Naive Bayes - Random Forest Ensemble Model Analysis and Heart Disease Prediction

Abstract

Abstract: The critical task of accurately diagnosing heart disease can potentially save lives. Leveraging the UCI machine learning heart disease dataset and employing ensemble machine learning techniques, including Gausian Naive Bayes and Random Forest algorithms, the research investigates 13 primary characteristics to predict heart disease risks. The conventional machine learning approaches are utilized to analyze the dataset, unveiling correlations between features and heart infection risks. The aim is to develop a user-friendly interface, the Heart Disease Clinical Decision Support System (HDCDSS), where patients input their clinical details to receive a predictive analysis of their coronary disease. The system, built in Python with Flask and Bootstrap, provides clients with personalized reports on their heart health, enhancing diagnostic accuracy and potentiallystreamlining healthcare processes.