A Comparative Study of Supervised Learning Algorithms for Heart Disease Prediction

Cardiovascular Diseases (CVD) are proven to be widespread in the population, often resulting in mortality. As per recent reports, the dramatic rise in heart attacks and cardiovascular illnesses is attributed, in part, to post-COVID symptoms, obesity, lifestyle changes brought on by the pandemic, and intense work pressure coupled with stress and hypertension. Early identification is the key to lowering the rising mortality rates from CVD. However, with limited medical facilities and lack of specialized doctors, it is difficult to continuously monitor the patients and provide consultations. At the same time, the amount of data acquired by the medical industry is so vast that it might be difficult to observe and interpret at times. Using the same data to train a machine learning algorithm, a prediction model can be developed. Such a prediction system can be effective for both doctors and patients. This research studies the different cardiovascular diseases and the risk factors. This investigates some of the most extensively used machine learning algorithms for predicting heart disease utilizing medical data and historical information. In this article, we have compared primary machine learning algorithms like Random Forest, Logistic Regression and SVM