This Article Full Text Full Text (PDF) Submit a response Alert me when this article is cited Alert me when eLetters are posted Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by Aronow, D. B. Articles by Croft, W. B. Search for Related Content PubMed PubMed Citation Articles by Aronow, D. B. Articles by Croft, W. B.

Ad Hoc Classification of Radiology Reports

University of Massachusetts, Amherst, Massachusetts.

Corresdpondence and reprints: David B. Aronow, MD, MPH, P.O. Box 9657, North Amherst, MA 01059. Reprints: Center for Intelligent Information Retrieval, University of Massachusetts, Amherst, MA 01003. e-mail: <david{at}aronow.com >.

Received for publication: 01/07/99; accepted for publication: 04/21/99.

Objective: The task of ad hoc classification is to automatically place a large number of text documents into nonstandard categories that are determined by a user. The authors examine the use of statistical information retrieval techniques for ad hoc classification of dictated mammography reports.

Design: The authors' approach is the automated generation of a classification algorithm based on positive and negative evidence that is extracted from relevance-judged documents. Test documents are sorted into three conceptual bins: membership in a user-defined class, exclusion from the user-defined class, and uncertain. Documentation of absent findings through the use of negation and conjunction, a hallmark of interpretive test results, is managed by expansion and tokenization of these phrases.

Measurements: Classifier performance is evaluated using a single measure, the F measure, which provides a weighted combination of recall and precision of document sorting into true positive and true negative bins.

Results: Single terms are the most effective text feature in the classification profile, with some improvement provided by the addition of pairs of unordered terms to the profile. Excessive iterations of automated classifier enhancement degrade performance because of overtraining. Performance is best when the proportions of relevant and irrelevant documents in the training collection are close to equal. Special handling of negation phrases improves performance when the number of terms in the classification profile is limited.

Conclusions: The ad hoc classifier system is a promising approach for the classification of large collections of medical documents. NegExpander can distinguish positive evidence from negative evidence when the negative evidence plays an important role in the classification.

This article has been cited by other articles:

				S. V.S. Pakhomov, J. D. Buntrock, and C. G. Chute Automating the Assignment of Diagnosis Codes to Patient Encounters Using Example-based and Machine Learning Techniques J. Am. Med. Inform. Assoc., September 1, 2006; 13(5): 516 - 525. [Abstract] [Full Text] [PDF]

				B. Hazlehurst, H. R. Frost, D. F. Sittig, and V. J. Stevens MediClass: A System for Detecting and Classifying Encounter-based Clinical Events in Any Electronic Medical Record J. Am. Med. Inform. Assoc., September 1, 2005; 12(5): 517 - 529. [Abstract] [Full Text] [PDF]

				A. B. Wilcox and G. Hripcsak The Role of Domain Knowledge in Automating Medical Text Report Classification J. Am. Med. Inform. Assoc., July 1, 2003; 10(4): 330 - 338. [Abstract] [Full Text] [PDF]

				D. W. Bates, R. S. Evans, H. Murff, P. D. Stetson, L. Pizziferri, and G. Hripcsak Detecting Adverse Events Using Information Technology J. Am. Med. Inform. Assoc., March 1, 2003; 10(2): 115 - 128. [Abstract] [Full Text] [PDF]

				P. G. Mutalik, A. Deshpande, and P. M. Nadkarni Use of General-purpose Negation Detection to Augment Concept Indexing of Medical Documents: A Quantitative Study Using the UMLS J. Am. Med. Inform. Assoc., November 1, 2001; 8(6): 598 - 609. [Abstract] [Full Text] [PDF]