AUTOMATED EXTRACTION OF MEDICAL EXPERT-SYSTEM RULES FROM CLINICAL DATABASES BASED ON ROUGH SET-THEORY

Automated knowledge acquisition is an important research issue to solv e the bottleneck problem in developing expert systems. Although many i nductive learning methods have been proposed for this purpose, most of the approaches focus only on inducing classification rules. However, medical experts also learn other information important for diagnosis f rom clinical cases. In this paper, a rule induction method is introduc ed, which extracts not only classification rules but also other medica l knowledge needed for diagnosis. This system was evaluated on three c linical databases, whose experimental results show that our proposed m ethod correctly induces diagnostic rules and estimates the statistical measures of rules. (C) 1998 Elsevier Science Inc. All rights reserved .