Chronic diseases are responsible for most deaths worldwide. These illnesses are increasingly prevalent, and there is a dire need for systems that can predict diseases before they develop. Early detection and prediction solutions could exploit powerful tools of artificial intelligence (AI), primarily methods of machine learning (ML) and data mining. In this study, a unified stacking framework was proposed to predict three significant chronic conditions, including heart disease, diabetes, and hypertension. The proposed model consists of Random Forest (RF), XGBoost, and LightGBM as base learners, while Logistic Regression (LR) is used as a meta learner. Three datasets on heart disease, diabetes, and hypertension from BRFSS 2015 are funded by the US CDC and were utilized to demonstrate implementation of the framework. An independent integrated framework was adopted across each dataset to have the same preprocessing, model settings, and validation scenarios across pipelines. For robust and reliable performance assessment, both hold out validation and stratified five-fold cross-validation were adopted. Using stratified five-fold cross-validation, the proposed framework has shown promising predictive performance with an overall accuracy of 99.20% for heart diseases, 97.90% for diabetes, and 99.93% for hypertension. In conclusion, these results indicate a competitive and stable ensemble model towards chronic disease prediction, which can be deployed in medical decision-making applications.
Y. Liu and B. Wang, “Advanced applications in chronic disease monitoring using IoT mobile sensing device data, machine learning algorithms, and frame theory: A systematic review.”
A. Al-Nafjan, A. Aljuhani, A. Alshebel, A. Alharbi, and A. Alshehri, “Artificial intelligence in predictive healthcare: A systematic review,” pp. 1-17, 2025.
M. A. Bouqentar et al., “Early heart disease prediction using feature engineering and machine learning algorithms,” Heliyon, vol. 10, no. 19, pp. 1-23, 2024, doi: 10.1016/j.heliyon.2024.e38731.
S. Afolabi, N. Ajadi, A. Jimoh, and I. Adenekan, “Predicting diabetes using supervised machine learning algorithms on e-health records,” Inform. Health, vol. 2, no. 1, pp. 9-16, 2025, doi: 10.1016/j.infoh.2024.12.002.
A. K. Yüksel and M. S. Güzel, “Efficient diabetes prediction using random forests and minimal health indicators on the BRFSS dataset,” vol. 2, no. 1, pp. 34-43, 2025.
P. Yadav, S. C. Sharma, R. Mahadeva, and S. P. Patole, “Exploring hyper-parameters and feature selection for predicting non-communicable chronic disease using stacking classifier,” IEEE Access, vol. 11, pp. 80030-80055, 2023, doi: 10.1109/ACCESS.2023.3299332.
K. Abnoosian, R. Farnoosh, and M. H. Behzadi, “Prediction of diabetes disease using an ensemble of machine learning multi-classifier models,” BMC Bioinformatics, vol. 24, no. 1, pp. 1-24, 2023, doi: 10.1186/s12859-023-05465-z.
J. Kaliappan et al., “Analyzing classification and feature selection strategies for diabetes prediction across diverse diabetes datasets,” Front. Artif. Intell., vol. 7, 2024, doi: 10.3389/frai.2024.1421751.
H. A. Al-Jamimi, “Synergistic feature engineering and ensemble learning for early chronic disease prediction,” IEEE Access, vol. 12, pp. 62215-62233, 2024, doi: 10.1109/ACCESS.2024.3395512.
N. Yanes, L. Jamel, B. Alabdullah, M. Ezz, A. Mohamed Mostafa, and H. Shabana, “Using machine learning for detection and prediction of chronic diseases,” IEEE Access, vol. 12, pp. 177674-177691, 2024, doi: 10.1109/ACCESS.2024.3494839.
W. Vin et al., “Development of a machine learning model for precision prognosis of rapid kidney function decline in people with diabetes and chronic kidney disease,” Diabetes Res. Clin. Pract., vol. 217, p. 111897, 2024, doi: 10.1016/j.diabres.2024.111897.
S. Zhang, F. Yang, L. Wang, S. Si, J. Zhang, and F. Xue, “Personalized prediction for multiple chronic diseases by developing the multi-task Cox learning model,” vol. 19, no. 9, 2023, doi: 10.1371/journal.pcbi.1011396.
L. Abualigah et al., “Artificial intelligence-driven translational medicine: A machine learning framework for predicting disease outcomes and optimizing patient-centric care,” J. Transl. Med., vol. 23, no. 1, 2025, doi: 10.1186/s12967-025-06308-6.
N. Rankovic, D. Rankovic, and I. Lukic, “Innovations in early detection of chronic non-communicable diseases among adolescents through an easy-to-use AutoML paradigm,” Health Care Manag. Sci., vol. 28, no. 3, pp. 434-460, 2025, doi: 10.1007/s10729-025-09718-6.
A. Teboul, “Heart disease health indicators dataset,” Kaggle, [Online]. Available: https://www.kaggle.com/datasets/alexteboul/heart-disease-health-indicators-dataset.
A. Teboul, “Diabetes health indicators dataset,” Kaggle, [Online]. Available: https://www.kaggle.com/datasets/alexteboul/diabetes-health-indicators-dataset.
P. Chuks, “Health dataset (hypertension),” Kaggle, [Online]. Available: https://www.kaggle.com/datasets/prosperchuks/health-dataset.
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, 2024, doi: 10.3390/diagnostics14020144.
