An Effective Approach for Heart Diseases Prognosis Using Machine Learning Techniques

Heart disease, often called as cardiovascular illness, is a term that refers to a group of illnesses that damage the heart, most commonly manifesting as myocardial infarctions or heart failure. When the heart is unable to pump sufficient blood to satisfy the body’s needs, this is referred to as heart failure. It connects a bevy of heart disease risk variables to a critical need for accurate, reliable, and pragmatic techniques for diagnosing and controlling the condition early on. Data mining is a common technique for evaluating vast volumes of data in the healthcare sector. Researchers analyze enormous volumes of complex medical data using a range of machine learning and data mining technologies, supporting doctors in the prediction of cardiac illness. This research study discusses numerous heart disease features, as well as ensemble and boosting models based on supervised learning algorithms like CatBoost, XGBoost, LGBM, etc. The goal of this study is to forecast whether such a patient will acquire heart disease. CatBoost classifier achieves the highest accuracy and F1 score, according to the results.