Early Detection of Coronary Heart Disease Based on Machine Learning Methods

Aim: Heart disease detection using machine learning methods has been an outstanding research topic as heart diseases continue to be a burden on healthcare systems around the world. Therefore, in this study, performances of for predictive classification coronary were compared.Material and Method: In three different models created with Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM) algorithms disease. For hyper parameter optimization, 3-repeats 10-fold repeated cross validation method was used. The performance evaluated based Accuracy, F1 Score, Specificity, Sensitivity, Positive Predictive Value, Negative Confusion Matrix (Classification matrix).Results: RF 0.929, SVM 0.897 LR 0.861 classified accuracy. F1-score, values model calculated 0.928, 0.929 respectively. Sensitivity value higher compared RF. Conclusion: Considering accurate rates Coronary disease, outperformed models. Also, had highest sensitivity value. We think that result, which high criterion order minimize overlooked patients, is clinically very important.