This Article Full Text Full Text (PDF) All Versions of this Article: M1157v1 10/4/330    most recent 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 Wilcox, A. B. Articles by Hripcsak, G. Search for Related Content PubMed PubMed Citation Articles by Wilcox, A. B. Articles by Hripcsak, G.

The Role of Domain Knowledge in Automating Medical Text Report Classification

Affiliations: of the authors: Department of Medical Informatics, University of Utah, Salt Lake City, Utah (ABW); Medical Informatics, Intermountain Health Care, Salt Lake City, Utah (ABW); Department of Medical Informatics, Columbia University, New York, New York (GH), USA

Correspondence and reprints: Adam B. Wilcox, PhD, Medical Informatics, Intermountain Health Care, 4646 West Lake Park Blvd., Salt Lake City, UT 84120; e-mail: <lpawilco{at}ihc.com>

Received for publication: 05/14/02; accepted for publication: 03/03/03.

Objective: To analyze the effect of expert knowledge on the inductive learning process in creating classifiers for medical text reports.

Design: The authors converted medical text reports to a structured form through natural language processing. They then inductively created classifiers for medical text reports using varying degrees and types of expert knowledge and different inductive learning algorithms. The authors measured performance of the different classifiers as well as the costs to induce classifiers and acquire expert knowledge.

Measurements: The measurements used were classifier performance, training-set size efficiency, and classifier creation cost.

Results: Expert knowledge was shown to be the most significant factor affecting inductive learning performance, outweighing differences in learning algorithms. The use of expert knowledge can affect comparisons between learning algorithms. This expert knowledge may be obtained and represented separately as knowledge about the clinical task or about the data representation used. The benefit of the expert knowledge is more than that of inductive learning itself, with less cost to obtain.

Conclusion: For medical text report classification, expert knowledge acquisition is more significant to performance and more cost-effective to obtain than knowledge discovery. Building classifiers should therefore focus more on acquiring knowledge from experts than trying to learn this knowledge inductively.

This article has been cited by other articles:

				N. K. Mishra, D. M. Cummo, J. J. Arnzen, and J. Bonander A Rule-based Approach for Identifying Obesity and Its Comorbidities in Medical Discharge Summaries J. Am. Med. Inform. Assoc., July 1, 2009; 16(4): 576 - 579. [Abstract] [Full Text] [PDF]

				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]