Fuzzy expert system for metabolic control in patients with type 2 diabetes mellitus

Abstract

The objective of this study was to develop a Fuzzy Expert System (FES) to help doctors evaluate the metabolic control in patients with Type 2 Diabetes Mellitus (T2DM). In this research work, normality tests were performed on 90 data in two variables. Later, confidence intervals (CI) were applied on the data for estimating the mean. Sixty tests were performed on the results, using the expert team’s knowledge, and they were compared with those estimated by the FES using the same cases. It was observed that the system succeeded in up to 93.33% of the cases. Response surface methodology shows that the variables Age, BMI and Psychological stress had a greater impact in this study. In conclusion, Metabolic control in patients with T2DM is a complicated work for doctors, because it implies multiple risk factors; for this reason, it is easy to prescribe wrong treatments. This problem includes uncertainty and inaccuracy, so the use of a FES is recommended to address this problem.