Cooperation between Expert Knowledge and Data Mining Discovered Knowledge

Abstract

Although expert elicited knowledge and data mining discovered knowledge appear to be completely opposite and competing solutions to the same problems, they are actually complementary concepts. Besides, together they maximize their individual qualities. This chapter highlights how each one profits from the other and illustrates their cooperation in existing systems developed in the medical domain. The authors have identified different types of cooperation that combine elicitation and data mining for knowledge acquisition, use expert knowledge to enact the knowledge discovery, use discovered knowledge to validate expert knowledge, and use discovered knowledge to improve the usability of an expert system. The chapter also describes their experience in combining expert and discovered knowledge in the development of a system for processing medical isokinetics data.