Reduced-rule based expert system by the simplification of logic functions for the diagnosis of diabetes.

Diabetes is a chronic and complex endocrine disease with metabolic disorders caused by the imbalance between secreted and needed insulin levels. In the present study, all probabilities were examined considering ten (10) indications (2¹⁰=1024 different cases) of diabetes using medical expert system (MES), and accordingly, a truth table was established. This table was simplified by the simplification method of logic functions. 15 main rules were obtained using minimization method for Boolean Functions (BFs). These rules established rules base of ES. Subsequently, the parameters of 768 patients were compared with this ES. Accuracy rate of the estimations of MES, created as a result these comparisons, was determined as 97.13% in diabetes patients, 97% in non-diabetes patients, 96.5% in Type 1 patients, 98.26% in Type 2 patients and 97.44% in pregnant patients.