COVID-19 Enfeksiyonunun Nitelik Seçme ile Birleştirilmiş Makine Öğrenmesi Yöntemleriyle Tahmin Edilmesi

Year 2022, Issue: 37, 52 - 58, 15.07.2022

Umut Ahmet Çetin , Fatih Abut

https://doi.org/10.31590/ejosat.1132337

Abstract

COVID-19, 31 Aralık 2019'dan itibaren dünyayı etkisi altına alan ve Mart 2020'de DSÖ tarafından pandemi ilan edilen bir enfeksiyondur. Bu çalışmada, yeni nitelik seçme tabanlı COVID-19 tahmin modelleri oluşturmak ve COVID-19 enfeksiyonunun tahmini için etkili değişkenleri ayırt etmek için minimum fazlalık maksimum önem (mRMR) ve Relief-F nitelik seçiciler ile ayrı ayrı birleştirilmiş Çok Katmanlı Algılayıcı (MLP), Tree Boost (TB), Radyal Temelli Fonksiyon Ağı (RBF), Destek Vektör Makinesi (SVM) ve K-Means Kümeleme (kMC) yöntemleri kullanılmıştır. Veri seti, 20.000 hasta (10.000 pozitif, 10.000 negatif) ile ilgili bilgileri içermektedir ve çeşitli kişisel, semptomatik ve asemptomatik değişkenlerden oluşmaktadır. Modellerin performansını değerlendirmek için doğruluk, duyarlılık ve F1-Skor metrikleri kullanılmıştır ve modellerin genelleme hataları 10 katlı çapraz doğrulama ile değerlendirilmiştir. Sonuçlar, bir hastanın COVID-19 enfeksiyonunu tahmin etmede mRMR’ın ortalama performansının Relief-F’den biraz daha iyi olduğunu göstermektedir. Ek olarak, mRMR’ın, COVID-19 tahmin değişkenlerinin göreceli alaka sırasını bulmada Relief-F algoritmasından daha başarılı olduğu gözlemlenmiştir. mRMR algoritması ateş ve öksürük gibi semptomatik değişkenleri vurgularken, Relief-F algoritması yaş ve ırk gibi asemptomatik değişkenleri öne çıkarmaktadır. Ayrıca, genel olarak MLP’nin COVID-19 enfeksiyonunu tahmin etmede diğer tüm sınıflandırıcılarından daha iyi performans gösterdiği de gözlemlenmiştir.

Keywords

Relief-F, mRMR, makine öğrenmesi, tahmin, COVID-19, koronavirüs

Project Number

FYL-2021-14257

Predicting COVID-19 Infection Using Machine Learning Methods Combined with Feature Selection

Abstract

COVID-19 is an infection that has affected the world since December 31, 2019, and was declared a pandemic by WHO in March 2020. In this study, Multi-Layer Perceptron (MLP), Tree Boost (TB), Radial Basis Function Network (RBF), Support Vector Machine (SVM), and K-Means Clustering (kMC) individually combined with minimum redundancy maximum relevance (mRMR) and Relief-F have been used to construct new feature selection-based COVID-19 prediction models and discern the influential variables for prediction of COVID-19 infection. The dataset has information related to 20.000 patients (i.e., 10.000 positives, 10.000 negatives) and includes several personal, symptomatic, and non-symptomatic variables. The accuracy, recall, and F1-score metrics have been used to assess the models’ performance, whereas the generalization errors of the models were evaluated using 10-fold cross-validation. The results show that the average performance of mRMR is slightly better than Relief-F in predicting the COVID-19 infection of a patient. In addition, mRMR is more successful than the Relief-F algorithm in finding the relative relevance order of the COVID-19 predictors. The mRMR algorithm emphasizes symptomatic variables such as fever and cough, whereas the Relief-F algorithm highlights non-symptomatic variables such as age and race. It has also been observed that, in general, MLP outperforms all other classifiers for predicting the COVID-19 infection.

Keywords

Relief-F, mRMR, machine learning, prediction, COVID-19, coronavirus

Supporting Institution

Çukurova University Scientific Research Projects Center

Project Number

FYL-2021-14257

References

• Althnian, A., Elwafa, A. A., Aloboud, N., Alrasheed, H., & Kurdi, H. (2020). Prediction of COVID-19 Individual Susceptibility using Demographic Data: A Case Study on Saudi Arabia. In Procedia Computer Science (Vol. 177, pp. 379–386). https://doi.org/10.1016/j.procs.2020.10.051
• Ciotti, M., Ciccozzi, M., Terrinoni, A., Jiang, W.-C., Wang, C.-B., & Bernardini, S. (2020). The COVID-19 pandemic. In Critical Reviews in Clinical Laboratory Sciences (Vol. 57, Issue 6, pp. 365–388). Informa UK Limited. https://doi.org/¬10.1080/10408363.2020.1783198
• COVID Live. (2022, May 15). Worldometers. https://www.-worldometers.info/coronavirus/
• Data on COVID-19 pandemic. (2021, May 24). Open Data from the State of Espirito Santo. https://dados.es.gov.br/-dataset/dados-sobre-pandemia-covid-19/resource/38cc5066-020d-4c5a-b4c0-e9f690deb6d4
• Fayyoumi, E., Idwan, S., & AboShindi, H. (2020). Machine Learning and Statistical Modelling for Prediction of Novel COVID-19 Patients Case Study: Jordan. In International Journal of Advanced Computer Science and Applications (Vol. 11, Issue 5). The Science and Information Organization. https://doi.org/10.14569/ijacsa.2020.0110518
• Hanchuan Peng, Fuhui Long, & Ding, C. (2005). Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. In IEEE Transactions on Pattern Analysis and Machine Intelligence (Vol. 27, Issue 8, pp. 1226–1238). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/-tpami.2005.159 Hsu, C. W., Chang, C. C., & Lin, C. J. (2003). A practical guide to support vector classification.
• Kulis, B., & Jordan, M. I. (2011). Revisiting k-means: New Algorithms via Bayesian Nonparametrics (Version 2). arXiv. https://doi.org/10.48550/ARXIV.1111.0352
• Natekin, A., & Knoll, A. (2013). Gradient boosting machines, a tutorial. In Frontiers in Neurorobotics (Vol. 7). Frontiers Media SA. https://doi.org/10.3389/fnbot.2013.00021
• Orr, M. J. (1996). Introduction to radial basis function networks.
• Popescu, M. C., Balas, V. E., Perescu-Popescu, L., & Mastorakis, N. (2009). Multilayer perceptron and neural networks. WSEAS Transactions on Circuits and Systems, 8(7), 579-588.
• Prakash, K. B. (2020). Analysis, Prediction and Evaluation of COVID-19 Datasets using Machine Learning Algorithms. In International Journal of Emerging Trends in Engineering Research (Vol. 8, Issue 5, pp. 2199–2204). The World Academy of Research in Science and Engineering. https://doi.org/10.30534/ijeter/2020/117852020
• Robnik-Šikonja, M., & Kononenko, I. (2003). In Machine Learning (Vol. 53, Issue 1/2, pp. 23–69). Springer Science and Business Media LLC. https://doi.org/10.1023/a:-1025667309714
• Souza, F. S. H., Hojo-Souza, N. S., dos Santos, E. B., da Silva, C. M., & Guidoni, D. L. (2020). Predicting the disease outcome in COVID-19 positive patients through Machine Learning: a retrospective cohort study with Brazilian data. https://doi.org/10.1101/2020.06.26.20140764
• Viana dos Santos Santana, Í., CM da Silveira, A., Sobrinho, Á., Chaves e Silva, L., Dias da Silva, L., Santos, D. F. S., Gurjão, E. C., & Perkusich, A. (2021). Classification Models for COVID-19 Test Prioritization in Brazil: Machine Learning Approach (Preprint). JMIR Publications Inc. https://doi.org/10.2196/preprints.27293
• Wollenstein-Betech, S., Cassandras, C. G., & Paschalidis, I. Ch. (2020). Personalized Predictive Models for Symptomatic COVID-19 Patients Using Basic Preconditions: Hospitalizations, Mortality, and the Need for an ICU or Ventilator. https://doi.org/10.1101/2020.05.03.20089813