EVALUATING 4 DIAGNOSTIC METHODS WITH ACUTE ABDOMINAL-PAIN CASES

Contemporary work in medical decision support is characterized by a mu ltitude of methods. To investigate their relative strengths and weakne sses, we built four diagnostic expert systems based on different metho ds (Bayes, case-based classification, heuristic classification) for an alysis of the same set of 1254 cases of acute abdominal pain previousl y documented in a prospective multicenter study. The results of the co mparative evaluation indicate that differences in overall performance are relatively small (statistically not significant). The performance depends more on the quality of the knowledge base and the case data th an on the inference methods of the expert systems. Methods relying exc lusively on empirical knowledge (Bayes, case-based classification) ten d to have slightly higher overall performance scores due to a diagnost ic bias toward ordinary and common diseases. By contrast, methods oper ating with expert knowledge (e. g., heuristic classification) perform slightly worse overall, but are more sensitive toward uncommon (seriou s) diseases.