Diagnosis of Heart Disease Using Improved Genetic Algorithm-Based Naive Bayes Classifier

Abstract

Heart disease is one of the most common diseases all over the world. The primary objective of this investigation is to diagnosis heart disease using hybrid classification based on NaN prediction and ANOVA test (NAN-ANOVA). The anticipated system comprises of two subsets: hybrid accelerated artificial bee colony and chicken swarm optimization algorithm (AABC-CSO) for effectual feature selection, followed by a classification technique with genetic algorithm based naive bayes classifier (GA-NBC). The first system in co-operates three stages: (i) loading the numerical value from the dataset (ii) evaluating the NaN value (iii) performing ANOVA test for efficient selection using AABC-CSO optimization algorithm. In second method, GA-NBC is proposed. The heart data set obtained from UCI machine repository, and was utilized for performing the computation. An accuracy of 61.0777%, sensitivity of 31.5868%, specificity of 67.8467%, precision of 17.9505, F-measure of 23.4050, G-mean of 46.6928 and loss of about 0.4480 was achieved according to the validation scheme.