Automated prediction of Heart disease using optimized machine learning techniques

Nowadays, heart disease is considered as one of the most significant factors of death. Several attempts have been made over the last few years to automate the diagnosis of cardiac disease. Nevertheless, the significance of machine learning has already been proved from literature studies. In our study, several machine learning algorithms such as Naive Bayes (NB), Multi-Layer Perceptron (MLP), Random Forest (RF) and Decision Tree (DT) will be compared to predict presence of heart disease using UCI data set. Several preprocessing techniques will be applied; brute force technique will be used for feature selection. Grid search mechanism will be used for parameter optimization. Experiments showed that Random Forest achieved the highest performance with the accuracy of 0.93 and AUC of 0.95.