open access

Vol 88, No 5 (2020)
Research paper
Published online: 2020-10-24
Submitted: 2020-04-25
Accepted: 2020-06-24
Get Citation

Using a simple open-source automated machine learning algorithm to forecast COVID-19 spread: A modelling study

Shahir Asfahan, Maya Gopalakrishnan, Naveen Dutt, Ram Niwas, Gopal Chawla, Mehul Agarwal, Mahendera Kumar Garg
DOI: 10.5603/ARM.a2020.0156
·
Pubmed: 33169811
·
Adv Respir Med 2020;88(5):400-405.

open access

Vol 88, No 5 (2020)
ORIGINAL PAPERS
Published online: 2020-10-24
Submitted: 2020-04-25
Accepted: 2020-06-24

Abstract

Introduction: Machine learning algorithms have been used to develop prediction models in various infectious and non-infectious settings including interpretation of images in predicting the outcome of diseases. We demonstrate the application of one such simple automated machine learning algorithm to a dataset obtained about COVID-19 spread in South Korea to better understand the disease dynamics.
Material and methods: Data from 20th January 2020 (when the first case of COVID-19 was detected in South Korea) to 4th March 2020 was accessed from Korea’s centre for disease control (KCDC). A future time-series of specified length (taken as 7 days in our study) starting from 5th March 2020 to 11th March 2020 was generated and fed to the model to generate predictions with upper and lower trend bounds of 95% confidence intervals. The model was assessed for its ability to reliably forecast using mean absolute percentage error (MAPE) as the metric.
Results: As on 4th March 2020, 145,541 patients were tested for COVID-19 (in 45 days) in South Korea of which 5166 patients tested positive. The predicted values approximated well with the actual numbers. The difference between predicted and observed values ranged from 4.08% to 12.77% . On average, our predictions differed from actual values by 7.42% (MAPE) over the same period.
Conclusion: Open source and automated machine learning tools like Prophet can be applied and are effective in the context of COVID-19 for forecasting spread in naïve communities. It may help countries to efficiently allocate healthcare resources to contain this pandemic.

Abstract

Introduction: Machine learning algorithms have been used to develop prediction models in various infectious and non-infectious settings including interpretation of images in predicting the outcome of diseases. We demonstrate the application of one such simple automated machine learning algorithm to a dataset obtained about COVID-19 spread in South Korea to better understand the disease dynamics.
Material and methods: Data from 20th January 2020 (when the first case of COVID-19 was detected in South Korea) to 4th March 2020 was accessed from Korea’s centre for disease control (KCDC). A future time-series of specified length (taken as 7 days in our study) starting from 5th March 2020 to 11th March 2020 was generated and fed to the model to generate predictions with upper and lower trend bounds of 95% confidence intervals. The model was assessed for its ability to reliably forecast using mean absolute percentage error (MAPE) as the metric.
Results: As on 4th March 2020, 145,541 patients were tested for COVID-19 (in 45 days) in South Korea of which 5166 patients tested positive. The predicted values approximated well with the actual numbers. The difference between predicted and observed values ranged from 4.08% to 12.77% . On average, our predictions differed from actual values by 7.42% (MAPE) over the same period.
Conclusion: Open source and automated machine learning tools like Prophet can be applied and are effective in the context of COVID-19 for forecasting spread in naïve communities. It may help countries to efficiently allocate healthcare resources to contain this pandemic.

Get Citation

Keywords

machine learning; COVID-19; coronavirus; pandemic; South Korea

About this article
Title

Using a simple open-source automated machine learning algorithm to forecast COVID-19 spread: A modelling study

Journal

Advances in Respiratory Medicine

Issue

Vol 88, No 5 (2020)

Article type

Research paper

Pages

400-405

Published online

2020-10-24

DOI

10.5603/ARM.a2020.0156

Pubmed

33169811

Bibliographic record

Adv Respir Med 2020;88(5):400-405.

Keywords

machine learning
COVID-19
coronavirus
pandemic
South Korea

Authors

Shahir Asfahan
Maya Gopalakrishnan
Naveen Dutt
Ram Niwas
Gopal Chawla
Mehul Agarwal
Mahendera Kumar Garg

References (15)
  1. Zhou F, Yu T, Du R, et al. Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: a retrospective cohort study. The Lancet. 2020; 395(10229): 1054–1062.
  2. World Healt Organization. Coronavirus disease (COVID-19) pandemic. Available online: www.who.int/emergencies/diseases/novel-coronavirus-2019. [Last accessed at: 05.10.2020].
  3. Lipsitch M, Swerdlow DL, Finelli L. Defining the epidemiology of COVID-19 — studies needed. N Engl J Med. 2020; 382(13): 1194–1196.
  4. Fauci AS, Lane HC, Redfield RR. COVID-19 — navigating the uncharted. N Engl J Med. 2020; 382(13): 1268–1269.
  5. Skrede OJ, Raedt SDe, Kleppe A, et al. Deep learning for prediction of colorectal cancer outcome: a discovery and validation study. The Lancet. 2020; 395(10221): 350–360.
  6. KCDC. Available online: http://www.cdc.go.kr. [Last accessed at: 09.05.2020].
  7. Taylor SJ, Letham B. Prophet: forecasting at scale. Facebook Research. Available online: https://research.fb.com/blog/2017/02/prophet-forecasting-at-scale/. [Last accessed at: 05.10.2020].
  8. Fang WX, Lan PC, Lin WR, et al. Combine Facebook prophet and LSTM with BPNN forecasting financial markets: the Morgan Taiwan Index. 2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS). 2019.
  9. Gilbert M, Pullano G, Pinotti F, et al. Preparedness and vulnerability of African countries against importations of COVID-19: a modelling study. The Lancet. 2020; 395(10227): 871–877.
  10. Wu J, Leung K, Leung G. Nowcasting and forecasting the potential domestic and international spread of the 2019-nCoV outbreak originating in Wuhan, China: a modelling study. The Lancet. 2020; 395(10225): 689–697.
  11. Hellewell J, Abbott S, Gimma A, et al. Feasibility of controlling COVID-19 outbreaks by isolation of cases and contacts. The Lancet Global Health. 2020; 8(4): e488–e496.
  12. Meade N. Industrial and business forecasting methods. J Forecast. 1983; 2(2): 194–196.
  13. van der Ploeg T, Austin PC, Steyerberg EW. Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints. BMC Med Res Methodol. 2014; 14: 137.
  14. Kuo L. Wuhan nurses' plea for international medics to help fight coronavirus. The Guardian. 26.02.2020. Available online: www.theguardian.com/world/2020/feb/26/wuhan-nurses-plea-international-medics-help-fight-coronavirus. [Last accessed: 05.10.2020].
  15. Orecchio-Egresitz H. Faced with tough choices, Italy is prioritizing young COVID-19 patients over the elderly. That likely “won’t fly” in the US. Buisness Insider. 11.03.2020. Available online: www.businessinsider.in/science/news/faced-with-tough-choices-italy-is-prioritizing-young-covid-19-patients-over-the-elderly-that-likely-wont-fly-in-the-us-/articleshow/74567872.cms. [Last accessed at: 05.10.2020].

Important: This website uses cookies. More >>

The cookies allow us to identify your computer and find out details about your last visit. They remembering whether you've visited the site before, so that you remain logged in - or to help us work out how many new website visitors we get each month. Most internet browsers accept cookies automatically, but you can change the settings of your browser to erase cookies or prevent automatic acceptance if you prefer.

Czasopismo Pneumonologia i Alergologia Polska dostęne jest również w Ikamed - księgarnia medyczna

Wydawcą serwisu jest "Via Medica sp. z o.o." sp.k., ul. Świętokrzyska 73, 80–180 Gdańsk

tel.:+48 58 320 94 94, faks:+48 58 320 94 60, e-mail: viamedica@viamedica.pl