Enhanced Machine Learning Model for Heart Disease Prediction with Naive Bayes, Warm, and Personalized Health Recommendations

This study presents a comprehensive approach to predicting cardiac illness through Weighted Association Rule Mining (WARM) and Naive Bayes (NB) algorithms. Addressing data preprocessing challenges like missing values and outliers, it employs a diverse dataset encompassing crucial health attributes such as age, gender, blood pressure, and cholesterol levels. Alongside model training and performance evaluation, a novel health recommendation feature is introduced, leveraging predictive models to offer personalized lifestyle guidance for heart health optimization. This enhancement underscores the study's commitment to holistic healthcare solutions, bridging predictive analytics with actionable insights for proactive cardiovascular care.