Incorporating Feature Selection Methods into Machine Learning-Based Covid-19 Diagnosis

Danacı, Çağla; Tuncer, Seda Arslan

doi:10.2478/acss-2022-0002

Abstract

The aim of the study is to diagnose Covid-19 by machine learning algorithms using biochemical parameters. In addition to the aim of the study, October selection was performed using 14 different feature selection methods based on the biochemical parameters available to us. As a result of the study, the performance of the algorithms and feature selection methods was evaluated using performance evaluation criteria. The dataset used in the study consists of 100 covid-negative and 121 covid-positive data from a total of 221 patients. The dataset includes 16 biochemical parameters used for the diagnosis of Covid-19. Feature selection methods were used to reduce the number of parameters and perform the classification process. The result of the study shows that the new feature set obtained using feature selection algorithms yields very similar results to the set containing all features. Overall, 5 features obtained from 16 features by feature selection methods yielded the best performance for the K-Nearest Neighbour algorithm with the FSVFS feature selection method of 86.4 %.

References

[1] A. Til, “Yeni Koranavirüs hastalığı hakkında bilinmesi gerekenler”, in 2020 Göller Bölgesi Aylık Ekonomi ve Kültür Dergisi, 2020, pp. 53–57.
Search in Google Scholar Back to article
[2] D. M. Ali, L. G. Zake, & N. K. El Kady, “Role of chest computed tomography versus real time reverse transcription polymerase chain reaction for diagnosis of COVID-19: A systematic review and meta-analysis”, Interdisciplinary Perspectives on Infectious Diseases, vol. 2021, Jun. 2021, Art no. 8798575. https://doi.org/10.1155/2021/8798575818432234194491
Search in Google Scholar Back to article
[3] U. Bilge, “Tıpta yapay zekâ ve uzman sistemler”, Türkiye Bilişim Derneği Kongresi, 2007, pp. 113–118.
Search in Google Scholar Back to article
[4] L. Li et al., “Artificial intelligence distinguishes COVID-19 from community acquired pneumonia on chest CT”, Radiology, vol. 296, no. 2, Mar. 2020, Art no. 200905. https://doi.org/10.1148/radiol.2020200905723347332191588
Search in Google Scholar Back to article
[5] F. S. H. De Souza, N. S. Hojo-Souza, E. B. Dos Santos, C. M. Da Silva, & D. L. Guidoni, “Predicting the disease outcome in COVID-19 positive patients through machine learning: A retrospective cohort study with Brazilian data”, Frontiers in Artificial Intelligence, vol. 4, 2021, Art no. 579931. https://doi.org/10.3389/frai.2021.579931842786734514377
Search in Google Scholar Back to article
[6] H. Budak, “Özellik seçim yöntemleri ve yeni bir yaklaşım”, Journal of the Institute of Natural and Applied Sciences of Süleyman Demirel University, vol. 22(Private), 21, 2018.10.19113/sdufbed.01653
Search in Google Scholar Back to article
[7] M. Karakaş. “Sınıflandırma problemlerinde özellik seçimi için karşıtlık tabanlı gri kurt optimizasyon algoritması”, Master Thesis, Bilecik Şeyh Edebali University, 2020, pp. 80.
Search in Google Scholar Back to article
[8] W. Yang, K. Wang, & W. Zuo, “Neighborhood component feature selection for high-dimensional data”, JCP, vol. 7, pp. 161–168, 2012. https://doi.org/10.4304/jcp.7.1.161-168
Search in Google Scholar Back to article
[9] Neighborhood component analysis (NCA) feature selection – MATLAB & Simulink. [Online]. Available: https://www.mathworks.com/help/stats/neighborhood-component-analysis.html. Accessed on: November 24, 2021.
Search in Google Scholar Back to article
[10] K. Güçkıran, İ. Cantürk, & L. Özyılmaz, “DNA microarray gene expression data classification using SVM, MLP, and RF with feature selection methods relief and LASSO”, Journal of the Institute of Natural and Applied Sciences of Suleyman Demirel University, vol. 23, no. 1, pp. 115–121, Apr. 2019. https://doi.org/10.19113/sdufenbed.453462
Search in Google Scholar Back to article
[11] T. Miftahushudur, C. Wael, & T. Praludi, “Infinite latent feature selection technique for hyperspectral image classification”, Jurnal Elektronika dan Telekomunikasi, vol. 19, no. 1, pp. 32–37, 2019. https://doi.org/10.14203/jet.v19.32-37
Search in Google Scholar Back to article
[12] F. Haider, S. Pollak, P. Albert, & S. Luz, “Emotion recognition in low-resource settings: An evaluation of automatic feature selection methods”, Computer Speech & Language, vol. 65, Jan. 2021, Art no. 101119. https://doi.org/10.1016/j.csl.2020.101119
Search in Google Scholar Back to article
[13] G. Cong, W.-C. Peng, W. E. Zhang, C. Li, & A. Sun, “Advanced data mining and applications”, in 13th International Conference, ADMA 2017, Singapore, November 5–6, 2017. https://doi.org/10.1007/978-3-319-69179-4
Search in Google Scholar Back to article
[14] G. Roffo, S. Melzi, U. Castellani, A. Vinciarelli, & M. Cristani, “Infinite feature selection: A graph-based feature filtering approach”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 12, pp. 4396–4410, Dec. 2021. https://doi.org/10.1109/TPAMI.2020.300284332750789
Search in Google Scholar Back to article
[15] Infinite Feature Selection – File Exchange – MATLAB Central. [Online]. Available: https://www.mathworks.com/matlabcentral/fileexchange/54763-infinite-feature-selection. Accessed on: November 24, 2021.
Search in Google Scholar Back to article
[16] S. Adams, R. Meekins, & P. A. Beling, “An empirical evaluation of techniques for feature selection with cost”, in 2017 IEEE International Conference on Data Mining Workshops (ICDMW), New Orleans, LA, USA, 2017, pp.834–841. https://doi.org/10.1109/ICDMW.2017.153
Search in Google Scholar Back to article
[17] F. Liu, & X. Liu, “Unsupervised feature selection for multi-cluster data via smooth distributed score”, in Emerging Intelligent Computing Technology and Applications, D.-S. Içinde, P. Huang, P. Gupta, X. Zhang, & P. Premaratne, Eds. Springer, Berlin, Heidelberg, 2012, pp. 74–79. https://doi.org/10.1007/978-3-642-31837-5_11
Search in Google Scholar Back to article
[18] R. Duangsoithong, & T. Windeatt, “Correlation-based and causal feature selection analysis for ensemble classifiers”, in Artificial Neural Networks in Pattern Recognition, F. Schwenker, & N. El Gayar, Eds. Springer, Berlin, Heidelberg, 2010, pp. 25–36. https://doi.org/10.1007/978-3-642-12159-3_3
Search in Google Scholar Back to article
[19] E. Yakut, B. Elmas, & S. Yavuz, “Yapay sinir ağları ve destek vektör makineleri yöntemleri borsa endeksi tahmini“, Süleyman Demirel Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, vol. 19, pp. 139–157, 2014.
Search in Google Scholar Back to article
[20] T. Kavzoğlu, & İ. Colkesen, “Karar ağaçları İle uydu görüntülerinin sınıflandırılması: Kocaeli Örneği“, Harita Teknolojileri Elektronik Dergisi, vol. 2, no. 1, pp. 36–45, 2010.
Search in Google Scholar Back to article
[21] M. F. Akca, “Karar Ağaçları (Makine Öğrenmesi Serisi-3)“, Deep Learning Türkiye. [Online]. Available: https://medium.com/deep-learning-turkiye/karar-a%C4%9Fa%C3%A7lar%C4%B1-makine-%C3%B6%C4%9Frenmesi-serisi-3-a03f3ff00ba5. Accessed on: November 23, 2020).
Search in Google Scholar Back to article
[22] E. Arslan, “Makine Öğrenmesi – KNN (K-Nearest neighbors) algoritması”, Medium. [Online]. Available: https://medium.com/@arslanev/makine-%C3%B6%C4%9Frenmesiknn-k-nearest-neighbors-algoritmas%C4%B1-bdfb688d7c5f. Accessed on: May 19, 2020.
Search in Google Scholar Back to article
[23] E. Çelik, M. Atalay, & H. Bayer, “Yapay sinir ağları ve destek vektör makineleri ile deprem tahminde sismik darbelerin kullanılması”, in 2014 IEEE 22nd Signal Processing and Communications Applications Conference, 2014.
Search in Google Scholar Back to article

Incorporating Feature Selection Methods into Machine Learning-Based Covid-19 Diagnosis

Abstract

Paradigm

My account