Extracting drug-drug interaction articles from MEDLINE to improve the content of drug databases.
- 1 January 2005
- journal article
- research article
- Vol. 2005, 216-20
Abstract
Drug-drug interaction systems exhibit low signal-to-noise ratios because of the amount of clinically insignificant or inaccurate information they contain. MEDLINE represents a respected source of peer-reviewed biomedical citations that potentially might serve as a valuable source of drug-drug interaction information, if relevant articles could be pinpointed effectively and efficiently. We evaluated the classification capability of Support Vector Machines as a method for locating articles about drug interactions. We used a corpus of "positive" and"negative" drug interaction citations to generate datasets composed of MeSH terms, CUI-tagged title and abstract text, and stemmed text words. The study showed that automated classification techniques have the potential to perform at least as well as PubMed in identifying drug-drug interaction articles.This publication has 8 references indexed in Scilit:
- Text Categorization Models for High-Quality Article Retrieval in Internal MedicineJournal of the American Medical Informatics Association, 2004
- Computerized Physician Order Entry and Medication Errors in a Pediatric Critical Care UnitPediatrics, 2004
- Evaluation of five full-text drug databases by pharmacy students, faculty, and librarians: do the groups agree?2004
- Learning Boolean queries for article quality filtering.2004
- HITON: a novel Markov Blanket algorithm for optimal variable selection.2003
- Drug‐Information Software for Palm Operating System Personal Digital Assistants: Breadth, Clinical Dependability, and Ease of UsePharmacotherapy: The Journal of Human Pharmacology and Drug Therapy, 2002
- Performance of Community Pharmacy Drug Interaction SoftwareJournal of the American Pharmaceutical Association, 2001
- Evaluation of Drug Interaction Document Citation in Nine On-Line Bibliographic DatabasesAnnals of Pharmacotherapy, 1997