AN INTEGRATED HYBRID SOFT VOTING ENSEMBLE AI MODEL OF MACHINE LEARNING AND DEEP LEARNING MODELS FOR DIABETES PREDICTION
DOI:
https://doi.org/10.15282//ijsecs.11.2.2025.13.0145Keywords:
Diabetes prediction, Machine learning, Deep learning, Soft voting classifier, AI-Based medical diagnosis, Hybrid ensemble learningAbstract
The goal of the study is to make a hybrid prediction model that uses both machine learning and deep learning methods to make diabetes predictions more accurate, generalizable, and robust. It combines ML and DL models, fixes class imbalance in medical datasets, and tests performance on several datasets, such as the Pima Indians Diabetes Dataset and the LMCH dataset, to see how well it works in real-life healthcare. The ML Ensemble, which included RF, LR, and XGBoost, and the DL Ensemble, which included CNN, FNN, and ENN, were the two stacked ensembles used in the study. Soft voting was used to aggregate the results to improve the accuracy of the predictions. To prepare the structured medical data, we employed feature preprocessing techniques and the Synthetic Minority Over-sampling Technique (SMOTE). Cross-validation was used to ensure that the results were good and to prevent them from being overly specific. The performance was compared to independent models and standard methods. The ensemble hybrid AI model performed better than the traditional ML and DL models. Its best performance metrics were Accuracy of 98.89%, Precision of 98.99%, Recall of 87.07%, F1-score of 92.05%, ROC-AUC of 92.48%, and Cohen's Kappa of 84.96%. This shows that it was better at generalizing and working with datasets that weren't balanced. The stacking of ensembles with soft voting combines machine learning and deep learning models to improve diabetes prediction performance and fix problems with class imbalance in medical datasets. The model's ability to be used in the real world and its ability to be generalized show that it could be used to find diabetes early and accurately, which could help with preventive healthcare strategies.
Downloads
References
[1] World Health Organization, “Diabetes,” Nov. 14, 2024. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/diabetes. Accessed: Jan. 22, 2026.
[2] T. T. Tran, G. Yun, and S. Kim, “Artificial intelligence and predictive models for early detection of acute kidney injury: Transforming clinical practice,” BMC Nephrology, vol. 25, no. 1, 2024, https://doi.org/10.1186/s12882-024-03793-7.
[3] N. Katiyar, H. K. Thakur, and A. Ghatak, “Recent advancements using machine learning and deep learning approaches for diabetes detection: A systematic review,” e-Prime—Advances in Electrical Engineering, Electronics and Energy, vol. 9, p. 100661, 2024, https://doi.org/10.1016/j.prime.2024.100661.
[4] Z. Allal, H. N. Noura, and K. Chahine, “Machine learning algorithms for solar irradiance prediction: A recent comparative study,” e-Prime—Advances in Electrical Engineering, Electronics and Energy, vol. 7, p. 100453, 2024, https://doi.org/10.1016/j.prime.2024.100453.
[5] A. Altamimi et al., “An automated approach to predict diabetic patients using KNN imputation and effective data mining techniques,” BMC Medical Research Methodology, vol. 24, no. 1, 2024, https://doi.org/10.1186/s12874-024-02324-0.
[6] G. A. Ansari, S. Shafi, M. D. Ansari, and A. Shadab, “Advanced supervised machine learning methods for precise diabetes mellitus prediction using feature selection,” Frontiers in Medicine, vol. 12, 2025, https://doi.org/10.3389/fmed.2025.1620268.
[7] P. B. Khokhar, C. Gravino, and F. Palomba, “Advances in artificial intelligence for diabetes prediction: Insights from a systematic literature review,” Artificial Intelligence in Medicine, vol. 164, p. 103132, 2025, https://doi.org/10.1016/j.artmed.2025.103132.
[8] M. A. Talukder, A. S. Talaat, and M. Kazi, “HXAI-ML: A hybrid explainable artificial intelligence-based machine learning model for cardiovascular heart disease detection,” Results in Engineering, p. 104370, 2025, https://doi.org/10.1016/j.rineng.2025.104370.
[9] I. Abdelbaky, M. Ahmed, and M. Taha, “Machine learning classification approaches for prediction of effective diabetes drugs,” Egyptian Informatics Journal, vol. 31, p. 100786, 2025, https://doi.org/10.1016/j.eij.2025.100786.
[10] W. Li, Y. Peng, and K. Peng, “Diabetes prediction model based on GA-XGBoost and stacking ensemble algorithm,” PLoS ONE, vol. 19, no. 9, p. e0311222, 2024, https://doi.org/10.1371/journal.pone.0311222.
[11] A. A. Amer, S. D. Ravana, and R. Ahamed, “Effective k-nearest neighbor models for data classification enhancement,” Journal of Big Data, vol. 12, no. 1, 2025, https://doi.org/10.1186/s40537-025-01137-2.
[12] S. Shamshirband, M. Fathi, A. Dehzangi, A. T. Chronopoulos, and H. Alinejad-Rokny, “A review on deep learning approaches in healthcare systems: Taxonomies, challenges, and open issues,” Journal of Biomedical Informatics, vol. 113, p. 103627, 2020, https://doi.org/10.1016/j.jbi.2020.103627.
[13] M. M. Zafar, Z. A. Khan, N. Javaid, M. Aslam, and N. Alrajeh, “From data to diagnosis: A novel deep learning model for early and accurate diabetes prediction,” Healthcare, vol. 13, no. 17, p. 2138, 2025, https://doi.org/10.3390/healthcare13172138.
[14] T. Qamar and N. Z. Bawany, “Understanding the black-box: Towards interpretable and reliable deep learning models,” PeerJ Computer Science, vol. 9, p. e1629, 2023, https://doi.org/10.7717/peerj-cs.1629.
[15] V. H. Rondón-Cordero, L. Montuori, M. Alcázar-Ortega, and P. Siano, “Advancements in hybrid and ensemble ML models for energy consumption forecasting: Results and challenges of their applications,” Renewable and Sustainable Energy Reviews, vol. 224, p. 116095, 2025, https://doi.org/10.1016/j.rser.2025.116095.
[16] F. Rustam et al., “Enhanced detection of diabetes mellitus using novel ensemble feature engineering approach and machine learning model,” Scientific Reports, vol. 14, no. 1, 2024, https://doi.org/10.1038/s41598-024-74357-w.
[17] I. Abousaber, H. F. Abdallah, and H. El-Ghaish, “Robust predictive framework for diabetes classification using optimized machine learning on imbalanced datasets,” Frontiers in Artificial Intelligence, vol. 7, 2025, https://doi.org/10.3389/frai.2024.1499530.
[18] H. B. Kibria, M. Nahiduzzaman, M. O. F. Goni, M. Ahsan, and J. Haider, “An ensemble approach for the prediction of diabetes mellitus using a soft voting classifier with an explainable AI,” Sensors, vol. 22, no. 19, p. 7268, 2022, https://doi.org/10.3390/s22197268.
[19] M. Ijaz, G. Alfian, M. Syafrudin, and J. Rhee, “Hybrid prediction model for type 2 diabetes and hypertension using DBSCAN-based outlier detection, SMOTE, and random forest,” Applied Sciences, vol. 8, no. 8, p. 1325, 2018, https://doi.org/10.3390/app8081325.
[20] B. O. Olorunfemi et al., “Efficient diagnosis of diabetes mellitus using an improved ensemble method,” Scientific Reports, vol. 15, no. 1, 2025, https://doi.org/10.1038/s41598-025-87767-1.
[21] N. Ahmed et al., “Machine learning-based diabetes prediction and development of smart web application,” International Journal of Cognitive Computing in Engineering, vol. 2, pp. 229–241, 2021, https://doi.org/10.1016/j.ijcce.2021.12.001.
[22] Y. Fan, “Diabetes diagnosis using a hybrid CNN-LSTM-MLP ensemble,” Scientific Reports, vol. 15, no. 1, 2025, https://doi.org/10.1038/s41598-025-12151-y.
[23] S. Kumari, D. Kumar, and M. Mittal, “An ensemble approach for classification and prediction of diabetes mellitus using soft voting classifier,” International Journal of Cognitive Computing in Engineering, vol. 2, pp. 40–46, 2021, https://doi.org/10.1016/j.ijcce.2021.01.001.
[24] E. Afsaneh, A. Sharifdini, H. Ghazzaghi, and M. Z. Ghobadi, “Recent applications of machine learning and deep learning models in the prediction, diagnosis, and management of diabetes: A comprehensive review,” Diabetology & Metabolic Syndrome, vol. 14, no. 1, 2022, https://doi.org/10.1186/s13098-022-00969-9.
[25] W. Zhang, Z. Xia, G. Cai, J. Wang, and X. Dong, “Enhancing diabetes risk prediction through focal active learning and machine learning models,” PLoS ONE, vol. 20, no. 7, p. e0327120, 2025, https://doi.org/10.1371/journal.pone.0327120.
[26] S. Dash et al., “Privacy-preserving diabetes and heart disease prediction via federated learning and WCO,” International Journal of Computational Intelligence Systems, vol. 18, no. 1, 2025, https://doi.org/10.1007/s44196-025-00956-8.
[27] S. K. Bejugam and J. Vankara, “An efficient model for diabetic detection using heuristic approach-based serial cascaded convolutional ensemble network,” Artificial Intelligence Review, vol. 58, no. 10, 2025, https://doi.org/10.1007/s10462-025-11334-3.
[28] L. Alzubaidi et al., “Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions,” Journal of Big Data, vol. 8, no. 1, pp. 1–74, 2021, https://doi.org/10.1186/s40537-021-00444-8.
[29] A. Rihan, M. Anbar, and B. A. Alabsi, “Meta-learner-based approach for detecting attacks on Internet of Things networks,” Sensors, vol. 23, no. 19, p. 8191, 2023, https://doi.org/10.3390/s23198191.
[30] Kaggle, “Pima Indians diabetes database,” 2016. [Online]. Available: https://www.kaggle.com/datasets/uciml/pima-indians-diabetes-database. Accessed: Jan. 22, 2026.
[31] Ziya, “Diabetes clinical dataset (100k rows),” Kaggle, 2025. [Online]. Available: https://www.kaggle.com/datasets/ziya07/diabetes-clinical-dataset100k-rows. Accessed: Jan. 22, 2026.
[32] Python Software Foundation, “Python,” 2025. [Online]. Available: https://www.python.org/. Accessed: Jan. 22, 2026.
[33] Scikit-learn,“Importance of feature scaling.” [Online]. Available: https://scikit-learn.org/stable/auto_examples/preprocessing/plot_scaling_importance.html. Accessed: Jan. 22, 2026.
[34] J. J. Sonia, P. Jayachandran, A. Q. Md, S. Mohan, A. K. Sivaraman, and K. F. Tee, “Machine-learning-based diabetes mellitus risk prediction using multi-layer neural network No-Prop algorithm,” Diagnostics, vol. 13, no. 4, p. 723, 2023, https://doi.org/10.3390/diagnostics13040723.
[35] G. I. Kim, S. Kim, and B. Jang, “Classification of mathematical test questions using machine learning on datasets of learning management system questions,” PLoS ONE, vol. 18, no. 10, p. e0286989, 2023, https://doi.org/10.1371/journal.pone.0286989.
[36] K. Singh, A. Mahajan, and V. Mansotra, “1D-CNN-based model for classification and analysis of network attacks,” International Journal of Advanced Computer Science and Applications, vol. 12, no. 11, 2021, https://doi.org/10.14569/IJACSA.2021.0121169.
[37] Y. Han, D. Y. Kim, J. Woo, and J. Kim, “Glu-Ensemble: An ensemble deep learning framework for blood glucose forecasting in type 2 diabetes patients,” Heliyon, vol. 10, no. 8, p. e29030, 2024, https://doi.org/10.1016/j.heliyon.2024.e29030.
[38] Q. Liu et al., “Development and validation of a meta-learner for combining statistical and machine learning prediction models in individuals with depression,” BMC Psychiatry, vol. 22, no. 1, 2022, https://doi.org/10.1186/s12888-022-03986-0.
[39] A. A. Khan, O. Chaudhari, and R. Chandra, “A review of ensemble learning and data augmentation models for class imbalanced problems: Combination, implementation and evaluation,” Expert Systems with Applications, vol. 244, p. 122778, 2023, https://doi.org/10.1016/j.eswa.2023.122778.
[40] A. T. Kuo, H. Chen, L. Tang, W. Ku, and X. Qin, “ProbSky: Efficient computation of probabilistic skyline queries over distributed data,” IEEE Transactions on Knowledge and Data Engineering, 2022, https://doi.org/10.1109/TKDE.2022.3151740.
[41] X. Liu, D. N. Yang, M. Ye, and W. C. Lee, “U-Skyline: A new skyline query for uncertain databases,” IEEE Transactions on Knowledge and Data Engineering, vol. 25, no. 4, pp. 945–960, 2013, https://doi.org/10.1109/TKDE.2012.33.
[42] B. Chen, D. Zhu, Y. Wang, and P. Zhang, “An approach to combine the power of deep reinforcement learning with a graph neural network for routing optimization,” Electronics, vol. 11, no. 3, p. 368, 2022, https://doi.org/10.3390/electronics11030368.
[43] M. Z. Islam, “Enhancing diabetes prediction accuracy using stacked machine learning and deep learning models: A public health approach,” Indonesian Journal of Computer Science, vol. 14, no. 4, 2025, https://doi.org/10.33022/ijcs.v14i4.4947.
[44] P. Kumar, “A comparison of CNN, RNN, and FNN algorithms to investigate effective diabetes prediction,” Archives of Computational Methods in Engineering, 2025, https://doi.org/10.1007/s11831-025-10333-5.
[45] K. Oliullah, M. Rasel, M. M. Islam, M. R. Islam, M. Anwar, and M. Whaiduzzaman, “A stacked ensemble machine learning approach for the prediction of diabetes,” Journal of Diabetes & Metabolic Disorders, 2023, https://doi.org/10.1007/s40200-023-01321-2.
[46] M. Barton and B. Lennox, “Model stacking to improve prediction and variable importance robustness for soft sensor development,” Digital Chemical Engineering, vol. 3, p. 100034, 2022, https://doi.org/10.1016/j.dche.2022.100034.
[47] R. K. Halder, M. A. Lima, M. N. Uddin, M. A. Islam, and A. Saha, “Integrated feature selection-based stacking ensemble model using optimized hyperparameters to predict breast cancer with smart web application,” Clinical eHealth, 2025, https://doi.org/10.1016/j.ceh.2025.08.001.
[48] K. Razzaq and M. Shah, “Next-generation machine learning in healthcare fraud detection: Current trends, challenges, and future research directions,” Information, vol. 16, no. 9, p. 730, 2025, https://doi.org/10.3390/info16090730.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 The Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
