Semantic processing to support clinical guideline development.

Marcelo Fiszman, Eduardo Ortiz, Bruce E. Bray, Thomas C. Rindflesch

Research output: Contribution to journalArticle

Abstract

Clinical practice guidelines are one of the main resources for communicating evidence-based practice to health professionals. During guideline development, questions that express a knowledge gap are answered by finding relevant citations in MEDLINE and other biomedical databases. Determining citation relevance involves extensive manual review. We propose an automated method for finding relevant citations based on guideline question classification, semantic processing, and rules that match question classes with semantic predications. In this initial study, we focused on a pediatric cardiovascular risk factor guideline. The overall performance of the system was 40% recall, 88% precision (F0.5-score 0.71), and 98% specificity. We show that relevant and nonrelevant citations have clinically different semantic characteristics and suggest that this method has the potential to improve the efficiency of the literature review process in guideline development.

Original languageEnglish (US)
Pages (from-to)187-191
Number of pages5
JournalAMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium
StatePublished - 2008
Externally publishedYes

Fingerprint

Semantics
Guidelines
Evidence-Based Practice
Practice Guidelines
MEDLINE
Databases
Pediatrics
Health

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Semantic processing to support clinical guideline development. / Fiszman, Marcelo; Ortiz, Eduardo; Bray, Bruce E.; Rindflesch, Thomas C.

In: AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium, 2008, p. 187-191.

Research output: Contribution to journalArticle

Fiszman, Marcelo ; Ortiz, Eduardo ; Bray, Bruce E. ; Rindflesch, Thomas C. / Semantic processing to support clinical guideline development. In: AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium. 2008 ; pp. 187-191.
@article{5499464d0185488699b4fdec2ad1e759,
title = "Semantic processing to support clinical guideline development.",
abstract = "Clinical practice guidelines are one of the main resources for communicating evidence-based practice to health professionals. During guideline development, questions that express a knowledge gap are answered by finding relevant citations in MEDLINE and other biomedical databases. Determining citation relevance involves extensive manual review. We propose an automated method for finding relevant citations based on guideline question classification, semantic processing, and rules that match question classes with semantic predications. In this initial study, we focused on a pediatric cardiovascular risk factor guideline. The overall performance of the system was 40{\%} recall, 88{\%} precision (F0.5-score 0.71), and 98{\%} specificity. We show that relevant and nonrelevant citations have clinically different semantic characteristics and suggest that this method has the potential to improve the efficiency of the literature review process in guideline development.",
author = "Marcelo Fiszman and Eduardo Ortiz and Bray, {Bruce E.} and Rindflesch, {Thomas C.}",
year = "2008",
language = "English (US)",
pages = "187--191",
journal = "AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium",
issn = "1559-4076",
publisher = "American Medical Informatics Association",

}

TY - JOUR

T1 - Semantic processing to support clinical guideline development.

AU - Fiszman, Marcelo

AU - Ortiz, Eduardo

AU - Bray, Bruce E.

AU - Rindflesch, Thomas C.

PY - 2008

Y1 - 2008

N2 - Clinical practice guidelines are one of the main resources for communicating evidence-based practice to health professionals. During guideline development, questions that express a knowledge gap are answered by finding relevant citations in MEDLINE and other biomedical databases. Determining citation relevance involves extensive manual review. We propose an automated method for finding relevant citations based on guideline question classification, semantic processing, and rules that match question classes with semantic predications. In this initial study, we focused on a pediatric cardiovascular risk factor guideline. The overall performance of the system was 40% recall, 88% precision (F0.5-score 0.71), and 98% specificity. We show that relevant and nonrelevant citations have clinically different semantic characteristics and suggest that this method has the potential to improve the efficiency of the literature review process in guideline development.

AB - Clinical practice guidelines are one of the main resources for communicating evidence-based practice to health professionals. During guideline development, questions that express a knowledge gap are answered by finding relevant citations in MEDLINE and other biomedical databases. Determining citation relevance involves extensive manual review. We propose an automated method for finding relevant citations based on guideline question classification, semantic processing, and rules that match question classes with semantic predications. In this initial study, we focused on a pediatric cardiovascular risk factor guideline. The overall performance of the system was 40% recall, 88% precision (F0.5-score 0.71), and 98% specificity. We show that relevant and nonrelevant citations have clinically different semantic characteristics and suggest that this method has the potential to improve the efficiency of the literature review process in guideline development.

UR - http://www.scopus.com/inward/record.url?scp=73949145261&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=73949145261&partnerID=8YFLogxK

M3 - Article

C2 - 18999127

AN - SCOPUS:73949145261

SP - 187

EP - 191

JO - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

JF - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

SN - 1559-4076

ER -