A Novel Fuzzy-Genetic Differential Evolutionary Algorithm for Optimization of A Fuzzy Expert Systems Applied to Heart Disease Prediction

This study presents a novel intelligent Fuzzy Genetic Differential Evolutionary model for the optimization of a fuzzy expert system applied to heart disease prediction in order to reduce the risk of heart disease. To this end, a fuzzy expert system has been proposed for the prediction of heart disease. The proposed model can be used as a tool to assist physicians. In order to: (1) tune the parameters of the membership function of the fuzzy expert system, (2) improve its performance and (3) increase its accuracy, the Genetic Algorithm combined with the Differential Evolution Algorithm has been applied to the fuzzy expert system. The proposed hybrid models, Fuzzy-GA, Fuzzy-DE, and Fuzzy-GA-DE were evaluated using ROC curve analysis and 10- fold cross-validation methods. In order to evaluate and validate the performance of the model, we applied it to a dataset including 380 samples collected from Parsian Hospital in Karaj. According to the results, the accuracy of the fuzzy expert system was 85.52% that has increased to 97.93% after to apply the hybrid Fuzzy-GA model and has increased to 97.67% after to apply the hybrid Fuzzy-DE model. Moreover, these hybrid models have improved the accuracy of the fuzzy expert system significantly. The ability to interpret the results in the fuzzy expert system and the high accuracy of the hybrid evolutionary models is very promising for the early prediction of heart disease and the provision of necessary care.