SUPPORTING MULTILEVEL MEDICAL-EDUCATION WITH KNOWLEDGE-BASED SYSTEMS

Knowledge-based systems for medicine have enjoyed minimal success in d eveloping countries as end-user systems. The reasons for this are comp lex. As funding agencies understandably tend to err on the side of cau tion, and knowledge-based systems are still (despite an almost 40 year history) seen as a new and untried technology, few have been implemen ted. Of those which have, most are inappropriately simple and thus do not fit in with the real-life clinical environment. In contrast to the sophisticated systems in use in developed countries which reflect a m ature technology, the use of knowledge-based systems in medicine in de veloping countries has primarily revolved around simple 'expert' syste ms, where the program functions more as a 'guru' than as a support fun ction. We propose the more appropriate use of these systems as educati onal tools in medicine. In this discussion paper we describe a multi-l evel programme to support medical education, focusing on patient infor mation systems involving natural language generation, decision-support systems as educational aids for primary health-care workers and model -based reasoning tools which allow exploratory learning for physicans in training. Throughout this paper we refer to Knowledge-Based Medical Education Systems as KBMES.