Intelligent Ensemble-Based Decision Support System for the Classification and Management of Type 2 Diabetes Mellitus (T2dm) Subtypes Using Clinical Data

Type 2 Diabetes Mellitus (T2DM) presents as a significant public health problem, which requires accurate diagnosis and personalized management to reduce disease complications, thus, improving patient outcome. This paper presents an intelligent ensemble-based decision support system for classification and management of T2DM subtypes using clinical data collected from the University of Nigeria Teaching Hospital (UNTH) and Parklane Hospital, Enugu State, Nigeria. A total number of 23,300 validated patient’s records were integrated and used in this study. Seven Machine Learning (ML) classifiers namely: Random Forest (RF), Multi-Layer Perceptron (MLP), Support Vector Machine (SVM), Naïve Bayes (NB), K-Nearest Neighbour (KNN), Extreme Gradient Boosting (XGBoost) and Decision Tree (DT) were trained and evaluated. The three best performing classifiers were combined using a stacking ensemble approach with XGBoost as the meta-classifier. In addition, a clinical decision support recommendation framework was designed and deployed to provide management recommendations for Normal, Mild Age-related Diabetes (MARD), Mild Obesity-related Diabetes (MOD), Severe Insulin-deficient Diabetes (SIDD) and Severe Insulin-resistant Diabetes (SIRD) patients. The experimental results revealed that the proposed stacking ensemble achieved an overall classification accuracy of 98.18% with excellent precision, recall, and F1-scores for all diabetes classes. The results further indicate that ensemble approach can be employed to achieve enhanced performance in diabetes classification with intelligent recommendation for clinical management of each diabetes subtype. The proposed decision support system can play a significant role in addressing challenges associated with diabetes management in limited-resource settings.

Type 2 Diabetes Mellitus, Ensemble Learning, Stacking Ensemble, XGBoost, Clinical Decision Support System

1. Afsaneh, E., Sharifdini, A., Ghazzaghi, H., & Zarei Ghobadi, M. (2022). Recent applications of machine learning and deep learning models in the prediction, diagnosis, and management of diabetes: A comprehensive review. Diabetology & Metabolic Syndrome, 14, Article 87. https://doi.org/10.1186/s13098-022-00969-9 [Google Scholar] [Crossref]

2. Agyemang, C., Nyesigala, D., & Beune, E. (2023). Subgroups of adult-onset diabetes: A data-driven cluster analysis in a Ghanaian population. Scientific Reports, 13(1), 10592. [Google Scholar] [Crossref]

3. Antar, S. A., Ashour, N. A., Sharaky, M., Khattab, M., Ashour, N. A., Zaid, R. T., Roh, E. J., Elkamhawy, A., & Al-Karmalawy, A. A. (2023). Diabetes mellitus: Classification, mediators, and complications; A gate to identify potential targets for the development of new effective treatments. Biomedicine & Pharmacotherapy, 168, 115734. https://doi.org/10.1016/j.biopha.2023.115734 [Google Scholar] [Crossref]

4. Atun, R., Davies, J. I., Gale, E. A. M., Bärnighausen, T., Beran, D., Kengne, A. P., et al. (2022). Diabetes in sub-Saharan Africa: From clinical care to health policy. The Lancet Diabetes & Endocrinology, 10(1), 50-62. [Google Scholar] [Crossref]

5. Chang, V., Ganatra, M. A., Hall, K., Golightly, L., & Xu, Q. A. (2022). An assessment of machine learning models and algorithms for early prediction and diagnosis of diabetes using health indicators. Healthcare Analytics, 2, 100118. [Google Scholar] [Crossref]

6. Dutta, A., Hasan, M. K., Ahmad, M., Awal, M. A., Islam, M. A., Masud, M., & Meshref, H. (2022). Early Prediction of Diabetes Using an Ensemble of Machine Learning Models. International Journal of Environmental Research and Public Health, 19(19), 12378. https://doi.org/10.3390/ijerph191912378 [Google Scholar] [Crossref]

7. Fregoso-Aparicio, L., Noguez, J., Montesinos, L., & García-García, J. A. (2021). Machine learning and deep learning predictive models for type 2 diabetes: A systematic review. Diabetology & Metabolic Syndrome, 13. https://doi.org/10.1186/s13098-021-00767-9 [Google Scholar] [Crossref]

8. Howlader, K. C., Satu, M. S., Awal, M. A., Islam, M. R., Islam, S. M. S., Quinn, J. M. W., & Moni, M. A. (2022). Machine learning models for classification and identification of significant attributes to detect type 2 diabetes. Health Information Science and Systems, 10(2). https://doi.org/10.1007/s13755-021-00168-2 [Google Scholar] [Crossref]

9. Ismail, L., Materwala, H., & Tayefi, M. (2022). Type 2 Diabetes with Artificial Intelligence Machine Learning: Methods and Evaluation. Archives of Computational Methods in Engineering, 29, 313-333. https://doi.org/10.1007/s11831-021-09582-x [Google Scholar] [Crossref]

10. Ordoñez Guillen, N. E., Gonzalez Compean, J. L., Lopez Arevalo, I., Contreras Murillo, M., & Aldana Bobadilla, E. (2023). Machine learning based study for the classification of Type 2 diabetes mellitus subtypes. BioData Mining. https://doi.org/10.1186/s13040-023-00340-2 [Google Scholar] [Crossref]

11. Petridis, P. D., Kristo, A. S., Sikalidis, A. K., & Kitsas, I. K. (2024). A review on trending machine learning techniques for type 2 diabetes mellitus management. Informatics, 11(70). https://doi.org/10.3390/informatics11040070 [Google Scholar] [Crossref]

12. Shin, J., Kim, J., Lee, C., Yoon, J. Y., Kim, S., Song, S., & Kim, H.-S. (2022). Development of various diabetes prediction models using machine learning techniques. Diabetes & Metabolism Journal, 46(6), 650-657. https://doi.org/10.4093/dmj.2021.0115 [Google Scholar] [Crossref]

13. Okoye, F. A., Njoku, C. E., & Ebere, U. C. (2026). A comprehensive review of deep learning approaches for automated farm weed classification. International Journal of Research and Innovation in Applied Science, 11(7), 1686–1699. https://doi.org/10.51584/IJRIAS.2026.11070118 [Google Scholar] [Crossref]

14. Ekene, N.C., Okoye, F.A., Chidi, E.U. et al. A comprehensive review of deep learning methods for weed classification in precision agriculture. Discov Artif Intell 6, 1180 (2026). https://doi.org/10.1007/s44163-026-01916-7 [Google Scholar] [Crossref]

15. Ebere UC, Edward A, Collins U, Asogwa TC, Nwobodo LO. A blind navigation guide model for obstacle avoidance using distance vision estimation-based YOLO-V8n. J Niger Soc Phys Sci. 2025;7(2025):2292. https://doi.org/10.46481/jnsps.2025.2292. [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet