Analyzing the impact of feature selection methods on machine learning algorithms for heart disease prediction

The present study examines the role of feature selection methods in optimizing machine learning algorithms for predicting heart disease. The Cleveland Heart disease dataset with sixteen feature selection techniques in three categories of filter, wrapper, and evolutionary were used. Then seven algorithms Bayes net, Naïve Bayes (BN), multivariate linear model (MLM), Support Vector Machine (SVM), logit boost, j48, and Random Forest were applied to identify the best models for heart disease prediction. Precision, F-measure, Specificity, Accuracy, Sensitivity, ROC area, and PRC were measured to compare feature selection methods' effect on prediction algorithms. The results demonstrate that feature selection resulted in significant improvements in model performance in some methods (e.g., j48), whereas it led to a decrease in model performance in other models (e.g. MLP, RF). SVM-based filtering methods have a best-fit accuracy of 85.5. In fact, in a best-case scenario, filtering methods result in + 2.3 model accuracy. SVM-CFS/information gain/Symmetrical uncertainty methods have the highest improvement in this index. The filter feature selection methods with the highest number of features selected outperformed other methods in terms of models' ACC, Precision, and F-measures. However, wrapper-based and evolutionary algorithms improved models' performance from sensitivity and specificity points of view.