EKMGS: A HYBRID CLASS BALANCING METHOD FOR MEDICAL DATA PROCESSING

Authors

DOI:

https://doi.org/10.37943/18PUYJ4315

Keywords:

imbalance, genetic algorithm (GA), oversampling, undersampling, hybrid, data analysis

Abstract

The field of medicine is witnessing rapid development of AI, highlighting the importance of proper data processing. However, when working with medical data, there is a problem of class imbalance, where the amount of data about healthy patients significantly exceeds the amount of data about sick ones. This leads to incorrect classification of the minority class, resulting in inefficient operation of machine learning algorithms. In this study, a hybrid method was developed to address the problem of class imbalance, combining oversampling (GenSMOTE) and undersampling (ENN) algorithms. GenSMOTE used frequency oversampling optimization based on a genetic algorithm, selecting the optimal value using a fitness function. The next stage implemented an ensemble method based on stacking, consisting of three base (k-NN, SVM, LR) and one meta-model (Decision Tree). The hyperparameters of the meta-model were optimized using the GridSearchCV algorithm. During the study, datasets on diabetes, liver diseases, and brain glioma were used. The developed hybrid class balancing method significantly improved the quality of the model: the F1-score increased by 10-75%, and accuracy by 5-30%. Each stage of the hybrid algorithm was visualized using a nonlinear UMAP algorithm. The ensemble method based on stacking, in combination with the hybrid class balancing method, demonstrated high efficiency in solving classification tasks in medicine. This approach can be applied for diagnosing various diseases, which will increase the accuracy and reliability of forecasts. It is planned to expand the application of this approach to large volumes of data and improve the oversampling algorithm using additional capabilities of the genetic algorithm.

Author Biographies

Zholdas Buribayev, Al-Farabi Kazakh National University, Kazakhstan

PhD, Аcting associate professor, Department of Computer Science

Saida Shaikalamova, Al-Farabi Kazakh National University, Kazakhstan

BSc, Laboratory assistant, Department of Computer Science

Ainur Yerkos, Al-Farabi Kazakh National University, Kazakhstan

MSc, Lecturer, Department of Computer Science

Rustem Imanbek, Al-Farabi Kazakh National University, Kazakhstan

MSc, Software Engineer, Department of Computer Science

References

Xu, Z. , Shen, D. , Nie, T. , Kou, Y. , Yin, N. , & Han, X. (2021). A cluster-based oversampling algorithm combining SMOTE and k-means for imbalanced medical data. Information Sciences, 572, 574- 589. https://doi.org/10.1016/j.ins.2021.02.056

Khushi, M., Shaukat, K., Alam, T. M., Hameed, I. A., Uddin, S., Luo, S., Yang, X., & Reyes, M. C. (2021). A Comparative Performance Analysis of Data Resampling Methods on Imbalance Medical Data. IEEE Access, 9, 109960–109975.

Mienye, I.D., & Sun, Y. (2021). Performance analysis of cost-sensitive learning methods with ap- plication to imbalanced medical data. Informatics in Medicine Unlocked, 25, 100690. https://doi. org/10.1016/j.imu.2021.100690

Wang, Y.-C., & Cheng, C.-H. (2021). A multiple combined method for rebalancing medical data with class imbalances. Computers in Biology and Medicine, 134, 104527. https://doi.org/10.1016/j. compbiomed.2021.104527

Lee, D., & Kim, K. (2021). An efficient method to determine sample size in oversampling based on classification complexity for imbalanced data. Expert Systems with Applications, 184, 115442. https://doi.org/10.1016/j.eswa.2021.115442

Abdi, L. , & Hashemi, S. (2016). To Combat Multi-Class Imbalanced Problems by Means of Over-Sam- pling Techniques. IEEE Transactions on Knowledge and Data Engineering, 28(1), 238–251. https:// doi.org/10.1109/TKDE.2015.2458858

Malek, N.H.A., Yaacob, W.F.W., Wah, Y.B., Md Nasir, S.A., Shaadan, N., & Indratno, S.W. (2022). Com- parison of ensemble hybrid sampling with bagging and boosting machine learning approach for imbalanced data. Indonesian Journal of Electrical Engineering and Computer Science, 29(1), 598. https://doi.org/10.11591/ijeecs.v29.i1.pp598-608

Xu, Z., Shen, D., Nie, T., & Kou, Y. (2020). A hybrid sampling algorithm combining MSMOTE and ENN based on Random forest for medical imbalanced data. Journal of Biomedical Informatics, 107, 103465. https://doi.org/10.1016/j.jbi.2020.103465

Analyticalmindsltd/smote_variants. (2024). [Jupyter Notebook]. analyticalmindsltd. https://github. com/analyticalmindsltd/smote_variants (Original work published 2018)

Jiang, K., Lu, J., & Xia, K. (2016). A Novel Algorithm for Imbalance Data Classification Based on Genetic Algorithm Improved SMOTE. Arabian Journal for Science and Engineering, 41(8), 3255– 3266. https://doi.org/10.1007/s13369-016-2179-2

Pristyanto, Y., Setiawan, N.A., & Ardiyanto, I. (2017). Hybrid resampling to handle imbalanced class on classification of student performance in classroom. 2017 1st International Conference on Informatics and Computational Sciences (ICICoS), 207–212. https://doi.org/10.1109/ICI- COS.2017.8276363

Choirunnisa, S., & Lianto, J. (2018). Hybrid Method of Undersampling and Oversampling for Han- dling Imbalanced Data. 2018 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), 276–280. https://doi.org/10.1109/ISRITI.2018.8864335

Nekooeimehr, I., & Lai-Yuen, S. K. (2016). Adaptive semi-unsupervised weighted oversampling (A-SUWO) for imbalanced datasets. Expert Systems with Applications, 46, 405–416. https://doi. org/10.1016/j.eswa.2015.10.031

Agustianto, K., & Destarianto, P. (2019). Imbalance Data Handling using Neighborhood Cleaning Rule (NCL) Sampling Method for Precision Student Modeling. 2019 International Conference on Computer Science, Information Technology, and Electrical Engineering (ICOMITEE), 86-89. https:// doi.org/10.1109/ICOMITEE.2019.8921159

Tang, B., & He, H. (2015). ENN: Extended Nearest Neighbor Method for Pattern Recognition [Research Frontier]. IEEE Computational Intelligence Magazine, 10(3), 52–60. https://doi.org /10.1109/MCI.2015.2437512

Tasci, E., Zhuge, Y., Kaur, H., Camphausen, K., & Krauze, A.V. (2022). Hierarchical Voting-Based Feature Selection and Ensemble Learning Model Scheme for Glioma Grading with Clinical and Molecular Characteristics. International Journal of Molecular Sciences, 23(22), 14155. https://doi. org/10.3390/ijms232214155

Diabetes. (n.d.). Retrieved 19 March 2024, from https://www.who.int/health-topics/diabetes

Devarbhavi, H., Asrani, S.K., Arab, J.P., Nartey, Y.A., Pose, E., & Kamath, P.S. (2023). Global burden of liver disease: 2023 update. Journal of Hepatology, 79(2), 516–537. https://doi.org/10.1016/j. jhep.2023.03.017

Mesfin, F.B., & Al-Dhahir, M.A. (2024). Gliomas. In StatPearls. StatPearls Publishing. http://www. ncbi.nlm.nih.gov/books/NBK441874/

Siahaan, W.F.A., Sitompul, O.S., & Situmorang, Z. (2020). The Accuracies of ANFIS and Genetic Algorithm with Tournament Selection on Classifying Hepatitis Data. 1566(1). Scopus. https://doi. org/10.1088/1742-6596/1566/1/012121

Downloads

Published

2024-06-30

How to Cite

Buribayev, Z. ., Shaikalamova, S., Yerkos, A. . ., & Imanbek, R. . . (2024). EKMGS: A HYBRID CLASS BALANCING METHOD FOR MEDICAL DATA PROCESSING. Scientific Journal of Astana IT University, 18, 5–16. https://doi.org/10.37943/18PUYJ4315

Issue

Section

Information Technologies
betpas
pendik escort anadolu yakasi escort bostanci escort kadikoy escort kartal escort kurtkoy escort umraniye escort
maltepe escort ataşehir escort ataşehir escort ümraniye escort pendik escort kurtköy escort anadolu yakası escort üsküdar escort şerifali escort kartal escort gebze escort kadıköy escort bostancı escort göztepe escort kadıköy escort bostancı escort üsküdar escort ataşehir escort maltepe escort kurtköy escort anadolu yakası escort ataşehir escort beylikdüzü escort