Automatic indexing and retrieval of encounter-specific evidence for point-of-care support

  • Authors:

  • Dympna M. O'Sullivan;Szymon A. Wilk;Wojtek J. Michalowski;Ken J. Farion

  • Affiliations:

  • School of Engineering and Applied Science, Aston University, Aston Triangle, Birmingham, B4 7ET, UK;Institute of Computing Science, Poznan University of Technology, Poznan, Poland;Telfer School of Management, University of Ottawa, Ottawa, Canada;Departments of Pediatrics and Emergency Medicine, University of Ottawa, Ottawa, Canada

  • Venue:
  • Journal of Biomedical Informatics
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Evidence-based medicine relies on repositories of empirical research evidence that can be used to support clinical decision making for improved patient care. However, retrieving evidence from such repositories at local sites presents many challenges. This paper describes a methodological framework for automatically indexing and retrieving empirical research evidence in the form of the systematic reviews and associated studies from The Cochrane Library, where retrieved documents are specific to a patient-physician encounter and thus can be used to support evidence-based decision making at the point of care. Such an encounter is defined by three pertinent groups of concepts - diagnosis, treatment, and patient, and the framework relies on these three groups to steer indexing and retrieval of reviews and associated studies. An evaluation of the indexing and retrieval components of the proposed framework was performed using documents relevant for the pediatric asthma domain. Precision and recall values for automatic indexing of systematic reviews and associated studies were 0.93 and 0.87, and 0.81 and 0.56, respectively. Moreover, precision and recall for the retrieval of relevant systematic reviews and associated studies were 0.89 and 0.81, and 0.92 and 0.89, respectively. With minor modifications, the proposed methodological framework can be customized for other evidence repositories.