Heart Disease Prediction Using XGBoost

Over the years, researchers have developed several expert systems to help cardiologists improve the diagnostic process by predicting heart diseases early on. Most of the available machine learning approaches are complicated and they were generally created for use with large data. Unfortunately, these approaches can't be effectively used in the scenarios with small data to train the model. In this view, this paper proposes a simple and effective diagnostic system that uses Extreme Gradient Boosting (XGBoost) with feature selection algorithm to predict heart disease in case of dataset with less records. Proper hyperparameter tuning is vital for the effective deployment of any classifier. To improve the hyperparameters of XGBoost, grid search is employed, which is an optimal method for hyperparameter optimization. Also, the One-Hot (OH) encoding approach is employed to encode categorical information in Cleveland heart disease dataset. To evaluate the proposed work, the suggested model is assessed and compared to other classifiers. The proposed model achieved an Area Under Curve (AUC) of 0.853 and prediction accuracy of 85.96%. From the experimental results, the proposed model achieved higher accuracy when compared to the other models.