Makine Öğrenmesi Yöntemleri ile Kan Tahlilinden Covid-19 Teşhisi

Yıl 2024, Cilt: 17 Sayı: 2, 120 - 131

Büşra Çakı , Ahmet Egesoy , Yasemin Topaloğlu

https://doi.org/10.54525/bbmd.1595417

Öz

Sağlık alanında kullanılan yapay zekâ teknolojileri, makine öğrenmesi yöntemleri öncülüğünde; erken tanı, değerlendirme ve karar verme gibi pek çok alanda etkili olmaktadır. Bu teknolojiler küresel bir salgına neden olmuş olan Covid-19 hastalığına tanı koymak ve gelişiminin izlenmesinde önemli başarı göstermiştir. Bu çalışmada hastalığı tanılamak ile birlikte, şiddetini ve bulaşıcılık düzeyinin saptanmasında, makine öğrenme yöntemlerini deneyimleyen çalışmalar taranmıştır. Bu incelemede tüm deneyimlerin dikkate alınması ve anlamlı sonuçlara ulaşılması amacıyla bazı eksik veriler tamamlanmış benzer çalışmalar birleştirilmiş ve sonuçlar karşılaştırılabilir hale getirilmiştir. Ayrıca hata maliyet analizini temel alarak değerlendirme ölçülerine F-β ölçütleri de katılmıştır. Yapay sinir ağı yönteminin hastalığın tanılanması ve şiddetini belirlemede başarılı olduğu görülmektedir. Bulaşma hızının belirlenmesinde ise hangi yöntemin daha iyi olduğunu belirlemekte kullanılabilecek güvenilir bir model henüz yoktur.

Anahtar Kelimeler

Makine öğrenmesi, Covid‐19, gerçek‐zamanlı ters transkripsiyon polimeraz zincir reaksiyonu, kan sayımı.

Diagnosis of Covid-19 by Machine Learning from Blood Test

Öz

Artificial intelligence technologies that are used in healthcare are led by machine learning methods and are effective in many areas such as early diagnosis, assessment and decision making. These technologies have shown significant success in diagnosing and monitoring the course of Covid-19 disease, which has caused a global epidemic. In this paper, studies that experimented with machine learning methods in diagnosing the disease, determining its severity and level of contagion were reviewed. In the review process, in order to take all of the experiences into account and reach meaningful outcomes, some missing data were completed and similar studies were combined so as to make the results comparable. In addition, F-β criteria were included in the evaluation metrics based on error cost analysis. The artificial neural network method was found to be successful in diagnosing the disease and determining its severity. There is not yet a reliable model that can be used, to determine which method is better in determining the infection rate.

Anahtar Kelimeler

Machine learning, Covid-19, real-time reverse transcription polymerase chain reaction, blood analysis.

Kaynakça

• Lewnard JA, Lo NC. The scientific and ethical basis for social-distancing interventions against COVID-19. Lancet Infect Dis. 2020 Jun,20(6):631-633.
• Koo JR, Cook AR, Park M, Sun Y, Sun H, Lim JT, Tam C, Dickens BL. Interventions to mitigate the early spread of SARS-CoV-2 in Singapore: a modeling study. Lancet Infect Dis. 3-2020 Jun,20(6):678-688.
• Pandemi ilan edilmesi-Dünya Sağlık Örgütü. DSÖ Genel Direktörü'nün 11 Şubat 2020 tarihinde 2019-nCoV medya brifinginde yaptığı açıklamalar. https://www.who.int/dg/speeches/detail/who-director-general-s-remarks-at-the-media-briefing-on-2019-ncov-on-11-february-2020 (2020).
• Rasheed J, Jamil A, Hameed AA, Al-Turjman F, Rasheed A. COVID-19 in the Age of Artificial Intelligence: A Comprehensive Review. Interdiscip Sci Comput Life Sci. Published online April 22, 2021.
• Guan WJ, Ni ZY, Hu Y, Liang WH, Ou CQ, He JX, Liu L, Shan H, Lei CL, Hui DSC, Du B, Li LJ, Zeng G, Yuen KY, Chen RC, Tang CL, Wang T, Chen PY, Xiang J, Li SY, Wang JL, Liang ZJ, Peng YX, Wei L, Liu Y, Hu YH, Peng P, Wang JM, Liu JY, Chen Z, Li G, Zheng ZJ, Qiu SQ, Luo J, Ye CJ, Zhu SY, Zhong NS, China Medical Treatment Expert Group for Covid-19. Clinical Characteristics of Coronavirus Disease 2019 in China. N Engl J Med. 2020 Apr 30,382(18):1708-1720.
• Chen N, Zhou M, Dong X, Qu J, Gong F, Han Y, Qiu Y, Wang J, Liu Y, Wei Y, Xia J, Yu T, Zhang X, Zhang L. Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: a descriptive study. Lancet. 2020 Feb 15,395(10223):507-513.
• Rodriguez-Morales A, Cardona-Ospina J, Gutierrez-Ocampo E, Villamizar-Pe~na R, Holguin-Rivera Y, Escalera-Antezana J, Alvarado-Arnez L, Bonilla-Aldana D, Franco-Paredes C, Henao-Martinez A. Clinical, laboratory and imaging features of COVID-19: a systematic review and meta-analysis. Trav Med Infect Dis 2020,34: 101623. Demirarslan M., Suner A. Rutin kan sınamaleriyle Covid-19 tanı tahmininde makine öğrenmesi yöntemleriyle mobil uygulama geliştirilmesi. Ege Tıp Dergisi. 2021, 60(4): 384-393.
• Yao H, Zhang N, Zhang R, Duan M, Xie T, Pan J, Peng E, Huang J, Zhang Y, Xu X, Xu H, Zhou F, Wang G. Severity Detection for the Coronavirus Disease 2019 (COVID-19) Patients Using a Machine Learning Model Based on the Blood and Urine Sınamas. Front Cell Dev Biol. 2020 Jul 31,8:683.
• Booth, A.L, Abels, E, McCaffrey, P, Development of a prognostic model for mortality in COVID-19 infection using machine learning. Mod. Pathol. 2021, 34, 522–531.
• Özen N. S., Saraç S. and Koyuncu M., "COVID-19 Vakalarının Makine Öğrenmesi Algoritmaları ile Tahmini: Amerika Birleşik Devletleri Örneği", Avrupa Bilim ve Teknoloji Dergisi, no. 22, pp. 134-139, Jan. 2021.
• WHO Gender and COVID-19, World Health Organization: Geneva, Switzerland, 2020.
• Malom, Z., Rahman, M.M.S., Nasrin, S., Taha, T.M., Asari, V.K. COVID_MTNet: COVID-19 detection with multi-task deep learning approaches. arXiv 2020, arXiv:2004.03747.
• Michael J. Loeffelholz & Yi-Wei Tang (2020) Laboratory diagnosis of emerging human coronavirus infections – the state of the art, Emerging Microbes & Infections, 9:1, 747-756.
• Zhu N, Zhang D, Wang W, Li X, Yang B, Song J, Zhao X, Huang B, Shi W, Lu R, Niu P, Zhan F, Ma X, Wang D, Xu W, Wu G, Gao GF, Tan W, China Novel Coronavirus Investigating and Research Team. A Novel Coronavirus from Patients with Pneumonia in China, 2019. N Engl J Med. 2020 Feb 20,382(8):727-733.
• Coronaviridae Study Group of the International Committee on Taxonomy of Viruses. The species Severe acute respiratory syndrome-related coronavirus: classifying 2019-nCoV and naming it SARS-CoV-2. Nat Microbiol 5, 536–544 (2020).
• Assaf D, Gutman Y, Neuman Y, Segal G, Amit S, Gefen-Halevi S, Shilo N, Epstein A, Mor-Cohen R, Biber A, Rahav G, Levy I, Tirosh A. Utilization of machine-learning models to accurately predict the risk for critical COVID-19. Intern Emerg Med. 2020 Nov,15(8):1435-1443.
• Brinati D, Campaigner A, Ferrari D, Locatelli M, Banfi G, Cabitza F. Detection of COVID-19 Infection from Routine Blood Exams with Machine Learning: A Feasibility Study. J Med Syst. 2020 Jul 1,44(8):135. Zoabi Y, Deri-Rozov S, Shomron N. Machine learning-based prediction of COVID-19 diagnosis based on symptoms. NPJ Digit Med. 2021 Jan 4,4(1):3.
• Sumayh S. Aljameel, Irfan Ullah Khan, Nida Aslam, Malak Aljabri, Eman S. Alsulmi, "Machine Learning-Based Model to Predict the Disease Severity and Outcome in COVID-19 Patients", Scientific Programming, vol. 2021, Article ID 5587188, 10 pages, 2021.
• Freitas Barbosa, V.A., Gomes, J.C., de Santana, M.A. et al. Heg.IA: an intelligent system to support diagnosis of Covid-19 based on blood sınamas. Res. Biomed. Eng. 38, 99–116 (2022). Scikit-Learn, F-Bta Skoru, Erişim adresi: https://scikit-learn.org/stable/modules/generated/sklearn.metrics.fbeta_score.html, Erişim Tarihi:02.02.2023.
• Alves MA, Castro GZ, Oliveira BAS, Ferreira LA, Ramírez JA, Silva R, Guimarães FG. Explaining machine learning based diagnosis of COVID-19 from routine blood sınamas with decision trees and criteria graphs. Comput Biol Med. 2021 May,132:104335.
• Jiangpeng Wu, Pengyi Zhang, Liting Zhang, Wenbo Meng, Junfeng Li, Chongxiang Tong, Yonghong Li, Jing Cai, Zengwei Yang, Jinhong Zhu, Meie Zhao, Huirong Huang, Xiaodong Xie, Shuyan Li, Rapid and accurate identification of COVID-19 infection through machine learning based on clinical available blood sınama results medRxiv 2020.04.02.20051136.
• Chadaga K, Chakraborty C, Prabhu S, Umakanth S, Bhat V, Sampathila N. Clinical and Laboratory Approach to Diagnose COVID-19 Using Machine Learning. Interdiscip Sci. 2022 Jun,14(2):452-470.
• Kukar M, Gunčar G, Vovko T, Podnar S, Černelč P, Brvar M, Zalaznik M, Notar M, Moškon S, Notar M (2021) COVİD-19 diagnosis by routine blood sınamas using machine learning. Sci Rep 11(1):1–9.
• Yang HS, Hou Y, Vasovic LV, Steel PAD, Chadburn A, Racine-Brzostek SE, Velu P, Cushing MM, Loda M, Kaushal R, Zhao Z, Wang F. Routine Laboratory Blood Sınamas Predict SARS-CoV-2 Infection Using Machine Learning. Clin Chem. 2020 Nov 1,66(11):1396-1404.
• AlJame M, Ahmad I, Imtiaz A, Mohammed A. Ensemble learning model for diagnosing COVID-19 from routine blood sınamas. Inform Med Unlocked. 2020,21:100449
• Kang J, Chen T, Luo H, Luo Y, Du G, Jiming-Yang M. Machine learning predictive model for severe COVID-19. Infect Genet Evol. 2021 Jun,90:104737.
• Sun N, Yang Y, Tang L, Li Z, Dai Y, Xu W, et al. (2021) A Prediction Model Based on Machine Learning for Diagnosing the Early COVID-19 patients. J Antivir Antiretrovir. S18:002.
• Arpaci I, Huang S, Al-Emran M, Al-Kabi MN, Peng M (2021) Predicting the COVİD-19 infection with fourteen clinical features using machine learning classifcation algorithms. Multimedia Tools Appl 80(8):11943–11957.
• Zhang RK, Xiao Q, Zhu SL, Lin HY, Tang M. Using different machine learning models to classify patients into mild and severe cases of COVID-19 based on multivariate blood sınamaing. J Med Virol. 2022 Jan,94(1):357-365.
• Plante TB, Blau AM, Berg AN, Weinberg AS, Jun IC, Tapson VF, Kanigan TS, Adib AB (2020) Development and external validation of a machine learning tool to rule out COVİD-19 among adults in the emergency department using routine blood sınamas: a large, multicenter, real-world study. J Med Internet Res 22(12): e24048.
• dos Santos Santana ÍV, da Silveira AC, Sobrinho Á, Silva LC, da Silva LD, Santos DF, Gurjão EC, Perkusich A (2021) Classifcation models for COVİD-19 sınama prioritization in Brazil: machine learning approach. J Med Internet Res 23(4): e27293.
• Luo C. L., Rong Y., Chen H., Zhang W., Wu L., Wei D., et al. (2019). A logistic regression model for noninvasive prediction of AFP-negative hepatocellular carcinoma. Technol. Cancer Res. Treat. 18:1533033819846632.
• Heijnen B. J., Bohringer S., Speyer R. (2020). Prediction of aspiration in dysphagia using logistic regression: oral intake and self-evaluation. Eur. Arch. Otorhinolaryngol. 277 197–205.
• Zhu N, Zhang D, Wang W, Li X, Yang B, Song J, Zhao X, Huang B, Shi W, Lu R, Niu P, Zhan F, Ma X, Wang D, Xu W, Wu G, Gao GF, Tan W, China Novel Coronavirus Investigating and Research Team. A Novel Coronavirus from Patients with Pneumonia in China, 2019. N Engl J Med. 2020 Feb 20,382(8):727-733.
• Zhang RK, Xiao Q, Zhu SL, Lin HY, Tang M. Using different machine learning models to classify patients into mild and severe cases of COVID-19 based on multivariate blood sınamaing. J Med Virol. 2022 Jan,94(1):357-365.
• Laatifi M, Douzi S, Bouklouz A, Ezzine H, Jaafari J, Zaid Y, El Ouahidi B, Naciri M. Machine learning approaches in Covid-19 severity risk prediction in Morocco. J Big Data. 2022,9(1):5.
• A.F.de M. Batista, J.L. Miraglia, T.H.R. Donato, A.D.P. Chia vegatto Filho, COVID-19 diagnosis prediction in emergency care patients: a machine learning approach, 2020.
• An C, Lim H, Kim DW, Chang JH, Choi YJ, Kim SW. Machine learning prediction for mortality of patients diagnosed with COVID-19: a nationwide Korean cohort study. Sci Rep. 2020 Oct 30,10(1):18716.
• Du R, Tsougenis ED, Ho JWK, Chan JKY, Chiu KWH, Fang BXH, Ng MY, Leung ST, Lo CSY, Wong HF, Lam HS, Chiu LJ, So TY, Wong KT, Wong YCI, Yu K, Yeung YC, Chik T, Pang JWK, Wai AK, Kuo MD, Lam TPW, Khong PL, Cheung NT, Vardhanabhuti V. Machine learning application for the prediction of SARS-CoV-2 infection using blood sınamas and chest radiograph. Sci Rep. 2021 Jul 9,11(1):14250
• Bertsimas D, Lukin G, Mingardi L, Nohadani O, Orfanoudaki A, Stellato B, Wiberg H, Gonzalez-Garcia S, Parra-Calderón CL, Robinson K, Schneider M, Stein B, Estirado A, A Beccara L, Canino R, Dal Bello M, Pezzetti F, Pan A, Hellenic COVID-19 Study Group. COVID-19 mortality risk assessment: An international multi-center study. PLoS One. 2020 Dec 9,15(12): e0243262.
• Sánchez-Montañés M, Rodríguez-Belenguer P, Serrano-López AJ, Soria-Olivas E, Alakhdar-Mohmara Y. Machine Learning for Mortality Analysis in Patients with COVID-19. Int J Environ Res Public Health. 2020 Nov 12,17(22):8386.
• Hu C, Liu Z, Jiang Y, Shi O, Zhang X, Xu K, Suo C, Wang Q, Song Y, Yu K, Mao X, Wu X, Wu M, Shi T, Jiang W, Mu L, Tully DC, Xu L, Jin L, Li S, Tao X, Zhang T, Chen X. Early prediction of mortality risk among patients with severe COVID-19, using machine learning. Int J Epidemiol. 2021 Jan 23,49(6):1918-1929.
• Kocadagli O, Baygul A, Gokmen N, Incir S, Aktan C. Clinical prognosis evaluation of COVID-19 patients: An interpretable hybrid machine learning approach. Curr Res Transl Med. 2022 Jan,70(1):103319.
• Gangloff C, Rafi S, Bouzillé G, Soulat L, Cuggia M (2021) Machine learning is the key to diagnose COVİD-19: a proofof-concept study. Sci Rep 11(1):1–1.
• Wu G, Zhou S, Wang Y, Lv W, Wang S, Wang T, Li X. A prediction model of outcome of SARS-CoV-2 pneumonia based on laboratory findings. Sci Rep. 2020 Aug 20,10(1):14042.
• Göreke V, Sarı V, Kockanat S. A novel classifier architecture based on deep neural network for COVID-19 detection using laboratory findings. Appl Soft Comput. 2021 Jul,106:107329.
• Sanche, S., Lin, Y., Xu, C., Romero-Severson, E., Hengartner, N., & Ke, R. (2020). Şiddetli Akut Solunum Sendromunun Yüksek Bulaşıcılığı ve Hızlı Yayılması Koronavirüs 2. Ortaya Çıkan Bulaşıcı Hastalıklar, 26(7), 1470-1477.
• Chan JF, Yuan S, Kok KH, To KK, Chu H, Yang J, Xing F, Liu J, Yip CC, Poon RW, Tsoi HW, Lo SK, Chan KH, Poon VK, Chan WM, Ip JD, Cai JP, Cheng VC, Chen H, Hui CK, Yuen KY. A familial cluster of pneumonia associated with the 2019 novel coronavirus indicating person-to-person transmission: a study of a family cluster. Lancet. 2020 Feb 15,395(10223):514-523.