Combining relevance assignment with quality of the evidence to support guideline development

Marcelo Fiszman, Bruce E. Bray, Dongwook Shin, Halil Kilicoglu, Glen C. Bennett, Olivier Bodenreider, Thomas C. Rindflesch

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Clinical practice guidelines are used to disseminate best practice to clinicians. Successful guidelines depend on literature that is both relevant to the questions posed and based on high quality research in accordance with evidence-based medicine. Meeting these standards requires extensive manual review. We describe a system that combines symbolic semantic processing with a statistical method for selecting both relevant and high quality studies. We focused on a cardiovascular risk factor guideline, and the overall performance of the system was 56% recall, 91% precision (F 0.5 -score 0.81). If quality of the evidence is not taken into account, performance drops to 62% recall, 79% precision (F 0.5 -score 0.75). We suggest that this system can potentially improve the efficiency of the literature review process in guideline development.

Original languageEnglish (US)
Title of host publicationMedinfo 2010 - Proceedings of the 13th World Congress on Medical Informatics
PublisherIOS Press
Pages709-713
Number of pages5
EditionPART 1
ISBN (Print)9781607505877
DOIs
StatePublished - Jan 1 2010
Externally publishedYes
Event13th World Congress on Medical and Health Informatics, Medinfo 2010 - Cape Town, South Africa
Duration: Sep 12 2010Sep 15 2010

Publication series

NameStudies in Health Technology and Informatics
NumberPART 1
Volume160
ISSN (Print)0926-9630
ISSN (Electronic)1879-8365

Conference

Conference13th World Congress on Medical and Health Informatics, Medinfo 2010
Country/TerritorySouth Africa
CityCape Town
Period9/12/109/15/10

Keywords

  • Clinical guidelines
  • Machine learning
  • Natural language processing

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Fingerprint

Dive into the research topics of 'Combining relevance assignment with quality of the evidence to support guideline development'. Together they form a unique fingerprint.

Cite this