Machine Learning Classifiers and Data Synthesis Techniques to Tackle with Highly Imbalanced COVID-19 Data

Document Type : Original Article

Authors

Avaz Naghipour ¹

Mohammad Reza Abbaszadeh Bavil Soflaei ¹

mostafa ghader-zefrehei ²

¹ Department of Computer Engineering, University College of Nabi Akram, Tabriz, Iran.

² Department of Animal Science, Faculty of Agriculture, University of Yasouj, Yasouj, Iran.

10.22067/cke.2024.88940.1121

Abstract

The COVID-19 pandemic has highlighted the urgent need for rapid and accurate diagnostic methods. In this study, we evaluate three machine learning models—Random Forest (RF), Logistic Regression (LR) and Decision Tree (DT)—for detecting COVID-19 trained on preprocessed imbalanced datasets with 5086 negative and 558 positive cases. To this end, we demonstrate the capability of two advanced data synthesis algorithms, Conditional Tabular Generative Adversarial Network (CTGAN) and Tabular Variational Autoencoder (TVAE), in addressing the class imbalance inherent in the dataset. The classifiers trained on the original as well as the balanced datasets were evaluated for comparison. Our findings reveal that RF obtains the highest accuracy of 98.83% on the CTGAN-balanced dataset. In conclusion, our results verify the potential of coupling data synthesis with traditional machine learning for the diagnosis of COVID-19. We hope that this research will make a significant contribution to the current AI (Artificial Intelligence) efforts in combating the pandemic.

Keywords

COVID-19 Detection

Machine Learning

CTGAN

TVAE

Class Imbalance

Subjects

• Machine learning

---

References

[1] Naming the coronavirus disease (COVID-19) and the virus that causes it, World Health Organization, 2020.

[2] S. Hamal et al. and R. M. Gibson. (2024, Jun.). A comparative analysis of machine learning algorithms for detecting COVID-19 using lung X-ray images. Decision Analytics Journal. [Online]. 11, p. 100460. Available: 10.1016/j.dajour.2024.100460

[3] Debata, B., P. Patnaik, and A. Mishra. (2020, Sep.). COVID‐19 pandemic! It's impact on people, economy, and environment. Journal of public affairs. [Online]. 20(4), p. e2372. Available: 10.1002/pa.2372

[4] Baker, C.A. and K.E. Gibson. (2022, Oct.). Persistence of SARS-CoV-2 on surfaces and relevance to the food industry. Current Opinion in Food Science. [Online]. 47, p. 100875. Available: 10.1016/j.cofs.2022.100875

[5] Turlapati, V.P.K. and M.R. Prusty. (2020, Dec.). Outlier-SMOTE: A refined oversampling technique for improved detection of COVID-19. Intelligence-Based Medicine. [Online]. 3-4, p. 100023. Available: 10.1016/j.ibmed.2020.100023

[6] 14.9 million excess deaths associated with the COVID-19 pandemic in 2020 and 2021, WHO, 2022.

[7] B. Amma. (2024, Mar.). En-RfRsK: An ensemble machine learning technique for prognostication of diabetes mellitus. Egyptian Informatics Journal. [Online]. 25, p. 100441. Available: 10.1016/j.eij.2024.100441

[8] S. El-Sappagh et al. and H. Saleh. (2021, Sep.). The role of medication data to enhance the prediction of Alzheimer’s progression using machine learning. Computational Intelligence and Neuroscience. [Online]. (1), 2021. Available: 10.1155/2021/8439655

[9] M. A. Islam et al. and S. Jannaty. (2024, Jun.). Precision Healthcare: A Deep Dive into Machine Learning Algorithms and Feature Selection Strategies for Accurate Heart Disease Prediction. Computers in Biology and Medicine. [Online]. 176, p. 108432. Available: 10.1016/j.compbiomed.2024.108432

[10]M. R. A. B. Soflaei, A. Salehpour and K. Samadzamini. (2024, Apr.). Enhancing network intrusion detection: a dual-ensemble approach with CTGAN-balanced data and weak classifiers. The Journal of Supercomputing. [Online]. 80, pp. 16301-16333. Available: 10.1007/s11227-024-06108-7

[11]A. Luque et al. and A. D. L. Heras. (2019, Jul.). The impact of class imbalance in classification performance metrics based on the binary confusion matrix. Pattern Recognition. [Online]. 91, pp. 216-231. Available: 10.1016/j.patcog.2019.02.023

[12]L. Xu et al. and K. Veeramachaneni, "Modeling tabular data using conditional gan," Advances in neural information processing systems, 2019.

[13] C. C. Dodoo et al. and J. Mensah. (2024, Jun.). Using machine learning algorithms to predict COVID-19 vaccine uptake: A year after the introduction of COVID-19 vaccines in Ghana. Vaccine: X. [Online]. 18, p. 100466. Available: 10.1016/j.jvacx.2024.100466

[14]Oyewola, D.O., E.G. Dada, and S. Misra. (2022, Nov.). Machine learning for optimizing daily COVID-19 vaccine dissemination to combat the pandemic. Health and Technology. [Online]. 12, pp. 1277-1293. Available: 10.1007/s12553-022-00712-4

[15]S. M. I. Osman and A. Sabit. (2022, Dec.). Predictors of COVID-19 vaccination rate in USA: A machine learning approach. Machine Learning with Applications. [Online]. 10, p. 100408. Available: 10.1016/j.mlwa.2022.100408

[16] M. A. Ahmed et al. and M. Hamid Ali, "Automatic COVID-19 pneumonia diagnosis from x-ray lung image: A Deep Feature and Machine Learning Solution," Journal of Physics: Conference Series, 2021, p. 012099.

[17]E. E. D. Hemdan, M. A. Shouman,  and M. E. Karar, "Covidx-net: A framework of deep learning classifiers to diagnose covid-19 in x-ray images," arXiv preprint arXiv:2003.11055, 2020.

[18]U. Hafeez et al. and H. A. Madni. (2022, Feb.). A CNN based coronavirus disease prediction system for chest X-rays. Journal of Ambient Intelligence and Humanized Computing. [Online]. 14(10), pp. 13179-13193. Available: 10.1007/s12652-022-03775-3

[19] H. Mohammad-Rahimi et al. and S. Ghafouri-Fard. (2021, Mar.). Application of machine learning in diagnosis of COVID-19 through X-ray and CT images: a scoping review. Frontiers in cardiovascular medicine. [Online]. 8, p. 638011. Available: 10.3389/fcvm.2021.638011

[20] M. D. Broda et al. and A. West. (2024, Jul.). Understanding COVID-19 infection among people with intellectual and developmental disabilities using machine learning. Disability and Health Journal. [Online]. 17(3), p. 101607. Available: 10.1016/j.dhjo.2024.101607

[21]Y. Fu et al. and S. Wang. (2024, May.). Using machine learning algorithms based on patient admission laboratory parameters to predict adverse outcomes in COVID-19 patients. Heliyon. [Online]. 10(9): p. e29981. Available: 10.1016/j.heliyon.2024.e29981

[22] K. Halteh et al. and K. Kumar. (2024, Mar.). Using machine learning techniques to assess the financial impact of the COVID-19 pandemic on the global aviation industry. Transportation Research Interdisciplinary Perspectives. [Online]. 24, p. 101043. Available: 10.1016/j.trip.2024.101043

[23] V. Kumar et al. and O. Cheikhrouhou. (2022, Apr.). COV-DLS: prediction of COVID-19 from X-rays using enhanced deep transfer learning techniques. Journal of Healthcare Engineering. [Online]. (1), p. 6216273. Available: 10.1155/2022/6216273

[24] A. Chen et al. and J. Chan, "Detecting Covid-19 in Chest X-Rays using Transfer Learning with VGG16," CSBio '20: Proceedings of the Eleventh International Conference on Computational Systems-Biology and Bioinformatics, Association for Computing Machinery: Bangkok, Thailand, 2020, pp. 93–96.

[25] M. M. Taresh et al. and M. L. Mutar. (2021, May.). Transfer Learning to Detect COVID-19 Automatically from X-Ray Images Using Convolutional Neural Networks. International Journal of Biomedical Imaging. [Online].  2021(1), p. 8828404. Available: 10.1155/2021/8828404

[26] F. Pedregosa. (2011). Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research. [Online]. 12, pp. 2825-2830. Available: cir.nii.ac.jp

[27] H. I. Sarker. (2021, Mar.). Machine Learning: Algorithms, Real-World Applications and Research Directions. SN Computer Science. [Online]. 2(3), p. 160. Available: 10.1007/s42979-021-00592-x

[28] M. Alloghani et al. and A. J. Aljaaf. (2019, Sep.). A Systematic Review on Supervised and Unsupervised Machine Learning Algorithms for Data Science. Supervised and Unsupervised Learning for Data Science. [Online]. pp. 3-21.

[29] G. Louppe, "Understanding random forests: From theory to practice," arXiv preprint arXiv:1407.7502, 2014.

[30] Y. Belsti et al. and H. Teede. (2023, Nov.). Comparison of machine learning and conventional logistic regression-based prediction models for gestational diabetes in an ethnically diverse population; the Monash GDM Machine learning model. International Journal of Medical Informatics. [Online]. 179, p. 105228. Available: 10.1016/j.ijmedinf.2023.105228

[31] P. Rajendra and S. Latifi. (2021, Jan.). Prediction of diabetes using logistic regression and ensemble techniques. Computer Methods and Programs in Biomedicine Update. [Online]. 1, p. 100032. Available:10.1016/j.cmpbup.2021.100032

[32] M. M. Chowdhury, R. S. Ayon and M. S. Hossain. (2024, Jun.). An investigation of machine learning algorithms and data augmentation techniques for diabetes diagnosis using class imbalanced BRFSS dataset. Healthcare Analytics. [Online]. 5, p. 100297. Available: 10.1016/j.health.2023.100297

[33] I. Goodfellow et al. and Y. Bengio, "Generative adversarial nets," Advances in neural information processing systems, 2014.

[34] M. S. K. Inan, S. Hossain and M. N. Uddin.(2023, Jan.). Data augmentation guided breast cancer diagnosis and prognosis using an integrated deep-generative framework based on breast tumor’s morphological information. Informatics in Medicine Unlocked. [Online]. 37, p. 101171. Available: 10.1016/j.imu.2023.101171

[35] S. Bourou et al. and T. Zahariadis. (2021, Sep.). A Review of Tabular Data Synthesis Using GANs on an IDS Dataset. Information. [Online]. 12(9), p. 375.  Available: 10.3390/info12090375.

[36] D. P. Kingma and M. Welling, "Auto-encoding variational bayes," arXiv preprint arXiv:1312.6114, 2013.

[37] V. W. D. Vargas et al. and J. L. V. Barbosa. (2022, Nov.). Imbalanced data preprocessing techniques for machine learning: a systematic mapping study. Knowledge and Information Systems. [Online]. 65(1), pp. 31-57. Available: 10.1007/s10115-022-01772-8

[38] N. V. Chawla et al. W. P. Kegelmeyer. (2002, Jun.). SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research. [Online]. 16, pp. 321-357. Available: 10.1613/jair.953

[39] T. Hasanin, T. Khoshgoftaar, "The Effects of Random Undersampling with Simulated Class Imbalance for Big Data," IEEE International Conference on Information Reuse and Integration (IRI), Lake City, UT, USA, 2018, pp. 70-79.

[40] Imbalanced learn. Available: imbalanced-learn.org

[41] I. Ashrapov, "Tabular GANs for uneven distribution," arXiv preprint arXiv:2010.00638, 2020.