Machine learning for the evaluation of the presence of heart disease

Currently, heart diseases are prevalent in the population. Machine learning methods may help in the identification of heart diseases in the different people with the analysis of various features of heart rate, such as PPE, spread, spread2, MDVP:Fo(Hz), MDVP:Shimmer, MDVP:Shimmer(dB), Shimmer:APQ3, Shimmer:APQ5, MDVP:APQ, Shimmer:DDA, DFA, RPDE, D2, MDVP:Fhi(Hz), MDVP:Flo(Hz), NHR, HNR, MDVP:Jitter(Abs), MDVP:Jitter(%), MDVP:RAP, MDVP:PPQ, and Jitter:DDP. The analysis was performed with the dataset from the UCI Machine learning repository from the Center for Machine Learning and Intelligent Systems. This paper proposes the use of different methods, such as Neural Network, Decision Tree, k-Nearest Neighbor (kNN), Combined nomenclature (CN2) rule inducer, Support Vector Machine (SVM), and Stochastic Gradient Descent (SGD). The best results on the 20-fold Cross-validation and the 10-fold Cross-validation are reported by DT and SVM methods (87.69%). Also, the best results on the 5-fold Cross-validation are reported by SGD (87.69%).