Effective Prognosis of Heart Attack Using Supervised Machine Learning Algorithms

Early identification of heart attack is essential and predicting it using clinical data is a complex process due to the multifaceted nature of the disease and the diverse range of contributing factors. Machine Learning (ML) algorithms are powerful tools for predicting heart disease by analyzing patient healthcare data. This paper explores the predictive analysis of heart attack using supervised ML algorithms: Adaptive Boosting (AdaBoost), Classification and Regression Tree (CART), and Random Forest (RF) algorithms. AdaBoost is a simple ensemble algorithm that improves the performance of weak learners by focusing on misclassified instances. CART is highly interpretable and efficient in handling non-linear data relationships. Random Forest is a robust algorithm that aggregates the predictions of multiple decision trees to produce accurate predictions. A comprehensive dataset comprising various cardiovascular health indicators is used to evaluate these algorithms. Simulation results demonstrate that the proposed algorithms significantly enhance prediction accuracy upto 96%.