An overview of statistical methods for the classification and retrieval of patient events

Research output: Contribution to journalArticle

Abstract

Statistical methods that can support text retrieval are becoming an increasing focus of medical informatics activities. We overview our adaptation of existing knowlege sources to create pseudo-documents for concept based latent semantic indexing. Experience demonstrated this tack of limited practical value, since retrieval performance was invariably unsatisfactory. We discovered this was due in part to the introduction of a vocabulary gap between the queries and the cases we sought to retrieve. In part to address this problem, and to avail our large body of humanly coded text as a knowledge source, we developed a least squares fit alternative for the computer assisted indexing and retrieval of biomedical texts. This technique demonstrates equivalent or superior retrieval performance when compared to all other textual retrieval techniques. It does not depend upon elaborate knowledge bases, lexicons, or thesauri. It is a promising technique for classifying and retrieving the large volumes of clinical text.

Original languageEnglish (US)
Pages (from-to)104-110
Number of pages7
JournalMethods of Information in Medicine
Volume34
Issue number1-2
StatePublished - 1995
Externally publishedYes

Fingerprint

Controlled Vocabulary
Medical Informatics
Knowledge Bases
Vocabulary
Least-Squares Analysis
Semantics

Keywords

  • Indexing
  • Statistical methods
  • Text retrieval

ASJC Scopus subject areas

  • Health Informatics
  • Nursing(all)
  • Health Information Management

Cite this

An overview of statistical methods for the classification and retrieval of patient events. / Chute, Christopher; Yang, Y.

In: Methods of Information in Medicine, Vol. 34, No. 1-2, 1995, p. 104-110.

Research output: Contribution to journalArticle

@article{3a1a20e55878416e9e5259b5047f0fc5,
title = "An overview of statistical methods for the classification and retrieval of patient events",
abstract = "Statistical methods that can support text retrieval are becoming an increasing focus of medical informatics activities. We overview our adaptation of existing knowlege sources to create pseudo-documents for concept based latent semantic indexing. Experience demonstrated this tack of limited practical value, since retrieval performance was invariably unsatisfactory. We discovered this was due in part to the introduction of a vocabulary gap between the queries and the cases we sought to retrieve. In part to address this problem, and to avail our large body of humanly coded text as a knowledge source, we developed a least squares fit alternative for the computer assisted indexing and retrieval of biomedical texts. This technique demonstrates equivalent or superior retrieval performance when compared to all other textual retrieval techniques. It does not depend upon elaborate knowledge bases, lexicons, or thesauri. It is a promising technique for classifying and retrieving the large volumes of clinical text.",
keywords = "Indexing, Statistical methods, Text retrieval",
author = "Christopher Chute and Y. Yang",
year = "1995",
language = "English (US)",
volume = "34",
pages = "104--110",
journal = "Methods of Information in Medicine",
issn = "0026-1270",
publisher = "Schattauer GmbH",
number = "1-2",

}

TY - JOUR

T1 - An overview of statistical methods for the classification and retrieval of patient events

AU - Chute, Christopher

AU - Yang, Y.

PY - 1995

Y1 - 1995

N2 - Statistical methods that can support text retrieval are becoming an increasing focus of medical informatics activities. We overview our adaptation of existing knowlege sources to create pseudo-documents for concept based latent semantic indexing. Experience demonstrated this tack of limited practical value, since retrieval performance was invariably unsatisfactory. We discovered this was due in part to the introduction of a vocabulary gap between the queries and the cases we sought to retrieve. In part to address this problem, and to avail our large body of humanly coded text as a knowledge source, we developed a least squares fit alternative for the computer assisted indexing and retrieval of biomedical texts. This technique demonstrates equivalent or superior retrieval performance when compared to all other textual retrieval techniques. It does not depend upon elaborate knowledge bases, lexicons, or thesauri. It is a promising technique for classifying and retrieving the large volumes of clinical text.

AB - Statistical methods that can support text retrieval are becoming an increasing focus of medical informatics activities. We overview our adaptation of existing knowlege sources to create pseudo-documents for concept based latent semantic indexing. Experience demonstrated this tack of limited practical value, since retrieval performance was invariably unsatisfactory. We discovered this was due in part to the introduction of a vocabulary gap between the queries and the cases we sought to retrieve. In part to address this problem, and to avail our large body of humanly coded text as a knowledge source, we developed a least squares fit alternative for the computer assisted indexing and retrieval of biomedical texts. This technique demonstrates equivalent or superior retrieval performance when compared to all other textual retrieval techniques. It does not depend upon elaborate knowledge bases, lexicons, or thesauri. It is a promising technique for classifying and retrieving the large volumes of clinical text.

KW - Indexing

KW - Statistical methods

KW - Text retrieval

UR - http://www.scopus.com/inward/record.url?scp=0028951240&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028951240&partnerID=8YFLogxK

M3 - Article

C2 - 9082119

AN - SCOPUS:0028951240

VL - 34

SP - 104

EP - 110

JO - Methods of Information in Medicine

JF - Methods of Information in Medicine

SN - 0026-1270

IS - 1-2

ER -