Classification of the death ratio of COVID-19 Pandemic using Machine Learning Techniques

Yıl 2022, , 566 - 581, 31.08.2022

Efehan Ulaş , Enes Filiz

https://doi.org/10.18185/erzifbed.1090984

Öz

Since the COVID-19 pandemic has appeared, many epidemiological models are developed around the world to estimate the number of infected individuals and the death ratio of the COVID-19 outbreak. There are several models developed on COVID-19 by using machine learning techniques. However, studies that considered feature selection in detail are very limited. Therefore, the aim of this study is to (i) investigate the independent and interactive effects of a diverse set of features and (ii) find the algorithms that are significant for classifying the death ratio of the COVID-19 outbreak. It was found that logistic regression and decision tree (C4.5, Random Forests, and REPTree) are the most suitable algorithms. A diverse set of features obtained by feature selection methods are the number of new tests per thousand, new cases per million, hospital patients per million, and weekly hospital admissions per million. The importance of this study is that a high rate of classification was obtained with a few features. This study showed that only the most relevant features should be considered in classification and the use of all variables in classification is not necessary.

Anahtar Kelimeler

Classification, Machine learning, Decision tree, COVID-19, Feature selection

Makine Öğrenimi Teknikleri kullanılarak COVID-19 Pandemisinin ölüm oranının sınıflandırılması

Öz

COVID-19 pandemisi ortaya çıktığından beri, enfekte olmuş bireylerin sayısını ve COVID-19 salgınının ölüm oranını tahmin etmek için dünya çapında birçok epidemiyolojik model geliştirilmiştir. CoVID-19 üzerinde makine öğrenimi teknikleri kullanılarak geliştirilmiş birkaç model bulunmaktadır. Ancak öznitelik seçimini ayrıntılı olarak ele alan çalışmalar oldukça sınırlıdır. Bu nedenle, bu çalışmanın amacı (i) çeşitli özelliklerin bağımsız ve etkileşimli etkilerini araştırmak ve (ii) COVID-19 salgınının ölüm oranını sınıflandırmak için önemli olan algoritmaları bulmaktır. Lojistik regresyon ve karar ağacının (C4.5, Random Forests ve REPTree) en uygun algoritmalar olduğu bulunmuştur. Öznitelik seçme yöntemleriyle elde edilen çeşitli öznitelikler, binde yeni test sayısı, milyonda yeni vaka, milyonda hastane hasta sayısı ve milyonda haftalık hastane kabulüdür. Bu çalışmanın önemi, birkaç özellik ile yüksek oranda sınıflandırma elde edilmiş olmasıdır. Bu çalışma, sınıflandırmada sadece en ilgili özelliklerin dikkate alınması gerektiğini ve sınıflandırmada tüm değişkenlerin kullanılmasının gerekli olmadığını göstermiştir.

Anahtar Kelimeler

Sınıflandırma, Makine öğrenmesi, Karar ağaçları, COVID-19, Öznitelik seçimi

Kaynakça

• Ai, T., Yang, Z., Hou, H., Zhan, C., Chen, C., Lv, W., . . . Xia, L. (2020). Correlation of chest ct and rt-pcr testing in coronavirus disease 2019 (covid-19) in china: a report of 1014 cases. Radiology, 200642.
• Ardabili, S. F., Mosavi, A., Ghamisi, P., Ferdinand, F., Varkonyi-Koczy, A. R., Reuter, U., . . . Atkinson, P. M. (2020). Covid-19 outbreak prediction with machine learning. Available at SSRN 3580188.
• Ardakani, A. A., Kanafi, A. R., Acharya, U. R., Khadem, N., & Mohammadi, A. (2020). Application of deep learning technique to manage covid-19 in routine clinical practice using ct images: Results of 10 convolutional neural networks. Computers in Biology and Medicine, 103795.
• Barstugan, M., Ozkaya, U., & Ozturk, S. (2020). Coronavirus (covid-19) classification using ct images by machine learning methods. arXiv preprint arXiv:2003.09424.
• Bertsimas, D., Lukin, G., Mingardi, L., Nohadani, O., Orfanoudaki, A., Stellato, B., . . . others (2020). Covid-19 mortality risk assessment: An international multi-center study. PloS one, 15(12), e0243262.
• Bhandari, S., Shaktawat, A. S., Tak, A., Patel, B., Shukla, J., Singhal, S., . . . others (2020). Logistic regression analysis to predict mortality risk in covid-19 patients from routine hematologic parameters. Ibnosina Journal of Medicine and Biomedical Sciences, 12(2), 123. Bradley, A. P. (1997). The use of the area under the roc curve in the evaluation of machine learning algorithms. Pattern recognition, 30(7), 1145–1159.
• Breiman, L. (2001). Random forests. Machine learning, 45(1), 5–32.
• Chang, W., Cheng, J., Allaire, J., Xie, Y., McPherson, J., et al. (2017). Shiny: web application framework for r. R package version, 1(5).
• Chen, X.-W., & Liu, M. (2005). Prediction of protein–protein interactions using random decision forest framework. Bioinformatics, 21(24), 4394–4400.
• Dong, E., Du, H., & Gardner, L. (2020). An interactive web-based dashboard to track covid-19 in real time. The Lancet infectious diseases, 20(5), 533–534.
• Donner, A., & Klar, N. (1996). The statistical analysis of kappa statistics in multiple samples. Journal of clinical epidemiology, 49(9), 1053–1058.
• Du, R.-H., Liang, L.-R., Yang, C.-Q., Wang, W., Cao, T.-Z., Li, M., . . . others (2020). Predictors of mortality for patients with covid-19 pneumonia caused by sars-cov-2: a prospective cohort study. European Respiratory Journal, 55(5).
• Eibe, F., Hall, M. A., & Witten, I. H. (2016). The weka workbench. online appendix for data mining: practical machine learning tools and techniques. In Morgan kaufmann.
• Fanelli, D., & Piazza, F. (2020). Analysis and forecast of covid-19 spreading in china, Italy and france. Chaos, Solitons & Fractals, 134, 109761.
• Flesia, L., Monaro, M., Mazza, C., Fietta, V., Colicino, E., Segatto, B., & Roma, P. (2020). Predicting perceived stress related to the covid-19 outbreak through stable psychological traits and machine learning models. Journal of clinical medicine, 9(10), 3350.
• Hosmer, D. W. (2000). Lemeshow s. applied logistic regression. New York.
• Jansson, J. (2016). Decision tree classification od products using c5. 0 and prediction of workload using time series analysis.
• Jiang, F., Meng, W., & Meng, X. (2009). Selectivity estimation for exclusive query translation in deep web data integration. In International conference on database systems for advanced applications (pp. 595–600).
• Kalmegh, S. (2015). Analysis of weka data mining algorithm reptree, simple cart and ran- domtree for classification of indian news. International Journal of Innovative Science, En- gineering & Technology, 2(2), 438–446.
• Loey, M., Manogaran, G., Taha, M. H. N., & Khalifa, N. E. M. (2020). A hybrid deep transfer learning model with machine learning methods for face mask detection in the era of the covid-19 pandemic. Measurement, 167, 108288.
• Magleby, R., Westblade, L. F., Trzebucki, A., Simon, M. S., Rajan, M., Park, J., ... Satlin, M. J. (2020). Impact of sars-cov-2 viral load on risk of intubation and mortality among hospitalized patients with coronavirus disease 2019. Clinical infectious diseases.
• Mele, M., & Magazzino, C. (2020). Pollution, economic growth, and covid-19 deaths in india: a machine learning evidence. Environmental Science and Pollution Research, 1–9.
• Quinlan, J. R. (2014). C4. 5: programs for machine learning. Elsevier.
• Ruan, Q., Yang, K., Wang, W., Jiang, L., & Song, J. (2020). Clinical predictors of mortality due to covid-19 based on an analysis of data of 150 patients from wuhan, china. Intensive care medicine, 46(5), 846–848.
• Soares, R. d. C. M., Mattos, L. R., & Raposo, L. M. (2020). Risk factors for hospitalization and mortality due to covid-19 in esp ́ırito santo state, brazil. The American journal of tropical medicine and hygiene, 103(3), 1184–1190.
• Srinivasan, D. B., & Mekala, P. (2014). Mining social networking data for classification using reptree. International Journal of Advance Research in Computer Science and Management Studies, 2(10).
• Sugumaran, V., Muralidharan, V., & Ramachandran, K. (2007). Feature selection using decision tree and classification through proximal support vector machine for fault diagnostics of roller bearing. Mechanical systems and signal processing, 21(2), 930–942.
• Team, R. C. (2017). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria.
• Togacar, M., Ergen, B., & Comert, Z. (2020). Covid-19 detection using deep learning models to exploit social mimic optimization and structured chest x-ray images using fuzzy color and stacking approaches. Computers in Biology and Medicine, 103805.
• ULAŞ, E. (2021). Prediction of COVID-19 Pandemic Before The Latest Restrictions in Turkey by Using SIR Model. Suleyman Demirel University Journal of Science, 16(1).
• Vaid, S., Cakan, C., & Bhandari, M. (2020). Using machine learning to estimate unobserved covid-19 infections in north america. The Journal of bone and joint surgery. American volume.
• Wang, P., Zheng, X., Li, J., & Zhu, B. (2020). Prediction of epidemic trends in covid-19 with logistic model and machine learning technics. Chaos, Solitons & Fractals, 139, 110058.
• Wu, J., Zhang, P., Zhang, L., Meng, W., Li, J., Tong, C., ... others (2020). Rapid and accurate identification of covid-19 infection through machine learning based on clinical available blood test results. medRxiv.
• Xu, K., Zhou, M., Yang, D., Ling, Y., Liu, K., Bai, T., ... Li, J. (2020). Application of ordinal logistic regression analysis to identify the determinants of illness severity of covid-19 in china. Epidemiology & Infection, 148.
• Yadav, M., Perumal, M., & Srinivas, M. (2020). Analysis on novel coronavirus (covid-19) using machine learning methods. Chaos, Solitons & Fractals, 139, 110050.
• Yesilkanat, C. M. (2020). Spatio-temporal estimation of the daily cases of covid-19 in worldwide using random forest machine learning algorithm. Chaos, Solitons & Fractals, 140, 110210.