Rethinking information delivery: using a natural language processing application for point-of-care data discovery

• Published in: Journal of the Medical Library Association Vol. 100; no. 2; pp. 113 - 120
• Main Authors: WORKMAN, T. Elizabeth, STODDART, Joan M
• Format: Journal Article
• Language: English
• Published: Chicago, IL Medical Library Association 01.04.2012; University Library System, University of Pittsburgh
• Subjects: Algorithms; Coronary Artery Disease - prevention & control; Data Display; Decision support systems; Decision Support Techniques; Exact sciences and technology; Health care; Humans; Information and communication sciences; Information Dissemination - methods; Information retrieval; Information science. Documentation; Information Storage and Retrieval - methods; Libraries; Library and information science. General aspects; Malaria - prevention & control; MEDLINE; MEDLINE - organization & administration; National Library of Medicine (U.S.); Natural Language Processing; Online health care information services; Pancreatitis - prevention & control; Pilot Projects; Pneumonia; Point-of-Care Systems; Sciences and techniques of general use; Semantics; Studies; United States; Use and user studies. Information needs; User-Computer Interface; United States; Database; Natural language; Language processing; Use study; Semantics; Information dissemination
• ISSN: 1536-5050; 1558-9439
• DOI: 10.3163/1536-5050.100.2.009

This paper examines the use of Semantic MEDLINE, a natural language processing application enhanced with a statistical algorithm known as Combo, as a potential decision support tool for clinicians. Semantic MEDLINE summarizes text in PubMed citations, transforming it into compact declarations that are filtered according to a user's information need that can be displayed in a graphic interface. Integration of the Combo algorithm enables Semantic MEDLINE to deliver information salient to many diverse needs. The authors selected three disease topics and crafted PubMed search queries to retrieve citations addressing the prevention of these diseases. They then processed the citations with Semantic MEDLINE, with the Combo algorithm enhancement. To evaluate the results, they constructed a reference standard for each disease topic consisting of preventive interventions recommended by a commercial decision support tool. Semantic MEDLINE with Combo produced an average recall of 79% in primary and secondary analyses, an average precision of 45%, and a final average F-score of 0.57. This new approach to point-of-care information delivery holds promise as a decision support tool for clinicians. Health sciences libraries could implement such technologies to deliver tailored information to their users.