Covid-19 Pandemic and Investigation of Artificial Intelligence Applications Used in the Pandemic

Abstract

İnsanlık tarihinde toplu ölümlere ve yıkımlara sebep olan onlarca pandemi yaşandığı kuşkusuzdur. Hızlı ve kıtalar arası sınır tanımayan yayılımıyla Covid-19 hastalığı da bir pandemiye dönüşmüştür. Covid-19 pandemisi, bazı kaynaklara göre insanlık tari-hinin başına gelen en büyük felaketlerden biridir. Dünya genelinde alınan çok ciddi önlemlere rağmen Covid-19 sağlık sistemlerini ve insan yaşamını tehdit etmeye de-vam etmektedir. Bu şartlar altında hem mevcut pandemiyi kontrol altına almada hem de yeni pandemilere karşı hazırlıklı olma noktasında insanlık daha hızlı, daha verimli, daha düşük maliyetli ve daha fazla doğruluğa sahip tanı ve tedavi yöntemlerine ihtiyaç duymaktadır. Hiç kuşkusuz doğru tasarlanmış ve hizmete sunulmuş yapay zekâ tekno-lojileri bize bu desteği sağlayacaktır. Öyle ki, eş zamanlı yürütülen birçok aşı çalışması, pandemi döneminde hayatı kolaylaştıran birçok uygulama, öngörü ve tahmin yeteneği olan yapay zekâ algoritmalarının kullanımı gibi durumlar, pandeminin yıkılıcığını bir miktar azaltmıştır. Bu çalışmanın amacı; güncel veriler ve literatür ışığında, koronavirüs kaynaklı pandemileri ve SARS-CoV-2 virüsünü genel olarak değerlendirmek; yapay zekanın özelliklerini açıklayarak pandemi sürecinde kullanılan yapay zekâ uygulamala-rına örnekler sunmaktır

Keywords

• Koronavirüs
• Covid-19
• Pandemi
• Yapay zekâ
• SARS-CoV-2

Covid-19 Pandemisi ve Pandemi Sürecinde Kullanılan Yapay Zekâ Uygulamaları

Abstract

It is certain that there have been dozens of pandemics in human history that caused mass deaths and destruction. Covid-19 disease has also turned into a pandemic with its rapid and intercontinental spread. According to some sources, the Covid-19 pandemic is one of the worst disasters in human history. Despite very serious precautions taken worldwide, Covid-19 continues to threaten health systems and human life. Under these conditions, humanity needs faster, cheaper, more efficient and more accurate diagnostic and treatment methods both in order to control the current pandemic and to be prepared for new pandemics. Undoubtedly, artificial intelligence technologies that are correctly designed and put into service will provide us with this support. In fact, many simulta-neous vaccination studies, many applications that make life easier during the pandemic period, the use of artificial intelligence algorithms with foresight and predictive ability, have somewhat reduced the destruction of the pandemic. This study aims to evaluate the coronavirus-induced pandemics and SARS-CoV-2 virus in general in the light of current data and literature, to explain the features of artificial intelligence, and to present examples of artificial intelligence applications used in the pandemic period.

Keywords

• Coronavirus
• Covid-19
• Pandemic
• Artificial Intelligence
• SARS-CoV-2

References

1. 1- Aslan R. Tarihten Günümüze Epidemiler, Pandemiler veCovid-19. Ayrıntı Dergisi. 2020 Apr;8:85.
2. 2- Özkoçak V, Koç F, Gültekin T. Pandemilere antropolojikbakış: koronavirüs (covid-19) örneği. Turkish Studies. 2020Apr;15(2):1183-1195. doi: 10.29228/TurkishStudies.42679
3. 3- Turing AM, 2009. Computing Machinery and Intelligence,In: Parsing the Turing Test, Ed; Epstein R, Roberts G, Beber G, First edition, Springer, Dordrecht, Netherlands, pp; 23-65. doi: 10.1007/978-1-4020-6710-5_3 4- Ak Ö. Küresel Kabus: Coronavirüs ve Covid-19 [Internet].Turkey: TÜBİTAK Bilim ve Teknik Dergisi; 2020 Mar [cited2020 Dec 12]. Available from: https://bilimteknik.tubitak.gov.tr/makale/soguk-alginligindan-olumcul-salgina-kuresel-ka-bus-coronavirus-ve-covid-19AUCP-value -19 90 (114 of 127) [83, 94]96 (294 of 307) [93, 98]0.96[0.94, 0.99]<0.001 CAP87 (152 of 175) [81, 91]92 (239 of 259) [88, 95]0.95[0.93, 0.97]<0.001 Non-94 (124 of 132) [88, 97]96 (291 of 302) [94, 98]0.98[0.97, 0.99]<0.001 Note: -19 = comm- neural network.Table 4. Performance of COVNet, the Deep Learning System, in the Independent Test SetCovid-19 and Al applications22
4. 5- UludağÖ. Koronavirüs enfeksiyonları ve yeni düşman:Covid-19. ADYÜSağlık Bilimleri Dergisi. 2020 Apr;6(1):118-127. doi: 10.30569/adiyamansaglik.716011
5. 6- Budak F, Korkmaz Ş. COVID-19 Pandemi Sürecine Yöne-lik Genel Bir Değerlendirme: Türkiye Örneği. Sosyal Araştır-malar ve Yönetim Dergisi. 2020 May;1:62-79. doi: 10.35375/sayod.738657
6. 7- Hasöksüz M, Kılıç S, Saraç F. Coronaviruses and SARS-COV-2. Turk J Med Sci. 2020 May;50:549-556. doi: 10.3906/sag-2004-127
7. 8- Alp Ş, Ünal S. Yeni koronavirüs (SARS-CoV-2) kaynaklıpandemi: Gelişmeler ve güncel durum. FLORA Dergisi. 2020May;25:69574. doi: 10.5578/flora.69574
8. 9- Samancı M. Küresel Bir Salgın: Covid-19. Samsun Sağ BilDer. 2020 June;5(1):6-11.

9. 10- Ulasli M, Verheije MH, de Haan CA, Reggiori F. Qualitativeand quantitative ultrastructural analysis of the membrane rear-rangements induced by coronavirus. Cellular microbiology. 2010May;12(6):844-861. doi: 10.1111/j.1462-5822.2010.01437.x
10. 11- Mavi D, İnkaya AÇ. Covid-19: İmmün patogenez. FLORA Dergisi. 2020 May;25:69606. doi: 10.5578/flora.69606
11. 12- Oxford Insights, Government Artificial Intelligence Readi-ness Index [internet], England, Oxford Insights and the Interna-tional Development Research Centre; 2019 Nov [cited 2021 Jan11]. Available from: https://www.oxfordinsights.com/ai-readi-ness2019
12. 13- Atav A. İlaçların diğer ilaçlar ile etkileşimlerinin uzmansistem ile belirlenmesi [master thesis]. [İstanbul (Turkey)]:Maltepe University, 2020.
13. 14- Turban E, Aronson JE, Liang TP. Decision Support SystemAnd Intelligent System, 7th ed., Prentice Hall Inc, New Jersey,2005. p.300-357.
14. 15- Turban E. Decision Support and Expert Systems: Manage-ment Support Systems, 4th ed., Prentice Hall Inc, New Jersey,1995, p435-675.
15. 16- Kliegr T, Bahnik S, Fürnkranz J. A review of possible effectsof cognitive biases on interpretation of rule-based machine learn-ing models. Artificial Intelligence. 2021 Jan;295:103458. doi:10.1016/j.artint.2021.103458
16. 17- Shrestha YR, Ben-Menahem SM, von Krogh G. Organiza-tional Decision-Making Structures in the Age of Artificial Intel-ligence. California Management Review. 2019 July;61(4):66-83.doi:10.1177/0008125619862257
17. 18- Dimiduk DM, Holm EA, Niezgoda SR. Perspectives on theImpact of Machine Learning, Deep Learning, and Artificial In-telligence on Materials, Processes, and Structures Engineering.Integr Mater Manuf Innov. 2018 Aug;7:157–172. doi: 10.1007/s40192-018-0117-8
18. 19- Liao SH. Expert system methodologies and applications—adecade review from 1995 to 2004. Expert Systems with Appli-cations. 2005 Jan;28(1):93-103. doi: 10.1016/j.eswa.2004.08.003
19. 20- Russell S, Dewey D, Tegmark M. Research Priorities forRobust and Beneficial Artificial Intelligence. AI Magazine. 2015Dec;36(4):105-114. doi: 10.1609/aimag.v36i4.2577
20. 21- Russel S, Hauert S, Altman R, Veloso M. Ethics of artificialintelligence. Nature. 2015 May;521:415-418.
21. 22- Tamer HY, Övgün B. Yapay Zeka Bağlamında Diji-tal Dönüşüm Ofisi. Ankara Üniversitesi SBF Dergisi. 2020May;75(2):775-803. doi: 10.33630/ausbf.691119
22. 23- Thierer AD, O’Sullivan AC, Russell R. Artificial Intelligenceand Public Policy. Mercatus Research Paper, 2017 Aug. Avail-able at SSRN: https://ssrn.com/abstract=3021135. doi: 10.2139/ssrn.302113524- Scherer MU. Regulating Artificial Intelligence Systems:Risks, Challenges, Competencies, and Strategies. Harvard Jour-nal of Law&Technology. 2016 Sep;29(2):354-400. doi: 10.2139/ssrn.2609777
23. 25- Lipmann RP. An Introduction to Computing with NeuralNets. IEEE ASSP Magazine. 1987 Apr;4(2):4-22. doi: 10.1109/MASSP.1987.1165576.
24. 26- Gupta S, Sharma V, Johri P. Artificial Intelligence in ForensicScience. International Research Journal of Engineering and Tech-nology. 2020 May;7(5):7181-7184.
25. 27- Uzun MM. Covid-19 ile Mücadelede Yapay Zekâ Uygulama-ları. ULİSA12. 2020 May;2:45-51.
26. 28- Lalmuanawma S, Hussain J, Chhakchhuak L. Applications ofmachine learning and artificial intelligence for Covid-19 (SARS-CoV-2) pandemic: A review. Chaos Solitons Fractals. 2020Oct;139:110059. doi: 10.1016/j.chaos.2020.110059
27. 29- Vaishya R, Javaid M, Haleem KI, Haleem A. Artificial In-telligence (AI) applications for COVID-19 pandemic. Dia-betes&Metabolic Syndrome. 2020 Apr;14(4):337-339. doi:10.1016/j.dsx.2020.04.012
28. 30- Worldmeters. The counter of coronavirus case in South Korea[internet]. South Korea, Government of South Korea; 2020 Dec[cited 2020 Dec 10]. Available from: https://www.worldometers.info/coronavirus/country/south-korea/
29. 31- Lin L, Hou Z. Combat COVID-19 with artificial intelligenceand big data. Journal of Travel Medicine. 2020 May;27(5):1-4.doi: 10.1093/jtm/taaa080
30. 32- Li L, Qin L, Xu Z, Yin Y, Wang X, Kong B, Bai J, Lu Y, FangZ, Song Q, Cao K, Liu D, Wang G, Xu Q, Fang X, Zhang S,Xia J, Xia J. Artificial Intelligence Distinguishes COVID-19 fromCommunity Acquired Pneumonia on Chest CT. Radiology. 2020Mar;200905. doi: 10.1148/radiol.2020200905
31. 33- Toğaçar M, Ergen B, Cömert Z. Covid-19 detection usingdeep learning models to exploit Social Mimic Optimizationand structured chest X-ray images using fuzzy color and stack-ing approaches. Computers in biology and Medicine. 2020June;121:103805. doi 10.1016/j.compbiomed.2020.103805
32. 34- Chu J. Artificial intelligence model detects asymptomaticCovid-19 infections through cellphone-recorded coughs [in-ternet]. USA, MIT News Office; 2020 Oct [cited 12 Jan 2021].Available from: https://news.mit.edu/2020/covid-19-cough-cell-phone-detection-1029
33. 35- FDA. Emergency Use Authorization Summary The KrogerHealth Covid-19 Test Home Collection Kit [internet]. USA, FDA;2021 Feb [cited 2021 Feb 24]. Available from: https://www.fda.gov/media/139683/download
34. 36- Jonker CM, Snoep JL, Treur J, Westerhoff HV, WijngaardsWC. Putting intentions into cell biochemistry: an artificial in-telligence perspective. Journal of Theoretical Biology. 2002Jan;214(1):105-134. doi: 10.1006/jtbi.2001.2444
35. 37- Zimmerman DE, Kulikowski CA, Huang Y, Feng W, TashiroM, Shimotakahara S, Chien C, Powers R, Montelione GT. Au-tomated analysis of protein NMR assignments using methodsfrom artificial intelligence. Journal of molecular biology. 1997June;269(4):592-610.
36. 38- Smith DM, Smith JC. Repurposing Therapeuticsfor COVID-19: Supercomputer-Based Docking to the-SARS-CoV-2Viral Spike ProteinandViral Spike Protein-HumanACE2 Interface. Chemrxiv, preprint. 2020 Mar. doi: 10.26434/chemrxiv.11871402.v4
37. 39- Richardson P, Griffin I, Tucker C, Smith D, Oechsle O, Phel-an A, Rawling M, Savory E, Stebbing J. Baricitinib as potentialtreatment for 2019-nCoV acute respiratory disease. Lancet. 2020Mar;395(10223):30-31. doi: 10.1016/S0140-6736(20)30304-4
38. 40- Scudellari M. Five Companies Using AI to Fight Coronavirus [internet]. USA, Spectrum IEEE; 2020 Mar [cited 2021 Jan 13]. Available from: https://spectrum.ieee.org/thehuman-os/artifi-cial-intelligence/medicalai/companies-ai-coronavirus
39. 41- Zhavoronkov A, Aladinskiy VA, Zhebrak A, Zagribelnyy B,Terentiev V, Bezrukov DS, Polykovskiy D, Shayakhmetov R, Fili-monov A, Orekhov P, Yan Y, Popova O, Vanhaelen Q, Aliper A,Ivanenkov YA. Potential 2019-nCoV 3C-like Protease InhibitorsDesigned Using Generative Deep Learning Approaches. Chem-Rxiv, preprint. 2020 Mar. doi: 10.26434/chemrxiv.11829102
40. 42- StoneWise. StoneWise Latest Devoloment [internet] China,StoneWise; 2020 Feb [cited 2021 Jan 17]. Available from: http://www.stonewise.cn/Report_en
41. 43- IBM. Artificial intelligence in medicine [internet]. USA,IBM Watson Health; 2020 Oct [cited 2021 Jan 18]. Availablefrom: https://www.ibm.com/watson-health/learn/artificial-intelli-gence-medicine