Comparative Analysis of Ensemble Learning Models for Cardiovascular Disease Using Explainable Artificial Intelligence

Syifa Alfariani; Fathoni Fathoni

doi:10.30871/jaic.v10i5.14126

Authors

Syifa Alfariani Universitas Sriwijaya
Fathoni Fathoni Universitas Sriwijaya

DOI:

https://doi.org/10.30871/jaic.v10i5.14126

Keywords:

Cardiovascular Disease, Ensemble Learning, Stacking Ensemble, Explainable Artificial Intelligence (XAI), SHAP, LIME

Abstract

Cardiovascular disease is one of the leading causes of death worldwide, making early risk detection essential to support clinical decision-making. Although machine learning models have been widely applied to cardiovascular disease prediction, challenges remain in achieving consistent performance improvements through ensemble learning and providing interpretable prediction results. This study aims to develop a cardiovascular disease risk prediction model by integrating ensemble learning and Explainable Artificial Intelligence (XAI) using the Cardiovascular Disease Dataset from Kaggle, consisting of 70,000 patient records. The research process includes Exploratory Data Analysis, data preprocessing, and model development using Random Forest, CatBoost, and LightGBM combined using a stacking approach with Logistic Regression as the meta-learner. Model interpretability was analyzed using SHAP and LIME, while performance was evaluated using accuracy, precision, recall, F1-score, and AUC-ROC. The results show that LightGBM achieved the highest accuracy of 74.13%, recall of 70.48%, and F1-score of 72.95%, while Random Forest achieved the highest precision of 76.21%. The stacking model achieved the highest AUC-ROC of 80.92%, although it did not consistently outperform individual models across all evaluation metrics. The interpretability analysis identified systolic blood pressure (ap_hi), age, cholesterol, diastolic blood pressure (ap_lo), and body mass index (BMI) as the most influential features in the predictions. This study demonstrates the integration of stacking ensemble learning and XAI using SHAP and LIME, resulting in a model with competitive predictive performance and improved interpretability for cardiovascular disease risk assessment.

Downloads

Download data is not yet available.

References

[1] T. Apriliyani, N. A. O. Pusparini, K. Karmilah, Z. Rohmah, W. A. S. Tunjung, and A. Nuriliani, “Mekanisme Penyakit Kardiovaskular terkait Penuaan,” Bioma : Berkala Ilmiah Biologi, vol. 26, no. 2, pp. 80–93, 2024, doi: 10.14710/bioma.2024.59115.

[2] World Health Organization, “Cardiovascular diseases (CVDs),” World Health Organization. Accessed: Jul. 23, 2026. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds)

[3] Kemenkes BPKP, “Potret Sehat Indonesia dari Kacamata SKI 2023,” Kemenkes.

[4] P. Shah, M. Shukla, N. H. Dholakia, and H. Gupta, “Predicting cardiovascular risk with hybrid ensemble learning and explainable AI,” Sci. Rep., vol. 15, no. 1, pp. 1–21, 2025, doi: 10.1038/s41598-025-01650-7.

[5] F. Yazdi and S. Asadi, “Enhancing Cardiovascular Disease Diagnosis: The Power of Optimized Ensemble Learning,” IEEE Access, vol. 13, no. February, pp. 46747–46762, 2025, doi: 10.1109/ACCESS.2025.3550015.

[6] A. Alqahtani, S. Alsubai, M. Sha, L. Vilcekova, and T. Javed, “Cardiovascular Disease Detection using Ensemble Learning,” Comput. Intell. Neurosci., vol. 2022, pp. 1–9, Aug. 2022, doi: 10.1155/2022/5267498.

[7] A. Tiwari, A. Chugh, and A. Sharma, “Ensemble framework for cardiovascular disease prediction,” Comput. Biol. Med., vol. 146, p. 105624, Jul. 2022, doi: 10.1016/j.compbiomed.2022.105624.

[8] Navita et al., “Advanced Hybrid Machine Learning Model for Accurate Detection of Cardiovascular Disease,” International Journal of Computational Intelligence Systems, vol. 18, no. 1, p. 51, Mar. 2025, doi: 10.1007/s44196-025-00771-1.

[9] I. Kiran, S. Ali, S. ur Rehman Khan, M. Alhussein, S. Aslam, and K. Aurangzeb, “An AI-Enabled Framework for Transparency and Interpretability in Cardiovascular Disease Risk Prediction,” Computers, Materials and Continua, vol. 82, no. 3, pp. 5057–5078, 2025, doi: 10.32604/cmc.2025.058724.

[10] N. Z. Dammak, H. Bezine, A. S. Nouri, and N. Derbel, “Innovative XAI Approaches for Predicting Cardiovascular Diseases,” OAlib, vol. 12, no. 10, pp. 1–25, 2025, doi: 10.4236/oalib.1114071.

[11] N. Uddin, P. Mahmud, M. Ahammed, Md. A. Uddin, M. Kazi, and Md. A. Talukder, “Explainable ensemble learning model for cardiovascular disease prediction with feature optimization and data balancing,” Discover Computing, vol. 29, no. 1, p. 44, Jan. 2026, doi: 10.1007/s10791-026-09930-0.

[12] C. Skouteli, N. Prenzas, A. Kakas, and C. S. Pattichis, “Explainable AI Modeling in the Prediction of Cardiovascular Disease Risk,” 2024. doi: 10.3233/SHTI240574.

[13] Svetlana Ulianova, “Cardiovascular Disease dataset,” Kaggle.

[14] S. M. Ganie and P. K. D. Pramanik, “A comparative analysis of boosting algorithms for chronic liver disease prediction,” Healthcare Analytics, vol. 5, Jun. 2024, doi: 10.1016/j.health.2024.100313.

[15] W. El Atifi, O. El Rhazouani, F. M. Khan, and H. Sekkat, “Optimizing ensemble machine learning models for accurate liver disease prediction in healthcare,” PLoS One, vol. 20, no. 8 August, Aug. 2025, doi: 10.1371/journal.pone.0330899.

[16] J. Liang et al., “Predictive Framework for Membrane Fouling in Full-Scale Membrane Bioreactors (MBRs): Integrating AI-Driven Feature Engineering and Explainable AI (XAI),” Processes, vol. 13, no. 8, p. 2352, Jul. 2025, doi: 10.3390/pr13082352.

[17] S. M. Ganie, P. K. D. Pramanik, M. Bashir Malik, S. Mallik, and H. Qin, “An ensemble learning approach for diabetes prediction using boosting techniques,” Front. Genet., vol. 14, Oct. 2023, doi: 10.3389/fgene.2023.1252159.

[18] A. Ogunpola, F. Saeed, S. Basurra, A. M. Albarrak, and S. N. Qasem, “Machine Learning-Based Predictive Models for Detection of Cardiovascular Diseases,” Diagnostics, vol. 14, no. 2, p. 144, Jan. 2024, doi: 10.3390/diagnostics14020144.

[19] D. Yadav, D. Rani, and O. P. Verma, “Impact of feature selection and feature engineering in prediction of cardiovascular diseases,” Comput. Biol. Med., vol. 197, p. 111027, Oct. 2025, doi: 10.1016/j.compbiomed.2025.111027.

[20] P. Iacobescu, V. Marina, C. Anghel, and A.-D. Anghele, “Evaluating Binary Classifiers for Cardiovascular Disease Prediction: Enhancing Early Diagnostic Capabilities,” J. Cardiovasc. Dev. Dis., vol. 11, no. 12, p. 396, Dec. 2024, doi: 10.3390/jcdd11120396.

[21] O. D. Yanti, S. Alfariani, S. N. Milla Celesta, K. D. Tania, and A. Rifai, “Comparative Analysis of the Performance of Machine Learning Methods and Text Embedding Techniques in Classifying Toxic Conversations in the Roblox Game,” Journal of Applied Informatics and Computing, vol. 10, no. 3, pp. 2775–2789, Jun. 2026, doi: 10.30871/jaic.v10i3.12646.

[22] L. Chmielowski, M. Kucharzak, and R. Burduk, “Novel method of building train and test sets for evaluation of machine learning models related to software bugs assignment,” Sci. Rep., vol. 13, no. 1, p. 21512, Dec. 2023, doi: 10.1038/s41598-023-48617-0.

[23] A. Ashraf et al., “A preprocessing-enhanced stacking classifier for generalized cardiovascular disease detection across diverse datasets,” Sci. Rep., vol. 16, no. 1, p. 16206, Mar. 2026, doi: 10.1038/s41598-026-41042-z.

[24] J. Liu, X. Dong, H. Zhao, and Y. Tian, “Predictive Classifier for Cardiovascular Disease Based on Stacking Model Fusion,” Processes, vol. 10, no. 4, p. 749, Apr. 2022, doi: 10.3390/pr10040749.

[25] A. Hussain and A. Aslam, “Hate speech against women and immigrants: A comparative analysis of machine learning and text embedding techniques,” 2024. [Online]. Available: www.jart.icat.unam.mx

[26] S. A. Atimbire, J. K. Appati, and E. Owusu, “Empirical exploration of whale optimisation algorithm for heart disease prediction,” Sci. Rep., vol. 14, no. 1, p. 4530, Feb. 2024, doi: 10.1038/s41598-024-54990-1.

[27] F. Ocampo Osorio, S. Alzate-Ricaurte, T. E. Mejia Vallecilla, and G. A. Cruz-Suarez, “The anesthesiologist’s guide to critically assessing machine learning research: a narrative review,” BMC Anesthesiol., vol. 24, no. 1, p. 452, Dec. 2024, doi: 10.1186/s12871-024-02840-y.

[28] A. E. Korial, I. I. Gorial, and A. J. Humaidi, “An Improved Ensemble-Based Cardiovascular Disease Detection System with Chi-Square Feature Selection,” Computers, vol. 13, no. 6, p. 126, May 2024, doi: 10.3390/computers13060126.

[29] O. Rainio, J. Teuho, and R. Klén, “Evaluation metrics and statistical tests for machine learning,” Sci. Rep., vol. 14, no. 1, p. 6086, Mar. 2024, doi: 10.1038/s41598-024-56706-x.

[30] A. Bozorgpanah and V. Torra, “Explainable machine learning models with privacy,” Progress in Artificial Intelligence, vol. 13, no. 1, pp. 31–50, Mar. 2024, doi: 10.1007/s13748-024-00315-2.

[31] M. U. Sreeja, A. O. Philip, and M. H. Supriya, “Towards explainability in artificial intelligence frameworks for heartcare: A comprehensive survey,” Journal of King Saud University - Computer and Information Sciences, vol. 36, no. 6, p. 102096, Jul. 2024, doi: 10.1016/j.jksuci.2024.102096.

[32] J. E. Ebinger et al., “Blood pressure variability supersedes heart rate variability as a real-world measure of dementia risk,” Sci. Rep., vol. 14, no. 1, p. 1838, Jan. 2024, doi: 10.1038/s41598-024-52406-8.

[33] I. Naskinova, M. Kolev, D. Karova, and M. Milev, “Machine Learning-Based Blood Pressure Prediction Using Cardiovascular Disease Data: A Comprehensive Comparative Study,” Electronics (Basel)., vol. 15, no. 2, p. 312, Jan. 2026, doi: 10.3390/electronics15020312.

[34] J. A. Otieno, J. Häggström, D. Darehed, and M. Eriksson, “Developing machine learning models to predict multi-class functional outcomes and death three months after stroke in Sweden,” PLoS One, vol. 19, no. 5 May, May 2024, doi: 10.1371/journal.pone.0303287.

[35] P. Neirz, H. Allende, and C. Saavedra, “Epistemic frontiers and the distinction between causality, information, and predictability in pattern recognition,” Sci. Rep., vol. 16, no. 1, p. 21803, May 2026, doi: 10.1038/s41598-026-52883-z.