Oversampling SMOTE to Handle Imbalance in Multiclass Diabetes Dataset
DOI:
https://doi.org/10.65853/jaden.v1i1.102Keywords:
Diabetes classification, class imbalance, SMOTE, machine learning, multiclass predictionAbstract
Diabetes mellitus is a chronic disease with an increasing global prevalence that requires early detection and accurate classification to prevent severe complications. Machine learning has been widely applied in diabetes prediction; however, one of the major challenges lies in the class imbalance problem commonly found in medical datasets. This study focuses on the Multiclass Diabetes Dataset, which consists of 264 samples and exhibits imbalanced distribution among classes (Class 2: 128 samples, Class 0: 96 samples, Class 1: 40 samples). Such imbalance may bias the classifier toward majority classes, reducing its ability to recognize minority classes. The results indicate that SMOTE effectively improved the model’s ability to classify minority classes, with significant increases in recall and F1-score. Among the tested algorithms, Random Forest achieved the best performance, with an overall accuracy of 98% and F1-score above 0.98. Although KNN experienced a slight performance drop after SMOTE, other algorithms, particularly SVM and Logistic Regression, demonstrated notable improvements.
Downloads
References
. Abousaber, I., Abdallah, H. F., & El-Ghaish, H. (2025). Robust predictive framework for diabetes classification using optimized machine learning on imbalanced datasets. Frontiers in Artificial Intelligence, 7. https://doi.org/10.3389/frai.2024.1499530.
. American Diabetes Association. (2022). Standards of medical care in diabetes—2022. Diabetes Care, 45(Suppl. 1), S1–S264.
. Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321–357. https://doi.org/10.1613/jair.953
. ElSeddawy, A. I., Karim, F. K., Hussein, A. M., & Khafaga, D. S. (2022). Predictive Analysis of Diabetes-Risk with Class Imbalance. Computational intelligence and neuroscience, 2022, 3078025. https://doi.org/10.1155/2022/3078025
. Gudiño-Ochoa, A., García-Rodríguez, J. A., Ochoa-Ornelas, R., Ruiz-Velazquez, E., Uribe-Toscano, S., Cuevas-Chávez, J. I., & Sánchez-Arias, D. A. (2025). Non-Invasive Multiclass Diabetes Classification Using Breath Biomarkers and Machine Learning with Explainable AI. Diabetology, 6(6), 51. https://doi.org/10.3390/diabetology6060051
. He, H., & Garcia, E. A. (2009). Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering, 21(9), 1263–1284. https://doi.org/10.1109/TKDE.2008.239
. Jang, Younseo. (2025). Feature-based ensemble modeling for addressing diabetes data imbalance using the SMOTE, RUS, and random forest methods: a prediction study. The Ewha Medical Journal. 48. 10.12771/emj.2025.00353.
. Joloudari, J. H., Marefat, A., Nematollahi, M. A., Oyelere, S. S., & Hussain, S. (2023). Effective Class-Imbalance Learning Based on SMOTE and Convolutional Neural Networks. Applied Sciences, 13(6), 4006. https://doi.org/10.3390/app13064006
. Kaliappan, J., Saravana Kumar, I. J., Sundaravelan, S., Anesh, T., Rithik, R. R., Singh, Y., Vera‑Garcia, D. V., Himeur, Y., Mansoor, W., Atalla, S., & Srinivasan, K. (2024). Analyzing classification and feature selection strategies for diabetes prediction across diverse diabetes datasets. Frontiers in Artificial Intelligence, 7, Article 1421751. https://doi.org/10.3389/frai.2024.1421751
. Kivrak, M., Avci, U., Uzun, H., & Ardic, C. (2024). The Impact of the SMOTE Method on Machine Learning and Ensemble Learning Performance Results in Addressing Class Imbalance in Data Used for Predicting Total Testosterone Deficiency in Type 2 Diabetes Patients. Diagnostics (Basel, Switzerland), 14(23), 2634. https://doi.org/10.3390/diagnostics14232634
. Mardianta, S., Affandy, Supriyanto, C., Supriyanto, C., & Wijaya, A. (2025, April 8). Diabetic Retinopathy Detection Based on Convolutional Neural Networks with SMOTE and CLAHE Techniques Applied to Fundus Images [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2504.05696
. Matboli, M., Khaled, A., Ahmed, M.F. et al. (2025). Machine learning-based stratification of prediabetes and type 2 diabetes progression. Diabetol Metab Syndr 17, 227 https://doi.org/10.1186/s13098-025-01786-6
. Mukherjee, M., & Khushi, M. (2021). SMOTE-ENC: A Novel SMOTE-Based Method to Generate Synthetic Data for Nominal and Continuous Features. Applied System Innovation, 4(1), 18. https://doi.org/10.3390/asi4010018.
. Sahid, M. A., Babar, M. U. H., & Uddin, M. P. (2024). Predictive modeling of multi-class diabetes mellitus using machine learning and filtering Iraqi diabetes data dynamics. PLOS ONE, 19(5), e0300785. https://doi.org/10.1371/journal.pone.0300785
. Shao, H., Liu, X., Zong, D., & Song, Q. (2024). Optimization of diabetes prediction methods based on combinatorial balancing algorithm. Nutrition & diabetes, 14(1), 63. https://doi.org/10.1038/s41387-024-00324-z
. Talebi Moghaddam, M., Jahani, Y., Arefzadeh, Z. et al. Predicting diabetes in adults: identifying important features in unbalanced data over a 5-year cohort study using machine learning algorithm. BMC Med Res Methodol 24, 220 (2024). https://doi.org/10.1186/s12874-024-02341-z
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Dika Dika, Syahrul Ramadhan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
