An Accurate Ensemble Machine Learning Model with Precision Engineering for Chronic Coronary Artery Disease Prognosis

In the US, ischemic heart disease (IHD) and CAD, also known as chronic heart disease (CHD), are major causes of death for people of all racial and ethnic backgrounds, regardless of gender. Cardiovascular disease claims the lives of someone every 33 seconds, which is a very high rate of occurrence. Particularly, coronary heart diseases are responsible for a significant percentage of these deaths—375,476 people in 2021 alone. Important risk factors for heart disease include smoking, and a host of other illnesses and lifestyle choices, including diabetes, obesity, poor eating habits, inactivity, and excessive alcohol use. In the process of creating effective screening tools and estimating the risk of CHD, machine learning (ML) approaches have gained popularity. Using a dataset from Kaggle, this work presents an ensemble machine learning model for CHD prediction with an accuracy of around 94.06%. The random forest algorithm, which has been trained using copious clinical and demographic data related to CHD patients, is the main working mechanism of the model. Through the use of an ensemble approach—which combines many machine learning techniques—the suggested model outperforms individual approaches in terms of prediction. This emphasizes how combining different machine learning techniques may improve accuracy. According to the study's conclusions, the ensemble model has potential as a useful tool for early CHD diagnosis and treatment, which would lessen the disease's effects on patients and healthcare systems. Keywords: Coronary heart disease (CHD), extra trees (ET), Support Vector Machine (SVM), ischemic heart disease (IHD), Machine Learning (ML).