Evaluating the Accuracy of Random Forest , Naive Bayes Classifier and KNN Algorithms for Heart Attack Monitoring

Abstract

Heart attack remains a leading cause of mortality worldwide. Early detection and intervention are crucial for improving patient outcomes. This paper investigates the application of two machine learning algorithms, Random Forest Naive Bayes Classifier and K-Nearest Neighbors (KNN), for heart attack monitoring and compares their accuracy in predicting heart attack events. We analyze a publicly available heart disease dataset, employing both algorithms to build predictive models. The performance of each model is evaluated using metrics such as accuracy, sensitivity, and specificity. The study aims to determine which algorithm demonstrates superior accuracy in identifying heart attacks, potentially aiding in the development of effective heart attack monitoring systems. This research paper explores the efficacy of two widely used machine learning algorithms—Random Forest Naive Bayes Classifier and K-Nearest Neighbors (KNN)—in the context of heart attack prediction. Utilizing a comprehensive, publicly accessible dataset on heart disease, this study constructs and compares predictive models using both algorithms. Each model's effectiveness is rigorously assessed through key performance indicators including accuracy, sensitivity (true positive rate), and specificity (true negative rate). By determining the most accurate predictive algorithm, this research contributes to the ongoing efforts in medical informatics to develop robust, reliable heart attack monitoring systems that could eventually be integrated into clinical settings to save lives. The ultimate goal of this comparison is to identify the most effective algorithm for heart attack prediction, providing valuable insights that could inform the design and implementation of future healthcare technologies aimed at heart disease prevention and management.