Heart Disease Prediction Using Hybrid Genetic Fuzzy Model

摘要: The objective of the work is to diagnose heart disease using computing techniques like genetic algorithm and fuzzy logic. system would help doctors automate diagnosis enhance medical care. In this paper a hybrid genetic-fuzzy designed. used for stochastic search that provides optimal solution feature selection problem. relevant features selected from dataset diagnosing develop classification model inference system. rules are generated sample data. Among entire rule set important subset algorithm. proposed uses benefits algorithms effective prediction in patients. sex, serum cholesterol (chol), maximum rate achieved (thalach), Exercise induced angina (exang), ST depression by exercise relative rest (oldpeak), number major vessels coloured (ca) thal value. Fuzzification Fuzzy Gaussian membership function defuzzification centroid method improves performance has been evaluated metrics accuracy, specificity, sensitivity, confusion matrix proving efficiency work. obtained accuracy 86% stratified k fold technique with values specificity sensitivity as .90 .80 respectively. attributes reduced 13 7 available UCI Machine learning repository. When compared existing increased 1.54%. named GAFL called Genetic Algorithm Logic prediction. It easy build thereby providing an option be hospitals centers aid physicians.