Evaluation of biomedical text-mining systems: Lessons learned from information retrieval
Professor and Chair in the Department of Medical Informatics & Clinical Epidemiology at Oregon Health & Science University. He is well known for his work in information retrieval, particularly in health and biomedical contexts. He currently serves as Chair of the TREC Genomics Track. He has published over 100 scientific papers and is author of the book ‘Information Retrieval: A Health and Biomedical Perspective’.
William Hersh, Department of Medical Informatics & Clinical Epidemiology, Oregon Health & Science University, 3181 SW Sam Jackson Park Rd, BICC, Portland, OR 97239, USA Tel: +1 503 494 4563 Fax: +1 503 494 4551 E-mail: hersh{at}ohsu.edu
Biomedical text-mining systems have great promise for improving the efficiency and productivity of biomedical researchers. However, such systems are still not in routine use. One impediment to their development is the lack of systematic and rigorous evaluation, comparable to the approaches developed for information retrieval systems. The developers of text-mining systems need to improve both test collections for system-oriented evaluation and undertake user-oriented evaluations to determine the most effective use of their systems for their intended audience.
Keywords: biomedical text mining, information retrieval, evaluation, recall, precision, Text Retrieval Conference