Semantic processing to support clinical guideline development.
Authors:
- 6 November 2008
- journal article
- Vol. 2008, 187-91
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.Keywords
This publication has 14 references indexed in Scilit:
- Knowledge-based Methods to Help Clinicians Find Answers in MEDLINEJournal of the American Medical Informatics Association, 2007
- Faculty Opinions recommendation of Evaluation of PICO as a knowledge representation for clinical questions.2007
- Extraction and use of linguistic patterns for modelling medical guidelinesArtificial Intelligence in Medicine, 2007
- Using outcome polarity in sentence extraction for medical question-answering.2006
- The interaction of domain knowledge and linguistic structure in natural language processing: interpreting hypernymic propositions in biomedical textJournal of Biomedical Informatics, 2003
- A knowledge-acquisition wizard to encode guidelines.2003
- Effective mapping of biomedical text to the UMLS Metathesaurus: the MetaMap program.2001
- A taxonomy of generic clinical questions: classification studyBMJ, 2000
- Developing Optimal Search Strategies for Detecting Clinically Sound Studies in MEDLINEJournal of the American Medical Informatics Association, 1994
- Evaluation of SAPHIRE: an automated approach to indexing and retrieving medical literature.1991