Application of a Medical Text Indexer to an online dermatology atlas.

G. R. Kim, A. R. Aronson, J. G. Mork, B. A. Cohen, C. U. Lehmann

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Clinical dermatology cases are presented as images and semi-structured text describing skin lesions and their relationships to disease. Metadata assignment to such cases is hampered by lack of a standardized dermatology vocabulary and facilitated methods for indexing legacy collections. In this pilot study descriptive clinical text from Dermatlas, a Web-based repository of dermatology cases, was indexed to Medical Subject Heading (MeSH) terms using the National Library of Medicine's Medical Text Indexer (MTI). The MTI is an automated text processing system that derives ranked lists of MeSH terms to describe the content of medical journal citations using knowledge from the Unified Medical Language System (UMLS) and from MEDLINE. For a representative, random sample of 50 Dermatlas cases, the MTI frequently derived MeSH indexing terms that matched expert-assigned terms for Diagnoses (88%), Lesion Types (72%), and Patient Characteristics (Gender and Age Groups, 62% and 84% respectively). This pilot demonstrates the potential for extending the MTI to automate indexing of clinical case presentations and for using MeSH to describe aspects of clinical dermatology.

Original languageEnglish (US)
Pages (from-to)287-291
Number of pages5
JournalMedinfo. MEDINFO
Volume11
Issue numberPt 1
StatePublished - 2004
Externally publishedYes

Fingerprint

Medical Subject Headings
Atlases
Dermatology
Unified Medical Language System
National Library of Medicine (U.S.)
Vocabulary
MEDLINE
Age Groups
Skin

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Kim, G. R., Aronson, A. R., Mork, J. G., Cohen, B. A., & Lehmann, C. U. (2004). Application of a Medical Text Indexer to an online dermatology atlas. Medinfo. MEDINFO, 11(Pt 1), 287-291.

Application of a Medical Text Indexer to an online dermatology atlas. / Kim, G. R.; Aronson, A. R.; Mork, J. G.; Cohen, B. A.; Lehmann, C. U.

In: Medinfo. MEDINFO, Vol. 11, No. Pt 1, 2004, p. 287-291.

Research output: Contribution to journalArticle

Kim, GR, Aronson, AR, Mork, JG, Cohen, BA & Lehmann, CU 2004, 'Application of a Medical Text Indexer to an online dermatology atlas.', Medinfo. MEDINFO, vol. 11, no. Pt 1, pp. 287-291.
Kim, G. R. ; Aronson, A. R. ; Mork, J. G. ; Cohen, B. A. ; Lehmann, C. U. / Application of a Medical Text Indexer to an online dermatology atlas. In: Medinfo. MEDINFO. 2004 ; Vol. 11, No. Pt 1. pp. 287-291.
@article{017f62506f744e7db6de2e9bebb97f25,
title = "Application of a Medical Text Indexer to an online dermatology atlas.",
abstract = "Clinical dermatology cases are presented as images and semi-structured text describing skin lesions and their relationships to disease. Metadata assignment to such cases is hampered by lack of a standardized dermatology vocabulary and facilitated methods for indexing legacy collections. In this pilot study descriptive clinical text from Dermatlas, a Web-based repository of dermatology cases, was indexed to Medical Subject Heading (MeSH) terms using the National Library of Medicine's Medical Text Indexer (MTI). The MTI is an automated text processing system that derives ranked lists of MeSH terms to describe the content of medical journal citations using knowledge from the Unified Medical Language System (UMLS) and from MEDLINE. For a representative, random sample of 50 Dermatlas cases, the MTI frequently derived MeSH indexing terms that matched expert-assigned terms for Diagnoses (88{\%}), Lesion Types (72{\%}), and Patient Characteristics (Gender and Age Groups, 62{\%} and 84{\%} respectively). This pilot demonstrates the potential for extending the MTI to automate indexing of clinical case presentations and for using MeSH to describe aspects of clinical dermatology.",
author = "Kim, {G. R.} and Aronson, {A. R.} and Mork, {J. G.} and Cohen, {B. A.} and Lehmann, {C. U.}",
year = "2004",
language = "English (US)",
volume = "11",
pages = "287--291",
journal = "Medinfo. MEDINFO",
number = "Pt 1",

}

TY - JOUR

T1 - Application of a Medical Text Indexer to an online dermatology atlas.

AU - Kim, G. R.

AU - Aronson, A. R.

AU - Mork, J. G.

AU - Cohen, B. A.

AU - Lehmann, C. U.

PY - 2004

Y1 - 2004

N2 - Clinical dermatology cases are presented as images and semi-structured text describing skin lesions and their relationships to disease. Metadata assignment to such cases is hampered by lack of a standardized dermatology vocabulary and facilitated methods for indexing legacy collections. In this pilot study descriptive clinical text from Dermatlas, a Web-based repository of dermatology cases, was indexed to Medical Subject Heading (MeSH) terms using the National Library of Medicine's Medical Text Indexer (MTI). The MTI is an automated text processing system that derives ranked lists of MeSH terms to describe the content of medical journal citations using knowledge from the Unified Medical Language System (UMLS) and from MEDLINE. For a representative, random sample of 50 Dermatlas cases, the MTI frequently derived MeSH indexing terms that matched expert-assigned terms for Diagnoses (88%), Lesion Types (72%), and Patient Characteristics (Gender and Age Groups, 62% and 84% respectively). This pilot demonstrates the potential for extending the MTI to automate indexing of clinical case presentations and for using MeSH to describe aspects of clinical dermatology.

AB - Clinical dermatology cases are presented as images and semi-structured text describing skin lesions and their relationships to disease. Metadata assignment to such cases is hampered by lack of a standardized dermatology vocabulary and facilitated methods for indexing legacy collections. In this pilot study descriptive clinical text from Dermatlas, a Web-based repository of dermatology cases, was indexed to Medical Subject Heading (MeSH) terms using the National Library of Medicine's Medical Text Indexer (MTI). The MTI is an automated text processing system that derives ranked lists of MeSH terms to describe the content of medical journal citations using knowledge from the Unified Medical Language System (UMLS) and from MEDLINE. For a representative, random sample of 50 Dermatlas cases, the MTI frequently derived MeSH indexing terms that matched expert-assigned terms for Diagnoses (88%), Lesion Types (72%), and Patient Characteristics (Gender and Age Groups, 62% and 84% respectively). This pilot demonstrates the potential for extending the MTI to automate indexing of clinical case presentations and for using MeSH to describe aspects of clinical dermatology.

UR - http://www.scopus.com/inward/record.url?scp=21644450423&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=21644450423&partnerID=8YFLogxK

M3 - Article

C2 - 15360820

AN - SCOPUS:21644450423

VL - 11

SP - 287

EP - 291

JO - Medinfo. MEDINFO

JF - Medinfo. MEDINFO

IS - Pt 1

ER -