Selection of Aggregation Function in Fuzzy Inference System for Metabolic Syndrome

Metabolic syndrome (MetS) has long-term, very detrimental effects, including chronic kidney disease, cardiovascular stroke, and diabetes mellitus. Therefore, early detection of MetS is important. Numerous global health organizations have made some Syndrome diagnosis criteria, but they are still mostly in a dichotomous form. On the other hand, continuous risk score been proven to be more sensitive with less error. This study aims build Fuzzy Inference System (FIS) model. diagnostic criteria issued by NCEP-APT III used as reference for generating rules. model uses max, probor, additive functions obtain membership values result rules aggregation seven steps: 1) Identification variables; 2) Determination fuzzy sets their functions; 3) Knowledge base generation; 4) Implementation implication 5) aggregation; 6) Defuzzification; 7) Performance testing selecting best function. The findings show max function most suitable process an accuracy, sensitivity, specificity, precision value 100% according measurement results NCEP-ATP III. A between 0% 99.99% considered non-high risk, whereas indicates high risk. also ideal distribution neighborhood level criteria.