An Adaptive Feature-Aware Hybrid Resampling Strategy for Imbalanced Diabetes Classification with Integrated Balanced Index Evaluation
DOI:
https://doi.org/10.29207/resti.v10i2.7418Keywords:
adaptive hybrid resampling, diabetes, imbalanced data, integrated balanced index, machine learningAbstract
Class imbalance remains a critical challenge in medical data classification, particularly in diabetes prediction, as it significantly degrades minority-class sensitivity. This study proposes an Adaptive Feature-Aware Hybrid Resampling Strategy (AHRS) that dynamically integrates oversampling and undersampling based on Imbalance Ratio (IR) and Feature Importance (FI). Unlike conventional static resampling methods, AHRS iteratively adjusts class distribution while preserving informative feature structures. In addition, this study introduces the Integrated Balanced Index (IBI), a bounded composite metric integrating precision, recall, and specificity to provide a fairer evaluation of classification performance on imbalanced medical datasets. The proposed approach was evaluated using the Pima Indian Diabetes Dataset (768 instances) with K-Nearest Neighbor, Naïve Bayes, and Random Forest classifiers under 5-fold stratified cross-validation. Experimental results demonstrate that AHRS consistently outperforms SMOTE, Random Oversampling, and Tomek Links, achieving accuracy improvements of 5–7% and recall gains of up to 10%. Random Forest combined with AHRS achieved the highest IBI score of 0.90, indicating strong balance between sensitivity and specificity. The findings suggest that adaptive, feature-aware resampling combined with balanced evaluation metrics provides a reliable and interpretable framework for fair medical classification systems and Clinical Decision Support Systems (CDSS).
Downloads
References
R. K. Halder, M. N. Uddin, M. A. Uddin, S. Aryal, and A. Khraisat, “Enhancing K-nearest neighbor algorithm: a comprehensive review and performance analysis of modifications,” J. Big Data, vol. 11, no. 1, 2024, doi: 10.1186/s40537-024-00973-y.
P. J. B. Pajila and B. G. Sheena, “A Comprehensive Survey on Naive Bayes Algorithm : Advantages , Limitations and Applications,” Int. Conf. Smart Electron. Commun. (ICOSEC 2023), no. Icosec, pp. 1227–1233, 2023, doi: 10.1109/ICOSEC58147.2023.10276274.
X. Yuan, S. Liu, W. Feng, and G. Dauphin, “Feature Importance Ranking of Random Forest-Based End-to-End Learning Algorithm,” Remote Sens., pp. 1–20, 2023, doi: https://doi.org/10.3390/rs15215203.
J. Luo, Y. Yuan, and S. Xu, “Improving GBDT performance on imbalanced datasets: An empirical study of class-balanced loss functions,” Neurocomputing, vol. 634, 2025, doi: 10.1016/j.neucom.2025.129896.
L. O. H. Nitesh V. Chawla, Kevin W. Bowyer, “SMOTE: Synthetic Minority Over-sampling Technique Nitesh,” J. Artif. Intell. Res. 16, vol. 4, no. 1, pp. 67–72, 2020, doi: 110.1613/jair.953.
F. Selection-based, N. Anomalies, and D. Strategy, “Borderline SMOTE Algorithm and Feature Selection-Based Network Anomalies Detection Strategy,” Energies, 2022, doi: https://doi.org/10.11591/eei.v11i3.3787.
G. E. A. P. A. Batista, M. C. Monard, and A. L. C. Bazzan, “Improving rule induction precision for automated annotation by balancing skewed data sets,” Lect. Notes Artif. Intell. (Subseries Lect. Notes Comput. Sci., vol. 3303, pp. 20–32, 2004, doi: 10.1007/978-3-540-30478-4_3.
W. Baddah et al., “Optimizing Heart Disease Prediction Models through SMOTE : Addressing Data Imbalance,” IEEE Xplore, 2024, doi: 10.1109/eSmarTA62850.2024.10638899.
T. Pan, J. Zhao, W. Wu, and J. Yang, “Learning imbalanced datasets based on SMOTE and Gaussian distribution,” Inf. Sci. (Ny)., vol. 512, pp. 1214–1233, 2020, doi: 10.1016/j.ins.2019.10.048.
X. Wang et al., “Exploratory study on classification of diabetes mellitus through a combined Random Forest Classifier,” BMC Med. Inform. Decis. Mak., vol. 21, no. 1, pp. 1–14, 2021, doi: 10.1186/s12911-021-01471-4.
B. H. Aubaidan, R. A. Kadir, and M. T. Ijab, “A Comparative Analysis of Smote and CSSF Techniques for Diabetes Classification Using Imbalanced Data,” J. Comput. Sci., vol. 20, no. 9, pp. 1146–1165, 2024, doi: 10.3844/JCSSP.2024.1146.1165.
Bakti Putra Pamungkas, Muhammad Jauhar Vikri, and Ita Aristia Sa’ida, “Application of SMOTE-ENN Method in Data Balancing for Classification of Diabetes Health Indicators with C4.5 Algorithm,” J. Sisfokom (Sistem Inf. dan Komputer), vol. 14, no. 2, pp. 183–188, 2025, doi: 10.32736/sisfokom.v14i2.2350.
A. Aich, M. M. Murshed, S. Hewage, and A. Mayeaux, “CopulaSMOTE: A Copula-Based Oversampling Approach for Imbalanced Classification in Diabetes Prediction,” Mach. Learn. Appl., pp. 0–3, 2025, doi: https://doi.org/10.48550/arXiv.2506.17326.
W. Chen, K. Yang, Z. Yu, Y. Shi, and C. L. P. Chen, A survey on imbalanced learning : latest research , applications and future directions, vol. 123. Artificial Intelligence Review, 2024. doi: 10.1007/s10462-024-10759-6.
M. Karuppasamy, J. M. Rani, and K. Poorani, “Metaheuristic Feature Selection for Diabetes Prediction with P-G-S Approach,” Procedia Comput. Sci., vol. 252, pp. 165–171, 2025, doi: 10.1016/j.procs.2024.12.018.
D. Dablain, B. Krawczyk, and N. V. Chawla, “DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data,” IEEE Trans. Neural Networks Learn. Syst., vol. 34, no. 9, pp. 6390–6404, 2023, doi: 10.1109/TNNLS.2021.3136503.
G. Tuysuzoglu et al., “Joint Tomek Links (JTL): An Innovative Approach to Noise Reduction for Enhanced Classification Performance,” IEEE Access, vol. 13, no. July, pp. 123059–123082, 2025, doi: 10.1109/ACCESS.2025.3580290.
A. Fernández, S. García, F. Herrera, and N. V. Chawla, “SMOTE for Learning from Imbalanced Data: Progress and Challenges, Marking the 15-year Anniversary,” J. Artif. Intell. Res., vol. 61, pp. 863–905, 2018, doi: 10.1613/jair.1.11192.
U. Ependi, “A Hybrid Sampling Approach for Improving the Classification of Imbalanced Data Using ROS and NCL Methods,” Int. J. Intell. Eng. Syst., vol. 16, no. 3, pp. 345–361, 2023, doi: 10.22266/ijies2023.0630.28.
H. He and E. A. Garcia, “Learning from Imbalanced Data,” IEEE Trans. Knowl. Data Eng., vol. 21, no. 9, pp. 1263–1284, 2009, doi: 10.1109/TKDE.2008.239.
G. Aguiar, B. Krawczyk, and A. Cano, A survey on learning from imbalanced data streams : taxonomy , challenges , empirical study , and reproducible, vol. 113, no. 7. Springer US, 2024. doi: 10.1007/s10994-023-06353-6.
Y. Yang, H. A. Khorshidi, and U. Aickelin, “A review on over-sampling techniques in classification of multi-class imbalanced datasets: insights for medical problems,” Front. Digit. Heal., no. July, 2024, doi: 10.3389/fdgth.2024.1430245.
M. Suyal and P. Goyal, “A Review on Analysis of K-Nearest Neighbor Classification Machine Learning Algorithms based on Supervised Learning,” Int. J. Eng. Trends Technol., vol. 70, no. 7, pp. 43–48, 2022, doi: https://doi.org/10.14445/22315381/IJETT-V70I7P205 Volume.
D. Berrar, “Bayes’ theorem and naive bayes classifier,” Encycl. Bioinforma. Comput. Biol. ABC Bioinforma., vol. 1–3, no. 2018, pp. 403–412, 2018, doi: 10.1016/B978-0-12-809633-8.20473-1.
J. K. Alwan, D. S. Jaafar, and I. R. Ali, “Diabetes diagnosis system using modified Naive Bayes classifier,” Indones. J. Electr. Eng. Comput. Sci., vol. 28, no. 3, pp. 1766–1774, 2022, doi: https://doi.org/10.11591/ijeecs.v28.i3.pp1766-1774.
A. A. Khaleel, A. A. M. Al-Azzawi, and A. M. Alkhazraji, “Random forest for lung cancer analysis using Apache Mahout and Hadoop based on software defined networking,” Indones. J. Electr. Eng. Comput. Sci., vol. 32, no. 2, pp. 1086–1093, 2023, doi: https://doi.org/10.11591/ijeecs.v32.i2.pp1086-1093.
T. A. Assegie, R. Subhashni, N. K. Kumar, J. P. Manivannan, P. Duraisamy, and M. F. Engidaye, “Random forest and support vector machine-based hybrid liver disease detection,” Bull. Electr. Eng. Informatics, vol. 11, no. 3, pp. 1650–1656, 2022, doi: https://doi.org/10.11591/eei.v11i3.3787.
Downloads
Published
Issue
Section
License
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;
