Prediction of the Prognosis of Covid-19 Disease Using Deep Learning Methods and Boruta Feature Selection Algorithm

Yıl 2022, Cilt: 22 Sayı: 3, 577 - 587, 30.06.2022

Nedim Muzoğlu , Melike Kaya Karaslan Ahmet Mesrur Halefoğlu Sıddık Yarman

https://doi.org/10.35414/akufemubid.1114346

Öz

Millions of people have lost their lives due to the Covid 19 pandemic, and inadequate health systems have been overwhelmed in many countries. Determining the intensive care and ventilation needs of Covid-19 patients and thus making predictions about the prognosis of the disease is crucial in terms of the patient's health status and the effective use of health systems. The Covid-19 chest computed tomography (CT) findings dataset created for this purpose consists of ground-glass opacity (GGO), consolidation, crazy paving pattern (CPP), consolidation and ground glass (GGOC), nodule and ground glass classes (GGON). The approach proposed in this study consists of four steps. The VGG16 model was trained with the chest CT findings dataset in the first step. The most discriminative features obtained in the second step were selected using the BORUTA algorithm. In the third step, the most valuable top 200, 300 and 400 features for each image were obtained by ranking method. In the last step these features were classified with Support Vector Machines and Linear Discriminant Analysis. The overall accuracy obtained for the chest CT findings dataset is 97.02%. This successful result, obtained using the dataset to predict Covid 19 disease prognosis with Deep Learning methods, is a crucial innovation in the classification of chest CT findings in viral types of pneumonia.

Anahtar Kelimeler

Covid-19, Chest ct findings, Boruta, Ground glass opacities, Consolidation, Crazy paving pattern

Boruta Öznitelik Seçimi Algoritması ve Derin Öğrenme Yöntemleri Kullanılarak Covid-19 Hastalığının Prognozunun Tahmini

Öz

Covid-19 pandemisi nedeniyle milyonlarca insan hayatını kaybetmiş ve birçok ülkede yetersiz sağlık sistemleri hizmet veremez hale gelmiştir. Covid-19 hastalarının yoğun bakım ve ventilasyon ihtiyaçlarının belirlenerek hastalığın prognozu hakkında tahminlerde bulunulması, hastanın sağlık durumu ve sağlık sistemlerinin etkin kullanımı açısından önemlidir. Bu amaçla oluşturulan Covid-19 akciğer bilgisayarlı tomografi (BT) bulguları veri seti buzlu cam opasitesi, konsolidasyon, kaldırım taşı paterni, konsodilasyon ve buzlu cam, nodül ve buzlu cam sınıflarını içermektedir. Bu çalışmada önerilen yaklaşım dört adımdan oluşmaktadır. Birinci adımda VGG-16 modeli akciğer BT bulguları veri seti ile eğitilmiştir. İkinci adımda elde edilen en ayırt edici öznitelikler BORUTA algoritması kullanılarak seçilmiştir. Üçüncü adımda sıralama yöntemiyle her görüntü için en değerli ilk 200, 300 ve 400 öznitelikler elde edilmiştir. Son adımda ise Destek Vektör Makineleri ve Lineer Diskriminant Analizi ile bu özellikler sınıflandırılmıştır. Akciğer BT bulguları veri seti için elde edilen genel doğruluk %97,02'dir. Derin Öğrenme yöntemleri ile Covid-19 hastalık prognozunu tahmin etmek için oluşturulan veri seti kullanılarak elde edilen bu başarılı sonuç, viral pnömoni türlerinin akciğer BT bulgularının sınıflandırılmasında çok önemli bir yeniliktir.

Anahtar Kelimeler

Covid-19, Akciğer bt bulguları, Boruta, Buzlu cam opasitesi, Kondolidasyon, Kaldırım taşı paterni

Kaynakça

• Ai, T., Yang, Z., Hou, H., Zhan, C., Chen, C., Lv, W., … Xia, L., 2020. Correlation of Chest CT and RT-PCR Testing for Coronavirus Disease 2019 (COVID-19) in China: A Report of 1014 Cases. Radiology, 296(2), E32–E40. https://doi.org/10.1148/radiol.2020200642
• Akbaş, İ., 2021. Emergency departments in the detection of COVID-19 cases; multi-centered data from Turkey. Haydarpasa Numune Training and Research Hospital Medical Journal, 61(3), 314–324. https://doi.org/10.14744/hnhj.2021.26121
• Akdaş Tekin, E., Meke, A., Küçükkepeci, H., Önol, S. D., Şimsek, F., Arıca, S., & Turgut, N., 2021. Prediction of Clinical Results with the First Thoracic CT Findings in COVID-2019 Patients; Survey Study. European Archives of Medical Research, 37(4), 268–272. https://doi.org/10.4274/eamr.galenos.2021.87004
• Altıntaş, D. D., & Şenol, A., 2021. Hastaneye Y atırılan COVID -19 H astalarında A kciğer B ilgisayarlı Tomografi Parankimal B ulguları ile C Reaktif Protein A rasındaki İlişki The Relationship Between Parenchymal Findings of Chest Computed Tomography and C Reactive Protein in COVID-19 Pati. Kocaeli Medical Journal, 10(2), 160–166.
• BATIREL, A., 2020. SARS-CoV-2: Ways of Transmission and Methods of Prevention. Southern Clinics of Istanbul Eurasia, 31, 1–7. https://doi.org/10.14744/scie.2020.00378
• Cau, R., Falaschi, Z., Paschè, A., Danna, P., Arioli, R., Arru, C. D., … Saba, L., 2021. CT findings of COVID-19 pneumonia in ICU-patients. Journal of Public Health Research, 10, 515–521. https://doi.org/10.4081/jphr.2021.2270
• COMERT, S. S., 2020. Radiological findings of COVID-19 pneumonia. Southern Clinics of Istanbul Eurasia, 31, 16–22. https://doi.org/10.14744/scie.2020.96158
• Cortes, C., Vapnik, V., & Saitta, L., 1995. Support-Vector Networks Editor. In Machine Leaming (Vol. 20). Kluwer Academic Publishers.
• Çelik, D., & Köse, Ş., 2020. COVID-19 in Adults: Clinical Findings. The Journal of Tepecik Education and Research Hospital, 30, 43–48. https://doi.org/10.5222/terh.2020.88896
• Ding, X., Xu, J., Zhou, J., & Long, Q., 2020. Chest CT findings of COVID-19 pneumonia by duration of symptoms. European Journal of Radiology, (January), 127.
• Fang, Y., Zhang, H., Xie, J., Lin, M., Ying, L., Pang, P., & Ji, W., 2020. Sensitivity of chest CT for COVID-19: Comparison to RT-PCR. Radiology, Vol. 296, E115–E117. Radiological Society of North America Inc. https://doi.org/10.1148/radiol.2020200432
• Gayaf, M., Anar, C., Güldaval, F., Karadeniz, G., Polat, G., Ayrancı, A., … Tatar, D., 2021. Clinical Characteristics and Transmission Routes of COVID-19 in the Early Period of the Pandemic in a Non-Covid Ward of Chest Diseases Hospital. Journal of İzmir Chest Hospital, 35(3), 140–148. https://doi.org/10.5222/igh.2021.24633
• Hashimoto N, Suzuki K, Liu J, et al., 2018. Deep neural network convolution (NNC) for three-class classification of diffuse lung disease opacities in high-resolution CT (HRCT): Consolidation, ground-glass opacity (GGO), and normal opacity. Med Imaging 2018 10575,113. https://doi.org/10.1117/12.2293550
• Hatipoğlu, N., 2020. The “New” Problem of Humanity: New Coronavirus (2019-nCoV / COVID-19) Disease. Medical Journal of Bakirkoy, 16(1), 1–8. https://doi.org/10.5222/BMJ.2020.22931
• Karahacıoğlu, D., Önol, S. D., Bayraktarlı, R. Y., & Şimşek, F. (2022). COVID-19 Pneumonia: Variation of Chest Computed Tomographic Findings at Different Phases of Disease. European Archives of Medical Research, 38(1), 61–66. https://doi.org/10.4274/eamr.galenos.2022.27676
• Kauczor, H. U., Heitmann, K., Heussel, C. P., Marwede, D., Uthmann, T., & Thelen, M., 2000. Automatic detection and quantification of ground-glass opacities on high-resolution CT using multiple neural networks: Comparison with a density mask. American Journal of Roentgenology, 175(5), 1329–1334. https://doi.org/10.2214/ajr.175.5.1751329
• Kıral, N., 2021. The effect of frequency of comorbidity on the severity and prognosis of hospitalized patients with SARS-Cov-2 infection. Southern Clinics of Istanbul Eurasia, 32 (March 2020), 245–252. https://doi.org/10.14744/scie.2021.35467
• Kursa, M. B., Jankowski, A., & Rudnicki, W. R., 2010. Boruta - A system for feature selection. Fundamenta Informaticae, 101(4), 271–285. https://doi.org/10.3233/FI-2010-288
• Li, K., Wu, J., Wu, F., Guo, D., Chen, L., Fang, Z., & Li, C., 2020. The Clinical and Chest CT Features Associated with Severe and Critical COVID-19 Pneumonia. Investigative Radiology, 55(6), 327–331. https://doi.org/10.1097/RLI.0000000000000672
• OZER, K. B., 2020. The Effect of Radiological and Laboratory Parameters on Prognosis in COVID 19 Disease. Southern Clinics of Istanbul Eurasia, 31(3), 203–207. https://doi.org/10.14744/scie.2020.87609
• Özdemir, Ö., 2021. Pathogenesis of Imaging in COVID-19 (narrative review). Southern Clinics of Istanbul Eurasia, 33(1), 92–97. https://doi.org/10.14744/scie.2021.97658
• Park, C. H., & Park, H., 2008. A comparison of generalized linear discriminant analysis algorithms. Pattern Recognition, 41(3), 1083–1097. https://doi.org/10.1016/j.patcog.2007.07.022
• Pekçevik, Y., & Belet, Ü., 2020. Patient Management in the Radiology Department, the Role of Chest Imaging During the SARS-CoV-2 Pandemic and Chest CT Findings Related to COVID-19 Pneumonia. The Journal of Tepecik Education and Research Hospital, 30, 195–212. https://doi.org/10.5222/terh.2020.13549
• Quiroz, J. C., Feng, Y. Z., Cheng, Z. Y., Rezazadegan, D., Chen, P. K., Lin, Q. T., … Cai, X. R., 2021. Development and validation of a machine learning approach for automated severity assessment of COVID-19 based on clinical and imaging data: Retrospective study. JMIR Medical Informatics, 9(2), 1–14. https://doi.org/10.2196/24572
• Tekcan Sanli, D. E., Yildirim, D., Sanli, A. N., Erozan, N., Husmen, G., Altundag, A., … Erel Kirisoglu, C., 2021. Predictive value of CT imaging findings in COVID-19 pneumonia at the time of first-screen regarding the need for hospitalization or intensive care unit. Diagnostic and Interventional Radiology, 27(5), 599–606. https://doi.org/10.5152/dir.2020.20421
• Toğaçar, M., Ergen, B., & Cömert, 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, 121. https://doi.org/10.1016/j.compbiomed.2020.103805
• Toğaçar, M., Muzoğlu, N., Ergen, B., Yarman, B. S. B., & Halefoğlu, A. M., 2022. Detection of COVID-19 findings by the local interpretable model-agnostic explanations method of types-based activations extracted from CNNs. Biomedical Signal Processing and Control, 71. https://doi.org/10.1016/j.bspc.2021.103128
• Togay, A., & Yılmaz, N., 2020. Laboratory Diagnosis of SARS-CoV-2. The Journal of Tepecik Education and Research Hospital, 30, 70–75. https://doi.org/10.5222/terh.2020.13007
• Türken, M., & Köse, Ş., 2020. COVID-19 Transmission and Prevention. The Journal of Tepecik Education and Research Hospital, 30, 36–42. https://doi.org/10.5222/terh.2020.02693
• Yang, X., He, X., Zhao, J., Zhang, Y., Zhang, S., & Xie, P., 2020. COVID-CT-Dataset: A CT Scan Dataset about COVID-19. Retrieved from http://arxiv.org/abs/2003.13865
• İnternet kaynakları 1 -https://covid19.who.int/,(04.05.2022)