Cardiovascular disease is one of the major causes of mortality worldwide, creating a strong need for reliable computational approaches for early risk prediction. Machine learning methods can identify complex relationships among demographic, physiological, biochemical, and lifestyle variables; however, their usefulness in healthcare depends not only on predictive performance but also on transparency, reliability, and integration with clinical workflows. This paper presents an explainable machine learning framework for cardiovascular disease prediction that combines multiple classification models with global and local explanation mechanisms. Random Forest, XGBoost, Support Vector Machine, and Logistic Regression are evaluated using a structured model development and validation framework. The system incorporates stratified cross-validation, independent testing, model performance analysis, and explainability using SHAP and LIME. SHAP is used to identify important predictive factors at the global level, while LIME provides patient-specific explanations for individual predictions. The framework is implemented as a secure web-based clinical decision-support platform with role-based authentication, patient record management, diagnostic history, audit logging, and automated report generation. Experiments use 70,000 anonymized cardiovascular disease records containing demographic, physiological, biochemical, and lifestyle attributes. The implemented system previously demonstrated a maximum reported accuracy of 94.2% using Random Forest with an AUC of 0.97. The evaluation framework further examines precision, recall, F1-score, AUROC, confusion matrices, model stability, and inference performance. The results demonstrate the potential of combining predictive modeling and explainability within an integrated healthcare platform while highlighting the importance of external and prospective clinical validation before real-world deployment.

Mrs. Manjula K, Niveditha G M, Chitra G S, Amith Baskar, Maaz Ahamed, "A Validation-Aware Explainable Machine Learning Framework for Cardiovascular Disease Prediction" International Journal of Computer Science and Engineering Development, V1(4): Page(9-24) September - October 2026. ISSN: 3139-0862. www.ijcsed.com. Published by Scientific and Academic Research Publishing.