Research Article
BibTex RIS Cite

Machine Learning Based Case Estimation Using Prophet Model with Time Series Data for Covid-19 Outbreak

Year 2020, Issue: 19, 827 - 835, 31.08.2020

Abstract

Coronaviruses were discovered in the 21st century and are a common type of virus that causes disease in humans and animals worldwide. After the SARS outbreak in 2002 and the MERS outbreaks in 2012, Covid-19 appeared in the Wuhan province of China at the end of 2019, causing an outbreak. In the period when this study was carried out, intensive studies related to Covid-19 which is still spreading and not yet under control are continuing in different disciplines, especially in the field of medicine. Almost all of the studies carried out are medical studies on the epidemiology of the virus, control and prevention activities. Machine learning, which is one of the predictive disciplines in computer science, can make consistent predictions based on the available data. The Prophet model, developed by the Facebook data science team and offered as an open source project, can provide consistent daily, weekly, periodic and annual estimates on the time series data. In this study, future estimations made with the Prophet model on the current dataset of Covid-19 cases worldwide, and it was revealed that the predictions provide a highly consistent result by comparing with real cases. In three separate estimation studies for confirmed Covid-19 cases, disease-induced deaths and survivors, it was predicted that the increase in the number of confirmed cases and deaths will be higher than the estimates in the one-week period following the date of the study, and the number of recovered cases will be based on the estimates.

References

  • K. McIntosh and S. Perlman, “Coronaviruses, including severe acute respiratory syndrome (SARS) and Middle East respiratory syndrome (MERS),” Mand. Douglas Bennetts Princ. Pract. Infect. Dis. Updat. Ed. 8th Ed Phila. PA Elsevier Saunders, 2015.
  • P. K. Chan and M. C. Chan, “Tracing the SARS-coronavirus,” J. Thorac. Dis., vol. 5, no. Suppl 2, p. S118, 2013.
  • R. J. de Groot et al., “Commentary: Middle East respiratory syndrome coronavirus (MERS-CoV): announcement of the Coronavirus Study Group,” J. Virol., vol. 87, no. 14, pp. 7790–7792, 2013.
  • E. R. Ahmet Görkem and S. ÜNAL, “2019 Koronavirüs Salgını–Anlık Durum ve İlk İzlenimler,” FLORA, vol. 25, p. 8, 2020.
  • N. Zhu et al., “A novel coronavirus from patients with pneumonia in China, 2019,” N. Engl. J. Med., 2020.
  • Johns Hopkins University (JHU), “Coronavirus COVID-19 (2019-nCoV) Global Cases.” https://gisanddata.maps.arcgis.com/apps/opsdashboard/index.html (accessed Mar. 18, 2020).
  • E. Dong, H. Du, and L. Gardner, “An interactive web-based dashboard to track COVID-19 in real time,” Lancet Infect. Dis., p. S1473309920301201, Feb. 2020, doi: 10.1016/S1473-3099(20)30120-1.
  • H. A. Rothan and S. N. Byrareddy, “The epidemiology and pathogenesis of coronavirus disease (COVID-19) outbreak,” J. Autoimmun., p. 102433, 2020.
  • V. Surveillances, “The epidemiological characteristics of an outbreak of 2019 novel coronavirus diseases (COVID-19)—China, 2020,” China CDC Wkly., vol. 2, no. 8, pp. 113–122, 2020.
  • R. M. Anderson, H. Heesterbeek, D. Klinkenberg, and T. D. Hollingsworth, “How will country-based mitigation measures influence the course of the COVID-19 epidemic?,” The Lancet, vol. 395, no. 10228, pp. 931–934, 2020.
  • A. J. Rodriguez-Morales et al., “Clinical, laboratory and imaging features of COVID-19: A systematic review and meta-analysis,” Travel Med. Infect. Dis., p. 101623, 2020.
  • T. Xu et al., “Clinical features and dynamics of viral load in imported and non-imported patients with COVID-19,” Int. J. Infect. Dis., 2020.
  • W. Yang et al., “Clinical characteristics and imaging manifestations of the 2019 novel coronavirus disease (COVID-19): A multi-center study in Wenzhou city, Zhejiang, China,” J. Infect., 2020.
  • M. A. Shereen, S. Khan, A. Kazmi, N. Bashir, and R. Siddique, “COVID-19 infection: origin, transmission, and characteristics of human coronaviruses,” J. Adv. Res., 2020.
  • S. Tian et al., “Characteristics of COVID-19 infection in Beijing,” J. Infect., 2020.
  • P. Li et al., “Transmission of COVID-19 in the terminal stage of incubation period: a familial cluster,” Int. J. Infect. Dis., 2020.
  • J. Hellewell et al., “Feasibility of controlling COVID-19 outbreaks by isolation of cases and contacts,” Lancet Glob. Health, 2020.
  • S. E. Seker, C. Mert, K. Al-Naami, N. Ozalp, and U. Ayan, “Time series analysis on stock market for text mining correlation of economy news,” Int. J. Soc. Sci. Humanity Stud., vol. 6, no. 1, pp. 69–91, 2013.
  • G. Bontempi, S. B. Taieb, and Y.-A. Le Borgne, “Machine learning strategies for time series forecasting,” in European business intelligence summer school, 2012, pp. 62–77.
  • S. J. Taylor and B. Letham, “Prophet: forecasting at scale,” Facebook Res., 2017.
  • S. J. Taylor and B. Letham, “Forecasting at scale,” Am. Stat., vol. 72, no. 1, pp. 37–45, 2018.

Covid-19 Salgınına Yönelik Zaman Serisi Verileri ile Prophet Model Kullanarak Makine Öğrenmesi Temelli Vaka Tahminlemesi

Year 2020, Issue: 19, 827 - 835, 31.08.2020

Abstract

Koronavirüsler 21. yüzyılda keşfedilen ve dünyada yaygın olarak görülen, insan ve hayvanlarda hastalığa sebep olan bir virüs türüdür. 2002 yılındaki SARS ve 2012 yılındaki MERS salgınlarından sonra, 2019 yılı sonunda Çin’in Wuhan eyaletinde ortaya çıkıp hızla yayılan Covid-19 bir pandemiye sebep olmuştur. Bu çalışmanın yapıldığı dönemde hala yayılmaya devam eden ve henüz kontrol altına alınamayan Covid-19 ile ilgili tıp alanı başta olmak üzere farklı disiplinlerde yoğun çalışmalar sürdürülmektedir. Yapılan çalışmaların neredeyse tamamı virüsün yapısı, kontrol ve önlemeye dair tıbbi çalışmalardır. Bilgisayar bilimlerinde öngörücü disiplinler içerisinde yer alan makine öğrenmesi, mevcut verilerden hareketle geleceğe dönük tutarlı tahminlerde bulunabilmektedir. Bu amaçla geliştirilen farklı modeller içerisinde Facebook veri bilimi ekibi tarafından geliştirilen ve açık kaynak kodla kullanıma sunulan Prophet modeli zaman serisi verileri üzerinde, günlük, haftalık, dönemsel, yıllık tutarlı tahminler ortaya koyabilmektedir. Bu çalışmada, dünya genelindeki Covid-19 vakalarına ilişkin güncel veri seti üzerinde, Prophet modeli ile geleceğe dönük tahminler yapılmış ve gerçek vakalarla karşılaştırılarak büyük oranda tutarlı sonuç verdikleri ortaya konmuştur. Doğrulanmış Covid-19 vakaları, virüsün sebep olduğu hastalık kaynaklı ölümler ve hastalıktan kurtulan vakalar için gerçekleştirilen üç ayrı tahminleme çalışmasında, doğrulanmış vaka ve ölüm sayılarındaki artışın çalışmanın yapıldığı tarihi takip eden bir haftalık süreçte tahminlerden yüksek olabileceği, kurtulan vaka sayılarının ise tahminler doğrultusunda gerçekleşeceği öngörülmüştür.

References

  • K. McIntosh and S. Perlman, “Coronaviruses, including severe acute respiratory syndrome (SARS) and Middle East respiratory syndrome (MERS),” Mand. Douglas Bennetts Princ. Pract. Infect. Dis. Updat. Ed. 8th Ed Phila. PA Elsevier Saunders, 2015.
  • P. K. Chan and M. C. Chan, “Tracing the SARS-coronavirus,” J. Thorac. Dis., vol. 5, no. Suppl 2, p. S118, 2013.
  • R. J. de Groot et al., “Commentary: Middle East respiratory syndrome coronavirus (MERS-CoV): announcement of the Coronavirus Study Group,” J. Virol., vol. 87, no. 14, pp. 7790–7792, 2013.
  • E. R. Ahmet Görkem and S. ÜNAL, “2019 Koronavirüs Salgını–Anlık Durum ve İlk İzlenimler,” FLORA, vol. 25, p. 8, 2020.
  • N. Zhu et al., “A novel coronavirus from patients with pneumonia in China, 2019,” N. Engl. J. Med., 2020.
  • Johns Hopkins University (JHU), “Coronavirus COVID-19 (2019-nCoV) Global Cases.” https://gisanddata.maps.arcgis.com/apps/opsdashboard/index.html (accessed Mar. 18, 2020).
  • E. Dong, H. Du, and L. Gardner, “An interactive web-based dashboard to track COVID-19 in real time,” Lancet Infect. Dis., p. S1473309920301201, Feb. 2020, doi: 10.1016/S1473-3099(20)30120-1.
  • H. A. Rothan and S. N. Byrareddy, “The epidemiology and pathogenesis of coronavirus disease (COVID-19) outbreak,” J. Autoimmun., p. 102433, 2020.
  • V. Surveillances, “The epidemiological characteristics of an outbreak of 2019 novel coronavirus diseases (COVID-19)—China, 2020,” China CDC Wkly., vol. 2, no. 8, pp. 113–122, 2020.
  • R. M. Anderson, H. Heesterbeek, D. Klinkenberg, and T. D. Hollingsworth, “How will country-based mitigation measures influence the course of the COVID-19 epidemic?,” The Lancet, vol. 395, no. 10228, pp. 931–934, 2020.
  • A. J. Rodriguez-Morales et al., “Clinical, laboratory and imaging features of COVID-19: A systematic review and meta-analysis,” Travel Med. Infect. Dis., p. 101623, 2020.
  • T. Xu et al., “Clinical features and dynamics of viral load in imported and non-imported patients with COVID-19,” Int. J. Infect. Dis., 2020.
  • W. Yang et al., “Clinical characteristics and imaging manifestations of the 2019 novel coronavirus disease (COVID-19): A multi-center study in Wenzhou city, Zhejiang, China,” J. Infect., 2020.
  • M. A. Shereen, S. Khan, A. Kazmi, N. Bashir, and R. Siddique, “COVID-19 infection: origin, transmission, and characteristics of human coronaviruses,” J. Adv. Res., 2020.
  • S. Tian et al., “Characteristics of COVID-19 infection in Beijing,” J. Infect., 2020.
  • P. Li et al., “Transmission of COVID-19 in the terminal stage of incubation period: a familial cluster,” Int. J. Infect. Dis., 2020.
  • J. Hellewell et al., “Feasibility of controlling COVID-19 outbreaks by isolation of cases and contacts,” Lancet Glob. Health, 2020.
  • S. E. Seker, C. Mert, K. Al-Naami, N. Ozalp, and U. Ayan, “Time series analysis on stock market for text mining correlation of economy news,” Int. J. Soc. Sci. Humanity Stud., vol. 6, no. 1, pp. 69–91, 2013.
  • G. Bontempi, S. B. Taieb, and Y.-A. Le Borgne, “Machine learning strategies for time series forecasting,” in European business intelligence summer school, 2012, pp. 62–77.
  • S. J. Taylor and B. Letham, “Prophet: forecasting at scale,” Facebook Res., 2017.
  • S. J. Taylor and B. Letham, “Forecasting at scale,” Am. Stat., vol. 72, no. 1, pp. 37–45, 2018.
There are 21 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Articles
Authors

Onur Sevli 0000-0002-8933-8395

Vesile Gül Başer Gülsoy 0000-0002-0752-9498

Publication Date August 31, 2020
Published in Issue Year 2020 Issue: 19

Cite

APA Sevli, O., & Başer Gülsoy, V. G. (2020). Covid-19 Salgınına Yönelik Zaman Serisi Verileri ile Prophet Model Kullanarak Makine Öğrenmesi Temelli Vaka Tahminlemesi. Avrupa Bilim Ve Teknoloji Dergisi(19), 827-835.