HEART ATTACK PREDICTION SYSTEM USING MACHINE LEARNING TECHNIQUE

Cardiovascular disease is currently the leading cause of death in high-income countries and is projected to become the top global cause of death by 2030. In the United States, heart disease, including conditions like coronary heart disease, hypertension, and stroke, remains the primary cause of death. According to the American Heart Association’s 2019 update, approximately 46% of US adults, equivalent to 116.4 million people, are estimated to have hypertension based on the new 2017 Hypertension Clinical Practice Guidelines. The impact of cardiovascular disease is profound, with a person dying from CVD every 38 seconds, resulting in approximately 2,303 CVD-related deaths per day based on 2016 data. Stroke, as a critical cardiovascular event, accounts for about 389.4 deaths daily, with a stroke-related death occurring every 3.70 minutes, according to the same data. The heart’s essential function of pumping blood throughout the body makes any malfunction potentially fatal, leading to organ failure, including the brain, within minutes. Contributing factors to the rising incidence of heart-related diseases include unhealthy lifestyle choices, work-related stress, and poor dietary habits, posing a significant global health concern. According to the World Health Organization, heart-related diseases cause approximately 17.7 million deaths annually, representing 31% of all global deaths. This worrisome trend is also apparent in India, where heart-related diseases have become the leading cause of mortality. To combat the increasing rates of heart-related diseases, particularly among younger individuals, it is vital to develop an early detection system for heart stroke symptoms to prevent fatalities. This project aims to analyze heart disease datasets and utilize feature selection techniques to construct a high-accuracy model using the best-performing machine learning algorithms. By deriving valuable insights from the data, the objective is to contribute to the prevention