Medical Informatics III

EnglishTürkçe

CHAPTER


DOI :10.26650/B/ET07.2023.005.22   IUP :10.26650/B/ET07.2023.005.22    Full Text (PDF)

Prediction of Covid-19 Test Results with Machine Learning Algorithms

Burcu Esin İliş, Emrah Gürlek, Fadime Akdeniz, Nada Misk, Reyhan Şahinbaş, Uygar Aydın, Çiğdem Erol

The COVID-19 epidemic, which has been at the top of the world agenda since the beginning of 2020, continues its existence and impact with the effect of mutations that have emerged at different times. Due to the impact of COVID-19 on individuals and its inter-individual spread, rapid and early diagnosis gains importance. This study it is aimed to predict COVID-19 test results using machine learning algorithms. For this purpose, the COVID-19 dataset of 2,742,596 observations collected between 11.03.2020 and 12.11.2020 of 2020 by the Israeli Ministry of Health was used. Before applying classification algorithms to the data set, six different data sets were obtained by going through different preprocessing processes (deletion of missing data, filling in missing data with logistic regression, and balancing). These six different data sets were obtained as a result of preprocessing; Analysis was carried out by applying six different machine learning algorithms: Support Vector Machines (SVM), Decision TreesC 4.5 Algorithm, Gradient Boosting, Naïve Bayes, Logistic Regression Classifier, and Artificial Neural Networks (ANN). As a result, The highest performance with 80.14% accuracy and 50% no information rate (NIR) was obtained in the balanced (A2) data set by deleting the random data after the deletion of missing data with the decision tree and artificial neural network algorithms.


Keywords: COVID-19, Machine Learning, Classification Algorithms
DOI :10.26650/B/ET07.2023.005.22   IUP :10.26650/B/ET07.2023.005.22    Full Text (PDF)

Makine Öğrenmesi Algoritmaları ile Covıd-19 Test Sonuçlarının Tahmin Edilmesi

Burcu Esin İliş, Emrah Gürlek, Fadime Akdeniz, Nada Misk, Reyhan Şahinbaş, Uygar Aydın, Çiğdem Erol

2020 yılının başından itibaren dünya gündeminin en üst sıralarında yer alan COVID-19 salgını farklı zamanlarda ortaya çıkan mutasyonların da etkisi ile varlığını ve etkisini halen sürdürmektedir. COVID-19’un bireyler üzerindeki etkisi ve bireyler arası yayılımı nedeniyle hızlı ve erken teşhis edilmesi önem kazanmaktadır. Bu çalışmada makine öğrenmesi algoritmaları kullanılarak COVID-19 test sonuçlarının tahmin edilmesi amaçlanmıştır. Bu amaçla İsrail Sağlık Bakanlığı tarafından 2020 yılının 11.03.2020- 12.11.2020 tarihleri arasında toplanan 2.742.596 gözlemden oluşan COVID-19 veri seti kullanılmıştır. Veri setine sınıflandırma algoritmaları uygulamadan önce farklı önişleme süreçlerinden geçirilerek (eksik verilerin silinmesi, lojistik regresyon ile eksik verilerin doldurulması dengeleme) altı ayrı veri seti elde edilmiştir. Önişleme sonucunda elde edilen bu altı farklı veri setine; Destek Vektör Makineleri (DVM), Karar Ağaçları- C 4.5 Algoritması, Gradient Boosting, Naïve Bayes, Lojistik Regresyon Sınıflandırıcı ve Yapay Sinir Ağları (YSA) olmak üzere altı farklı makine öğrenmesi algoritması uygulanarak analiz gerçekleştirilmiştir. Sonuç olarak; %80,14 doğruluk ve %50 no information rate (NIR) ile en yüksek performans karar ağacı ve yapay sinir ağı algoritmaları ile eksik verilerin silinmesi ön işleminden sonra rastgele veri silinerek dengelenmiş (A2) veri setinde elde edilmiştir. 


Keywords: COVID-19, Makine Öğrenmesi, Sınıflandırma Algoritmaları

References

  • Ahamad, M. M., Aktar, S., Rashed-Al-Mahfuz, M., Uddin, S., Liò, P., Xu, H., … Moni, M. A. (2020). A machine learning model to identify early stage symptoms of SARS-Cov-2 infected patients. Expert Systems with Applications, 160, 113661. doi:10.1016/j.eswa.2020.113661. google scholar
  • Arslan, H., Aygün, B. (2021). Yaygın Semptomlardan Covid-19 Tespitinde Makine Öğrenmesi Algoritmalarının Karşılaştırmalı Performans Analizi. 29th Signal Processing and Communications Applications Conference (SIU), 978-1-6654-3649-6/21/$31.00 © 2021 IEEE. doi: 10.1109/SIU53274.2021.9477809 google scholar
  • Chen, T., He, T., Benesty, M., Khotilovich, V., Tang, Y., Cho, H., Chen, K., Mitchell, R., Cano, I., Zhou, T., Li, M., Xie, J., Lin, M., Geng, Y., & Li, Y. (2021). xgboost: Extreme gradient boosting (R package version 1.4.1.1) [Computer software]. The Comprehensive R Archive Network. Available from https://CRAN.R-project.org/package=xgboost google scholar
  • Corporation, M., & Weston, S. (2020). doParallel: Foreach parallel adaptor for the ‘parallel’ package (R package version 1.0.16) [Computer software]. The Comprehensive R Archive Network. Available from https:// CRAN.R-project.org/package=doParallel google scholar
  • Cortes, C., Vapnik, V. ve Saitta, L. (1995). Support-vector networks. Machine Learning 1995 20:3, 20(3), 273– 297. google scholar
  • de Moraes Batista, A. F., Miraglia, J. L., Donato, T. H. R., & Chiavegatto Filho, A. D. P. (2020). COVID-19 diagnosis prediction in emergency care patients: a machine learning approach. medRxiv, 1-8. google scholar
  • Deb, K., Pratap, A., Agarwal, S. ve Meyarivan, T. (2002). A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 6(2), 182–197. google scholar
  • Freund, Y. ve Schapire, R. E. (1997). A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting. Journal of Computer and System Sciences, 55(1), 119–139. google scholar
  • Fritsch, S., Guenther, F., & Wright, M. N. (2019). neuralnet: Training of neural networks (R package version 1.44.2) [Computer software]. The Comprehensive R Archive Network. Available from https://CRAN.R-project.org/package=neuralnet google scholar
  • Hoffmann, C. (2020). Teşhis Testleri ve Prosedürleri. B.S. Kamps, C. Hoffmann (Eds.), COVID Reference TUR 2020.5 içinde (s. 207- 234). Steinhäuser Verlag. https://amedeo.com/CovidReference05_tr.pdf. google scholar
  • Hornik, K. Buchta, C., Hothorn, T., Karatzoglou, A., Meyer, D., Zeileis, A. (2020). Package ‘RWeka’: R/Weka İnterface Available from http://cran.nexr.com/web/packages/parallelSVM/parallelSVM.pdf google scholar
  • Lalmuanawma, S., Hussain, J. ve Chhakchhuak, L. (2020). Applications of machine learning and artificial intelligence for Covid-19 (SARS-CoV-2) pandemic: A review. Chaos, Solitons and Fractals, 139, 110059. google scholar
  • Meyer, D., Dimitriadou, E., Hornik, K., Weingessel, A., & Leisch, F. (2021). e1071: Misc functions of the department of statistics, probability Theory Group (Formerly: E1071), TU Wien (R package version 1.7-9) [Computer software]. The Comprehensive R Archive Network. Available from https://CRAN.R-project. org/package=e1071 google scholar
  • Rosiers, W. (2015). Package ‘ParallelSVM’: A Parallel-Voting Versiyon of the Support-Vector-Machine Algorithm. Available from http://cran.nexr.com/web/packages/parallelSVM/parallelSVM.pdf google scholar
  • Soui, M., Mansouri, N., Alhamad, R. et al. NSGA-II as feature selection technique and AdaBoost classifier for COVID-19 prediction using patient’s symptoms. Nonlinear Dyn 106, 1453–1475 (2021). google scholar
  • T.C. Sağlık Bakanlığı Covid-19 Bilgilendirme Platformu. (2021). Covid-19 Nedir? https://covid19.saglik.gov. tr/TR-66300/covid-19-nedir-.html google scholar
  • Ünal, Y. ve Dudak, M. N. (2020). Classification of Covid-19 Dataset with Some Machine Learning Methods. Journal of Amasya University The Institute of Science and Technology (JAUIST), 1, 30–37. google scholar
  • West, C. P., Montori, V. M. ve Sampathkumar, P. (2020). COVID-19 Testing: The Threat of False-Negative Results. Mayo Clinic Proceedings, 95(6), 1127–1129. google scholar
  • World Health Organization. (2020, 11 Mart). Virtual press conference on COVID-19 [Basın Bildirisi]. https:// www.who.int/docs/default-source/coronaviruse/transcripts/who-audio-emergencies-coronavirus-press-conference-full-and-final-11mar202 google scholar
  • World Health Organization. (2021). Coronavirus Disease (COVID-19) Dashboard With Vaccination Data. World Health Organization. https://covid19.who.int/ adresinden erişildi. google scholar
  • Zoabi, Y., Deri-Rozov, S. ve Shomron, N. (2021). Machine learning-based prediction of COVID-19 diagnosis based on symptoms. npj Digital Medicine, 4(1), 1–5. google scholar


SHARE




Istanbul University Press aims to contribute to the dissemination of ever growing scientific knowledge through publication of high quality scientific journals and books in accordance with the international publishing standards and ethics. Istanbul University Press follows an open access, non-commercial, scholarly publishing.