A Dual-Stage Ensemble Machine Learning and Deep Learning Framework for Cardiovascular Disease Prediction

This study set out to determine whether ensemble machine learning techniques—Bagging, Boosting, and Stacking—combined with a deep learning benchmark, could deliver an accurate, non-invasive tool for cardiovascular disease risk prediction using routinely available clinical data. The findings confirm that this objective was achieved: all four ensemble-style classifiers and the 1D-CNN produced strong predictive performance, with the Stacking Classifier attaining perfect classification metrics (100% accuracy, precision, recall, and F1 score) by integrating Random Forest, Support Vector Machine, and Logistic Regression through a meta-learning layer, and Random Forest and XGBoost each exceeding 97% accuracy individually. Revisiting the research question posed at the outset—how readily available clinical data can be leveraged through ensemble learning to build a reliable screening tool—the results demonstrate that Stacking-based ensemble architectures are the most effective approach among those tested, followed closely by Bagging (Random Forest) and Boosting (XGBoost), while simpler Boosting variants such as AdaBoost and deep learning approaches such as the 1D-CNN, though still useful, offer comparatively lower reliability for this task. The implications of this work are twofold. Practically, it provides evidence that a carefully pre-processed, moderately sized clinical dataset combined with an appropriately chosen ensemble architecture can support a non-invasive, low-cost, and rapid cardiovascular risk-screening tool suitable for integration into clinical decision-support systems. Theoretically, it reinforces the value of combining complementary learning paradigms—variance reduction (Bagging), bias reduction (Boosting), and model diversity (Stacking)—over relying on any single algorithm. While the near-perfect results warrant cautious interpretation and further external validation, this research lays a solid foundation for future work on explainable, generalizable, and deployable machine learning systems for early cardiovascular disease detection  

1.      C. Mansoor, S. K. Chettri and H. Naleer, “Advancing Heart Disease Prediction through Synergistic Integration of Machine Learning and Deep Learning Techniques,” 2024 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI), Chennai, India, 2024, pp. 1 - 6. 2.      M. S. Gangadhar, K. V. S. Sai, S. H. S. Kumar, K. A. Kumar, M. Kavitha, and S. Aravinth, “Machine learning and deep learning techniques on accurate risk prediction of coronary heart disease,” in *Proceedings of the 2023 7th International Conference on Computing Methodologies and Communication (ICCMC)*, (2023), pp. 227–232. 3.      Ouyang, Shuge. “Research of heart disease prediction based on machine learning.” 2022 5th International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE). IEEE, 2022. 4.      A. A. Romalt and R. M. S. Kumar, “Prediction of Cardio Vascular Disease by Deep Learning and Machine Learning-A Combined Data Science Approach,” 2022 International Conference on Computer, Power and Communications (ICCPC), 2022, pp. 83 - 85, doi: 10.1109/ICCPC55978.2022.10072141. 5.      C. R. Shaker, A. Sidhartha, A. Praveena, A. Chrsity and B. Bharati, “An Analysis of Heart Disease Prediction using Machine Learning and Deep Learning Techniques,” 2022 6th International Conference on Trends in Electronics and Informatics (ICOEI), Tirunelveli, India, 2022, pp. 1484–1491, doi: 10.1109/ICOEI53556.2022.9776745. 6.      Kumar S, Thakur B. Heart Disease Prediction Using a Stacked Ensemble Learning Approach. SN Comput Sci. 2025;6:3. 7.      Sultan, S.Q.; Javaid, N.; Alrajeh, N.; Aslam, M. Machine Learning-Based Stacking Ensemble Model for Prediction of Heart Disease with Explainable AI and K-Fold Cross-Validation: A Symmetric Approach. Symmetry 2025, 17, 185. 8.      Shahid Mohammad Ganie, Pijush Kanti Dutta Pramanik, Majid Bashir Malik3, Anand Nayyar, Kyung Sup Kwak, An Improved Ensemble Learning Approach for Heart Disease Prediction Using Boosting Algorithms, CSSE, Vol.46, No.3, 2023. 9.      Abdellatif, A.; Mubarak, H., Abdellatef, H., Kanesan, J., Abdelltif, Y., Chow, C.-O., Chuah, J.H., Gheni, H.M., Kendall, G. Computational detection and interpretation of heart disease based on conditional variational auto-encoder and stacked ensemble-learning framework. Biomed. Signal Process. Control 2024, 88,105644. 10.   Ankit Saxena, Renu Sharma, and Vinod Jain, “Advanced Heart Disease Prediction System Using Hybrid Machine Learning Techniques,” 2023 5th International Conference on Computing, Communication and Intelligent Systems (ICCCIS), 2023, pp. 638 - 643.