Development of Predictive Modeling of Heart Disease Outcomes Using XGBoost Machine Learning and Assessing the Impact of XGBoost on Heart Disease Prediction Accuracy

Now a day the increase in global death is due to heart disease or heart related issues. So, in order to reduce this global death, count early detection of heart disease is very much important. This work helps to mainly predict the possibility of heart disease. So, early detection of such disease helps to reduce the death rate. The dataset used here is Statlog dataset and it has been downloaded from Goggle. It is a publicly available dataset that has been used to build the model and XG-Boost has been used for prediction. The platform used for performing this work is Python Jupyter notebook which is an open-source web application that helps to perform data visualization, machine learning and much more. So, this work mainly focused on DBSCAN, SMOTEEN and XG-Boost. DBSCAN for detection of outliers, SMOTEEN for balancing of data and XG-Boost for prediction of heart disease.