tobun D. Ng

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

This research investigated the application of techniques successfully used in previous information retrieval research, to the more challenging area of medical informatics. It was performed on a biomedical document collection testbed, CANCERLIT, provided by the National Cancer Institute (NCI), which contains information on all types of cancer therapy. The quality or usefulness of terms suggested by three different thesauri, one based on MeSH terms, one based solely on terms from the document collection, and one based on the Unified Medical Language System (UMLS) Metathesaurus, was explored with the ultimate goal of improving CANCERLIT information search and retrieval. Researchers affiliated with the University of Arizona Cancer Center evaluated lists of related terms suggested by different thesauri for 12 different directed searches in the CANCERLIT testbed. The preliminary results indicated that among the thesauri, there were no statistically significant differences in either term recall or precision. Surprisingly, there was almost no overlap of relevant terms suggested by the different thesauri for a given search. This suggests that recall could be significantly improved by using a combined thesaurus approach.

Original languageEnglish (US)
Pages (from-to)171-186
Number of pages16
JournalDecision Support Systems
Volume30
Issue number2
DOIs
StatePublished - Dec 27 2000

Fingerprint

Controlled Vocabulary
Thesauri
Information Storage and Retrieval
Information retrieval
Unified Medical Language System
Testbeds
Medical Informatics
National Cancer Institute (U.S.)
Research
Neoplasms
Research Personnel
Thesaurus
Information Retrieval
Cancer

ASJC Scopus subject areas

  • Management Information Systems
  • Information Systems
  • Information Systems and Management

Cite this

Exploring the use of concept spaces to improve medical information retrieval. / Houston, Andrea L.; Chen, Hsinchun; Schatz, Bruce R.; Hubbard, Susan M.; Sewell, Robin R.; Ng, Tobun D.

In: Decision Support Systems, Vol. 30, No. 2, 27.12.2000, p. 171-186.

Research output: Contribution to journalArticle

Houston, Andrea L. ; Chen, Hsinchun ; Schatz, Bruce R. ; Hubbard, Susan M. ; Sewell, Robin R. ; Ng, Tobun D. / Exploring the use of concept spaces to improve medical information retrieval. In: Decision Support Systems. 2000 ; Vol. 30, No. 2. pp. 171-186.
@article{b12d4e7ce52942efa593a1d58ab9abe6,
title = "Exploring the use of concept spaces to improve medical information retrieval",
abstract = "This research investigated the application of techniques successfully used in previous information retrieval research, to the more challenging area of medical informatics. It was performed on a biomedical document collection testbed, CANCERLIT, provided by the National Cancer Institute (NCI), which contains information on all types of cancer therapy. The quality or usefulness of terms suggested by three different thesauri, one based on MeSH terms, one based solely on terms from the document collection, and one based on the Unified Medical Language System (UMLS) Metathesaurus, was explored with the ultimate goal of improving CANCERLIT information search and retrieval. Researchers affiliated with the University of Arizona Cancer Center evaluated lists of related terms suggested by different thesauri for 12 different directed searches in the CANCERLIT testbed. The preliminary results indicated that among the thesauri, there were no statistically significant differences in either term recall or precision. Surprisingly, there was almost no overlap of relevant terms suggested by the different thesauri for a given search. This suggests that recall could be significantly improved by using a combined thesaurus approach.",
author = "Houston, {Andrea L.} and Hsinchun Chen and Schatz, {Bruce R.} and Hubbard, {Susan M.} and Sewell, {Robin R.} and Ng, {Tobun D.}",
year = "2000",
month = "12",
day = "27",
doi = "10.1016/S0167-9236(00)00097-X",
language = "English (US)",
volume = "30",
pages = "171--186",
journal = "Decision Support Systems",
issn = "0167-9236",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Exploring the use of concept spaces to improve medical information retrieval

AU - Houston, Andrea L.

AU - Chen, Hsinchun

AU - Schatz, Bruce R.

AU - Hubbard, Susan M.

AU - Sewell, Robin R.

AU - Ng, Tobun D.

PY - 2000/12/27

Y1 - 2000/12/27

N2 - This research investigated the application of techniques successfully used in previous information retrieval research, to the more challenging area of medical informatics. It was performed on a biomedical document collection testbed, CANCERLIT, provided by the National Cancer Institute (NCI), which contains information on all types of cancer therapy. The quality or usefulness of terms suggested by three different thesauri, one based on MeSH terms, one based solely on terms from the document collection, and one based on the Unified Medical Language System (UMLS) Metathesaurus, was explored with the ultimate goal of improving CANCERLIT information search and retrieval. Researchers affiliated with the University of Arizona Cancer Center evaluated lists of related terms suggested by different thesauri for 12 different directed searches in the CANCERLIT testbed. The preliminary results indicated that among the thesauri, there were no statistically significant differences in either term recall or precision. Surprisingly, there was almost no overlap of relevant terms suggested by the different thesauri for a given search. This suggests that recall could be significantly improved by using a combined thesaurus approach.

AB - This research investigated the application of techniques successfully used in previous information retrieval research, to the more challenging area of medical informatics. It was performed on a biomedical document collection testbed, CANCERLIT, provided by the National Cancer Institute (NCI), which contains information on all types of cancer therapy. The quality or usefulness of terms suggested by three different thesauri, one based on MeSH terms, one based solely on terms from the document collection, and one based on the Unified Medical Language System (UMLS) Metathesaurus, was explored with the ultimate goal of improving CANCERLIT information search and retrieval. Researchers affiliated with the University of Arizona Cancer Center evaluated lists of related terms suggested by different thesauri for 12 different directed searches in the CANCERLIT testbed. The preliminary results indicated that among the thesauri, there were no statistically significant differences in either term recall or precision. Surprisingly, there was almost no overlap of relevant terms suggested by the different thesauri for a given search. This suggests that recall could be significantly improved by using a combined thesaurus approach.

UR - http://www.scopus.com/inward/record.url?scp=0034541094&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034541094&partnerID=8YFLogxK

U2 - 10.1016/S0167-9236(00)00097-X

DO - 10.1016/S0167-9236(00)00097-X

M3 - Article

AN - SCOPUS:0034541094

VL - 30

SP - 171

EP - 186

JO - Decision Support Systems

JF - Decision Support Systems

SN - 0167-9236

IS - 2

ER -