Design of a Fuzzy System Based on Lookup Table for Diagnosis and Predicting of Metabolic Syndrome in Preschoolers, Children, and Adolescents

The purpose of this study was to provide a fuzzy system for predicting and diagnosing metabolic syndrome (MetS) in preschoolers, children, and adolescents. In this study, previous research on the factors affecting metabolic syndrome, especially in children, and adolescents, has been considered. After integrating the initial variables, a fuzzy system has been designed with 8 data on age, waist size, systole blood pressure, diastole blood pressure, body mass index (BMI), waist-to-height ratio, nutrition, and abdominal obesity. Ultimately, the system gives us an output that diagnoses the health status of a child or adolescent with MetS or predicts the possibility of a person contracting the disease in the future. The system is designed based on the data of 1300 persons participating in the fifth study of the program for monitoring and prevention of non-communicable diseases of children, and Adolescents in Tehran and Isfahan provinces that 1050 data were used as training data and 250 data as test data that used to test the rules and output of the system. After reviewing the rules and eliminating similar or contradictory rules using their degree calculation, finally, the system was designed with 45 rules, a multiplication inference engine, a single fuzzifier, and a centroid defuzzifier. Then the system was evaluated using the confusion matrix accuracy, sensitivity, and specificity. Our analysis shows that this method, with an error rate of less than 4 percent more accurate than other methods, can predict and diagnose MetS in children.