Machine Learning Approaches for Predicting Heart Attacks

Heart attacks are the leading cause of deaths worldwide. However, diagnosing them can be difficult as their symptoms can resemble those of other illnesses. There are several types of heart diseases, which makes identifying symptoms challenging. Mistaking these symptoms for something else can be very harmful to the patient. Heart disease is caused by various factors such as high bp, unhealthy diet, smoking, and lack of physical activity. New approaches are required to address heart problems since more young people are suffering from heart attacks, and current medical tools and diagnostic procedures are insufficient. This research aims to investigate the use of Machine Learning (ML) algorithms in heart attack prediction, emphasizing early detection and thereby increasing life expectancy and decreasing mortality rate. This research tries to determine the most successful models for heart attack prediction by analyzing KNN, Logistic Regression, XGBClassifier and ExtraTreeClassifier approaches. It also discusses the impact of these technologies in changing healthcare practices. The work synthesizes findings from 2016 to 2023, aiming to provide a comprehensive overview of the past works done in the field of heart attack detection and also proposes a methodology to predict heart disease using machine learning.