ACQUIRING BACKGROUND KNOWLEDGE FOR MACHINE LEARNING USING FUNCTION DECOMPOSITION - A CASE-STUDY IN RHEUMATOLOGY

Domain or background knowledge is often needed in order to solve diffi cult problems of learning medical diagnostic rules. Earlier experiment s have demonstrated the utility of background knowledge when learning rules for early diagnosis of rheumatic diseases. A particular form of background knowledge comprising typical co-occurrences of several grou ps of attributes was provided by a medical expert. This paper explores the possibility of automating the process of acquiring background kno wledge of this kind and studies the utility of such methods in the pro blem domain of rheumatic diseases. A method based on function decompos ition is proposed that identifies typical co-occurrences for a given s et of attributes. The method is evaluated by comparing the typical co; occurrences it identifies as well as their contribution to the perform ance of machine learning algorithms, to the ones provided by a medical expert. (C) 1998 Elsevier Science B.V. All rights reserved.