EVALUATION OF THE USE OF INDUCTION IN THE DEVELOPMENT OF A MEDICAL EXPERT-SYSTEM

In an earlier study, two medical expert systems for diagnosing thyroid disorders, developed by the application of induction on a sample of p reviously diagnosed cases and on expert-generated rules, diagnosed a s et of test cases better than an expert system developed by the more tr aditional method of collaboration between a knowledge engineer and an expert. In this paper, an alternative measure of the accuracy of diagn osis of each system is used to evaluate the systems. Diagnoses for eve ry distinct case represented by a combination of indicating factors ar e compared with diagnoses that the expert made. The induced systems pr ovide diagnoses for many more distinct cases, but a much higher propor tion of these diagnoses are incorrect. It is argued that generalizing to unseen cases is an inappropriate use of induction algorithms. The s ystematic development of a decision table is a more appropriate method for devising a medical expert system. (C) 1994 Academic Press, Inc.