ANALISIS PERFORMA SMOTE DAN SMOTE-TOMEKLINK UNTUK KLASIFIKASI DIABETES : XGBOOST-SHAP
DOI:
https://doi.org/10.37859/seis.v6i2.11357
Abstract
This study examines the effects of SMOTE and SMOTE-TomekLink on XGBoost classification and SHAP interpretability using an imbalanced diabetes dataset (100,000 samples, 91.5% : 8.5% ratio). Three research gaps are addressed: (i) direct experimental comparison of both resampling techniques within identical pipelines; (ii) quantification of minority sensitivity stability through Stratified 5-Fold Cross-Validation; and (iii) reliability of post-resampling SHAP interpretation. Results demonstrate significant superiority of SMOTE-TomekLink with a F1-score of 0.89 (SMOTE 0.85, baseline 0.81), recall of 0.86 (SMOTE 0.85, baseline 0.70), and the lowest false positive rate of 176 cases (SMOTE 345, baseline 40). The lowest cross-validation standard deviation (0.0021) validates superior stability. These figures meet the very good performance category (F1-score >0.85, recall >0.80) for imbalanced medical classification. Primary contribution: the first controlled comparative design that simultaneously examines resampling effects on classification metrics and SHAP interpretation validity. SHAP analysis verifies HbA1c and blood glucose as dominant predictors (52.3% variance), consistent with medical standards.
Downloads
References
Abousaber, I., Abdallah, H. F., & El-Ghaish, H. (2024). 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
Adeleke, O., Adebowale, O. J., Ayoade, I., Olawuyi, I., & Jen, T.-C. (2026). Residential energy consumption dynamics: A SHAP-based interpretation, k-means clustering, and predictive modelling. Green Energy and Resources, 100169. https://doi.org/10.1016/j.gerr.2026.100169
Arabani, M., Safari, M., & Rahimabadi, M. M. (2026). SHAP-Based Ensemble Machine Learning for Predicting Hveem-Derived Shear Strength from Marshall Tests. Results in Engineering, 109853. https://doi.org/10.1016/j.rineng.2026.109853
Ashisha, G. R., Mary, X. A., Kanaga, E. G. M., Andrew, J., & Eunice, R. J. (2024). Random Oversampling-Based Diabetes Classification via Machine Learning Algorithms. International Journal of Computational Intelligence Systems, 17(1). https://doi.org/10.1007/s44196-024-00678-3
Ayoade, O. B., Shahrestani, S., & Ruan, C. (2025). Machine Learning and Deep Learning Approaches for Predicting Diabetes Progression: A Comparative Analysis. Electronics (Switzerland), 14(13). https://doi.org/10.3390/electronics14132583
Elhadad, A., Rayan, A., & Taloba, A. I. (2026). A novel APSGWO-XGBoost framework for heart disease detection: Enhancing diagnostic accuracy and efficiency in healthcare. Journal of Radiation Research and Applied Sciences, 19(1), 102258. https://doi.org/10.1016/j.jrras.2026.102258
Elreedy, D., Atiya, A. F., & Kamalov, F. (2024). A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning. Machine Learning, 113(7), 4903–4923. https://doi.org/10.1007/s10994-022-06296-4
Fachmi, A. N., Dwi Patria, R., Ramadhan, F. R., Pudjiati, S., & Sari, A. P. (2026). Perbandingan Kinerja Klasifikasi Data Mining untuk Diagnosis Diabetes. https://ejournal.sisfokomtek.org/index.php/jumin/article/view/8024/4681
Ghufron Syifa, M., Anissa Maori, N., Sucipto, A., & Studi Tekni, P. (2026). Penerapan SMOTE dan XGBoost untuk Klasifikasi Penyakit Ginjal Kronis pada Data yang Tidak Seimbang.
Hairani, H., Anggrawan, A., & Priyanto, D. (2023). Improvement Performance of the Random Forest Method on Unbalanced Diabetes Data Classification Using Smote-Tomek Link. www.joiv.org/index.php/joiv
Islam, Md. N., Rimon, Md. M. H., Shamim, S. S.-E.-A., Fahad, Z. M., Mony, Md. J. I., & Chowdhury, Md. J. U. (2025). An Improved Ensemble-Based Machine Learning Model with Feature Optimization for Early Diabetes Prediction. http://arxiv.org/abs/2512.02023
Jang, Y. (2025). Feature-based ensemble modeling for addressing diabetes data imbalance using the SMOTE, RUS, and random forest methods: a prediction study. Ewha Medical Journal, 48(2), e32. https://doi.org/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 (Switzerland), 13(6). https://doi.org/10.3390/app13064006
Kumar, Y., Koul, A., Singla, R., & Ijaz, M. F. (2023). Artificial intelligence in disease diagnosis: a systematic literature review, synthesizing framework and future research agenda. Journal of Ambient Intelligence and Humanized Computing, 14(7), 8459–8486. https://doi.org/10.1007/s12652-021-03612-z
Muhammad, M., Samodro, J., Sakti, M., Kumudasmoro, B. M., Fahmi, M., & Nahdli, M. (2026). Analisis Pengaruh Ketidakseimbangan Data terhadap Kinerja Model Klasifikasi Penyakit Jantung (Vol. 6, Number 1). https://ejurnal.umri.ac.id/index.php/SEIS/article/view/11050/4100
Netayawijit, P., Chansanam, W., & Sorn-In, K. (2025). Interpretable Machine Learning Framework for Diabetes Prediction: Integrating SMOTE Balancing with SHAP Explainability for Clinical Decision Support. Healthcare (Switzerland), 13(20). https://doi.org/10.3390/healthcare13202588
Optarina, Y., Suarna, N., Bahtiar, A., Rahaningsih, N., & Prihartono, W. (2026). OPTIMASI MODEL XGBOOST UNTUK PREDIKSI PENYAKIT JANTUNG MENGGUNAKAN OPTUNA. Jurnal Software Engineering and Information System (SEIS), 6(1), 50–55. https://ejurnal.umri.ac.id/index.php/SEIS/article/view/10527/4096
Pinem, J., Astuti, W., & Adiwijaya. (2025). Explainable Ensemble Learning Framework with SMOTE, SHAP and LIME for Predicting 30-Day Readmission in Diabetic Patients. Jurnal RESTI, 9(5), 983–990. https://doi.org/10.29207/resti.v9i5.6977
Rafie, Z., Talab, M. S., Koor, B. E. Z., Garavand, A., Salehnasab, C., & Ghaderzadeh, M. (2025). Leveraging XGBoost and explainable AI for accurate prediction of type 2 diabetes. BMC Public Health, 25(1). https://doi.org/10.1186/s12889-025-24953-w
Sadeghi, S., Khalili, D., Ramezankhani, A., Mansournia, M. A., & Parsaeian, M. (2022). Diabetes mellitus risk prediction in the presence of class imbalance using flexible machine learning methods. BMC Medical Informatics and Decision Making, 22(1). https://doi.org/10.1186/s12911-022-01775-z
Septiana Rizky, P., Haiban Hirzi, R., Hidayaturrohman, U., Hamzanwadi Selong Jl TGKH Muhammad Zainuddin Abdul Madjid Pancor, U., & Timur, L. (2022). Perbandingan Metode LightGBM dan XGBoost dalam Menangani Data dengan Kelas Tidak Seimbang. In J Statistika (Vol. 15, Number 2). www.unipasby.ac.id
Sir, Y. A., & Soepranoto, A. H. H. (2022). Pendekatan Resampling Data Untuk Menangani Masalah Ketidakseimbangan Kelas. Jurnal Komputer Dan Informatika, 10(1), 31–38. https://doi.org/10.35508/jicon.v10i1.6554
Sirag, A., & Nor, N. M. (2021). Out-of-pocket health expenditure and poverty: Evidence from a dynamic panel threshold analysis. Healthcare (Switzerland), 9(5). https://doi.org/10.3390/healthcare9050536
Sukamto, T. F., Prameswary, C. L., Royadi, D., & Sofia, D. (2025). Diabetes Disease Prediction on Unbalanced Data Using SMOTE-Tomek Links and Random Forest Algorithm. G-Tech: Jurnal Teknologi Terapan, 9(3), 1194–1203. https://doi.org/10.70609/g-tech.v9i3.7164
Zhang, Y., Deng, L., & Wei, B. (2024). Imbalanced Data Classification Based on Improved Random-SMOTE and Feature Standard Deviation. Mathematics, 12(11). https://doi.org/10.3390/math12111709
Zuhairi, A. H., Yakub, F., Omar, M., Sharifuddin, M., Razak, K. A., & Faruq, A. (2024). Imbalanced Flood Forecast Dataset Resampling Using SMOTE-Tomek Link. International Exchange and Innovation Conference on Engineering and Sciences, 10, 845–850. https://doi.org/10.5109/7323359
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Arifah Budi Hidayah, Ali Nur Ikhsan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Copyright Notice
An author who publishes in the Journal of Software Engineering and Information System (SEIS) agrees to the following terms:
- Author retains the copyright and grants the journal the right of first publication of the work simultaneously licensed under the Creative Commons Attribution-ShareAlike 4.0 License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal
- Author is able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book) with the acknowledgement of its initial publication in this journal.
- Author is permitted and encouraged to post his/her work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of the published work (See The Effect of Open Access).
Read more about the Creative Commons Attribution-ShareAlike 4.0 Licence here: https://creativecommons.org/licenses/by-sa/4.0/.
