Abstract
Information gathering in medicine generally follows a set of sequence: an interview with the patient, an examination, and one or more laboratory tests to support the working diagnosis. Building a knowledge base from observing a medical examination, however, is risky. Medical decision-making relies on imprecise information gathered in a variety of ways and interpreted in a largely intuitive fashion. This paper proposes a novel method that integrates neural network and expert system paradigms to produce an automated knowledge acquisition system. This system will produce symbolic knowledge from medical data automatically.