A Clinical support system for Prediction of Heart Disease using Machine Learning Techniques

Abstract

Heart disease is a leading cause of death worldwide. However, it remains difficult for clinicians to predict heart disease as it is a complex and costly task. Hence, we proposed a clinical support system for predicting heart disease to help clinicians with diagnostic and make better decisions. Machine learning algorithms such as Naïve Bayes, K-Nearest Neighbor, Support Vector Machine, Random Forest, and Decision Tree are applied in this study for predicting Heart Disease using risk factors data retrieved from medical files. Several experiments have been conducted to predict HD using the UCI data set, and the outcome reveals that Naïve Bayes outperforms using both cross-validation and train-test split techniques with an accuracy of 82.17%, 84.28%, respectively. The second conclusion is that the accuracy of all algorithm decrease after applying the cross-validation technique. Finally, we suggested multi validation techniques in prospectively collected data towards the approval of the proposed approach.