Critical Analysis of Heart Attack Disease Prediction Using Supervised Learning Algorithms

Heart attack occurs when something stops the blood flow to your heart therefore it can’t receive the oxygen it needs. Recent studies show that the number of deaths due to heart attacks have increased seriously, and majority of the deaths are mainly due to sudden heart attacks. This study's primary goal is to anticipate heart attacks before they happen, in order to lower the risk of death and lead happier lives. The goal of this work is to create a system that can forecast heart attacks and, using machine learning techniques, pinpoint their underlying causes. Identification and detection of heart disorders are the key challenges. While there are several methods available to help predict heart disease, they are either expensive or inefficient at determining the likelihood of heart disease. Early detection can lower the mortality rate and effects of heart illness. Nevertheless, daily patient monitoring is still not realistic. Since there is a lot of data in the current world, we will utilise a range of machine learning techniques to examine the data for hidden impacts. In the proposed study, we can clearly see that Logistic Regression outperformed KNN, SVM ,Decision Tree, and Random Forest Algorithms in terms of precision, f1 score ,recall, support and accuracy.