REASONING REQUIREMENTS FOR DIAGNOSIS OF HEART-DISEASE

Over the past dozen years, the Heart Disease Program (HDP) has been de veloped to assist physicians in reasoning about cardiovascular disorde rs. Driven by several evaluations, the inference mechanism has progres sed from a logic based model, to a Bayesian Probability Network (BPN) and finally a pseudo-Bayesian network with temporal and severity reaso ning. Though aspects of cardiovascular reasoning are handled well by B PNs, temporal reasoning, homeostatic feedback mechanisms and effects o f disease severities require additional inference strategies. This art icle discusses how these reasoning problems are handled, and deals wit h closely linked issues in building the user interface to collect deta iled cardiovascular data and provide clear explanations of diagnoses. (C) 1997 Elsevier Science B.V.