DECIPHERING CARDIAC HEALTH: A DEEP DIVE INTO MACHINE LEARNING FOR PREDICTIVE HEART DISEASE MODELING

Abstract

Heart disease is a grave concern that affects millions across the globe. Preventive healthcare relies on timely exposure and accurate prediction of heart disease This research paper examines the practice of machine learning algorithms to envisage heart disease, leveraging diverse datasets and advanced analytical techniques. The study begins with a thorough review of existing literature on ML-based heart disease estimation models, highlighting the strengths and confines of various algorithms. Subsequently, a comprehensive dataset comprising demographic, clinical, and lifestyle factors is employed for model development. The research focuses on popular ML algorithms such as Random forests, KNN, SVM, and Neural Networks, comparing their performance in terms of sensitivity, specificity, and overall accurate results published will vary by the datasets, sizes, and many other features [1] Cardiovascular diseases (CVDs) refer to a group of medical conditions that have a control on the heart and blood vessels. It's important to be aware of the conditions that can affect our hearts and overall health. Among these are coronary heart disease, cerebrovascular disease, rheumatic heart disease, and other related ailments. According to WHO, CVDs are the major reason for death around the world, claiming an estimated 17.9 million lives each year.