Discovery of rules for medical expert systems-rough set approach

The paper presents a systematic approach from knowledge acquisition by using a rule induction method to construct a decision support systems as follows. First, a rule induction system based on a rough set model is introduced and is applied to a database for diagnosis of headaches to extract diagnostic rules. Then, by use of the induced knowledge, an expert system which makes a differential diagnosis of headaches is developed. Finally, this expert system is evaluated at an outpatient clinic, the results of which show that the system performance is reasonable, compared with a medical expert.