Heart Disease Risk Assessment using Bayesian Networks

This paper uses Bayesian Networks to display an extensive approach to heart disease risk assessment. Cardiovascular diseases (CVDs) are one of the main leading causes of death worldwide, making up 32% of all global fatalities [1]. We developed and analyzed different types of Bayesian Network models to predict and estimate the risk of heart disease based on patient data [8]. Our approach includes domain knowledge, structure learning algorithms, and feature selection techniques to create an accurate and understandable model. The final model achieves an ROC AUC score of 0.846, displaying its capability in risk prediction. We also explore practical applications of the model for medical decision support [2].