Predicting Cardiovascular Disease with Machine Learning: An Explainable AI Approach

Abstract

Cardiovascular disease affects a huge number of individuals worldwide. Early detection and accurate risk prediction can reduce its impact. Traditional risk factors drive the urgency of developing predictive models that can effectively identify individuals at high risk. This study explores multiple machine learning techniques, including logistic regression, random forests, ensemble model and deep learning algorithms to develop an effective and explainable Cardiovascular Disease (CVD) risk prediction system. A key innovation in this work is the integration of risk stratification and Explainable AI (XAI) techniques to improve model transparency and interpretability in predictions, enabling healthcare professionals to understand the rationale behind model decisions. This is critical for gaining clinical trust and promoting the adoption of AI-driven diagnostic tools in healthcare settings.