Decision Support System in Healthcare for Heart Disease Prediction

Heart conditions include heart failure, arrhythmias, and coronary artery disease are still among the leading causes of death in the world. Improving patient outcomes, lowering death rates, and efficiently allocating healthcare resources all depend on early identification and accurate prognosis of heart disorders. The goal of this research is to create a predictive model for cardiac problems using machine learning techniques to produce a Decision Support System (DSS). The system will be able to forecast an individual's chance of acquiring heart disease by examining a variety of risk factors and medical data. The research focuses on the use of a dataset that includes patient medical information, such as their demographics, medical history, and test results. In order to forecast accuracy, precision, and recall where the XGBoost algorithm performed well. In this work, we used many machine learning models to present a Heart Disease Prediction Support System because it will enable physicians to diagnose heart disease earlier and prevent its onset. Treatment of cardiac illnesses becomes easier with the system's outstanding performance and promising major breakthroughs in detection. The XGBoost algorithm outperforms all other models with outstanding accuracy of 93.24%, Precision of 94.2%, sensitivity of 93.4%, specificity of 92.9%, and F1 score of 93.8%.