Online Registration

ISO 9001:2015

International Journal of Innovations & Research Analysis (IJIRA) [ Vol. 6 | No. 3(II) | July - September, 2026 ]

An Optuna-Optimized Dynamic Stacked Ensemble for Cardiovascular Disease Prediction

Sunanda Budihal & Dr. Sheetalrani R Kawale

As cardiovascular disease (CVD) has become a growing burden, the need for strong predictive models that can aid in early diagnosis and clinical decision making has become increasingly urgent. To overcome this challenge, in this work, a real world clinical dataset is obtained from Ayush Multi-speciality Hospital and Research Centre (AMSHRC), Vijayapur, karnataka(India) and a dynamic stacked ensemble model is proposed for prediction of cardiovascular diseases. The proposed approach combines the strengths of multiple machine learning models through adaptive ensemble learning to achieve accurate and reliable risk prediction. The framework uses dynamic top three model selection, hard-sample instability-aware weighting, stratified fivefold cross validation and Optuna-based Bayesian hyperparameter optimization to boost the predictive power and model robustness. Four   state-of-the-art machine learning algorithms Xgboost, Catboost, Extra Trees and Random forest   are fine-tuned and evaluated, and the top three models are joined via stacked ensemble framework. Experimental evaluation demonstrates that the proposed stacked ensemble model outperformed the individual baseline models by achieving 98.0%  accuracy, 97.4 % F1-score, 99.6% ROC-AUC and 95.8% MCC on the AMSHRC clinical dataset. These findings indicate that the developed dynamic stacked ensemble model is an effective and robust approach for cardiovascular disease prediction and has the potential to support early clinical decision-making.

Budihal, S. & Kawale, S. (2026). An Optuna-Optimized Dynamic Stacked Ensemble for Cardiovascular Disease Prediction. International Journal of Innovations & Research Analysis, 06(03(II)), 85–96. https://doi.org/10.62823/IJIRA/06.3(II).950
  1. World Health Organization, “Cardiovascular diseases (CVDs),” World Health Organization, Jul. 31, 2025.                        
  2. N. Biswas, V. Kuppili, D. R. Edla, S. Lipare, A. K. Singh, and S. Badhoni, “Machine learning-based model to predict heart disease in early stage employing different feature selection techniques,” Biomed. Res. Int., vol. 2023, Art. no. 6864343, 2023, doi: 10.1155/2023/6864343.
  3. Y. Rimal, A. Sharma, S. Pokharel, R. Rijal, P. Khanal, and B. Kandel, “Comparative analysis of heart disease prediction using logistic regression, SVM, KNN, and random forest with cross-validation,” Sci. Rep., vol. 15, Art. no. 13444, 2025, doi: 10.1038/s41598-025-93675-1.
  4. M. D. Teja and G. M. Rayalu, “Optimizing heart disease diagnosis with advanced machine learning models: A comparison of predictive performance,” BMC Cardiovasc. Disord., vol. 25, Art. no. 212, 2025, doi: 10.1186/s12872-025-04627-6.
  5. D. H. Wolpert, “Stacked generalization,” Neural Netw., vol. 5, no. 2, pp. 241–259, 1992, doi: 10.1016/S0893-6080(05)80023-1.
  6. O. Sagi and L. Rokach, “Ensemble learning: A survey,” WIREs Data Mining Knowl. Discov., vol. 8, no. 4, Art. no. e1249, 2018, doi: 10.1002/widm.1249.
  7. H. El-Sofany, B. Bouallegue, and Y. M. Abd El-Latif, “A proposed technique for predicting heart disease using machine learning algorithms and an explainable AI method,” Sci. Rep., vol. 14, Art. no. 23277, 2024, doi: 10.1038/s41598-024-74656-2.
  8. D. Rohan, G. P. Reddy, Y. V. P. Kumar, K. P. Prakash, and Ch. P. Reddy, “An extensive experimental analysis for heart disease prediction using artificial intelligence techniques,” Sci. Rep., vol. 15, Art. no. 6132, 2025, doi: 10.1038/s41598-025-90530-1.
  9. M. Qadeer, R. Ayaz, and M. I. Thohir, “Heart failure prediction through a comparative study of machine learning and deep learning models,” Eng. Proc., vol. 107, Art. no. 61, 2025, doi: 10.3390/engproc2025107061.
  10. S. Budihal, S. R. Kawale, and N. Agarwal, “A machine learning framework for heart disease prediction with feature selection and hyperparameter optimization across benchmark and real-world datasets,” Cureus J. Comput. Sci., vol. 3, no. 1, 2026, doi: 10.7759/s44389-026-00150-7.
  11. C. Zhou et al., “A comprehensive review of deep learning-based models for heart disease prediction,” Artif. Intell. Rev., vol. 57, Art. no. 263, 2024, doi: 10.1007/s10462-024-10899-9.
  12. H. He and E. A. Garcia, “Learning from imbalanced data,” IEEE Trans. Knowl. Data Eng., vol. 21, no. 9, pp. 1263–1284, Sep. 2009, doi: 10.1109/TKDE.2008.239.
  13. B. Krawczyk, “Learning from imbalanced data: Open challenges and future directions,” Prog. Artif. Intell., vol. 5, no. 4, pp. 221–232, 2016, doi: 10.1007/s13748-016-0094-0.
  14. T. Akiba, S. Sano, T. Yanase, T. Ohta, and T. Koyama, “Optuna: A next-generation hyperparameter optimization framework,” in Proc. 25th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, Anchorage, AK, USA, 2019, pp. 2623–2631, doi: 10.1145/3292500.3330701.
  15. J. Snoek, H. Larochelle, and R. P. Adams, “Practical Bayesian optimization of machine learning algorithms,” in Adv. Neural Inf. Process. Syst., vol. 25, 2012, pp. 2951–2959.
  16. T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, San Francisco, CA, USA, 2016, pp. 785–794, doi: 10.1145/2939672.2939785.
  17. L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001, doi: 10.1023/A:1010933404324.
  18. Hamid M, Rahman A, Islam M. Fine-tuned CatBoost machine learning approach for early detection of cardiovascular disease through predictive model IEEE Access, 2025, 13: 99876-99888. Doi : 10.1038/s41598-025
  19. S. Budihal, S. R. Kawale, N. Agarwal, and B. Halalli, "Feature-group-aware cardiovascular disease prediction using gated neural fusion and CatBoost-based clinical feature analysis," Cureus J. Comput. Sci., vol. 3, no. 1, 2026, doi: 10.7759/s44389-026-00068-0.
  20. P. Geurts, D. Ernst, and L. Wehenkel, “Extremely randomized trees,” Mach. Learn., vol. 63, no. 1, pp. 3–42, 2006, doi: 10.1007/s10994-006-6226-1.
  21. D. M. W. Powers, “Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation,” J. Mach. Learn. Technol., vol. 2, no. 1, pp. 37–63, 2011.
  22. R. Kohavi, “A study of cross-validation and bootstrap for accuracy estimation and model selection,” in Proc. 14th Int. Joint Conf. Artif. Intell., Montreal, QC, Canada, 1995, pp. 1137–1145.
  23. A. Tiwari, A. Chugh, and A. Sharma, “Ensemble framework for cardiovascular disease prediction,” Comput. Biol. Med., vol. 146, Art. no. 105624, 2022,

doi: 10.1016/j.compbiomed.2022.105624.

DOI:

Article DOI: 10.62823/IJIRA/06.3(II).9503

DOI URL: https://doi.org/10.62823/IJIRA/06.3(II).9503

Download Full Paper:

Download