Use of econometrics and machine learning models to predict the number of new cases per day of COVID-19

  • Roberto Silva USP
  • Bruna Barreira USP
  • Fernando Xavier USP
  • Antonio Saraiva USP
  • Carlos Cugnasca USP

Resumo


The COVID-19 pandemics will impact the demand for healthcare severely. It is essential to continually monitor and predict the expected number of new cases for each country. We explored the use of econometrics, machine learning, and ensemble models to predict the number of new cases per day for Brazil, China, Italy, and South Korea. These models can be used to make predictions in the short term, complementing the epidemiological models. Our main findings were: (i) there is no single best model for all countries; (ii) ensembles can, in some instances, improve the results of individual models; and (iii) the ML models had worse results due to the lack of data.

Referências

Dominguez, A., Muñoz, P., Martínez, A., Orcau, A. (1996) "Monitoring mortality as an indicator of influenza in Catalonia, Spain". Journal of Epidemiology & Community Health, v.50, n.3, p.293-298.

Dong, E., Du, H., Gardner, L. (2020) "An interactive web-based dashboard to track COVID-19 in real time". The Lancet Infectious Diseases, Correspondence, p.1-2.

Ferguson, N. et al. (2020) "Report 9: Impact of non-pharmaceutical interventions (NPIs) to reduce COVID19 mortality and healthcare demand", 2020, p.1-20.

Garg, S. (2020) "Hospitalization rates and characteristics of patients hospitalized with laboratory-confirmed coronavirus disease 2019—COVID-NET, 14 states, March 1– 30". Morbidity and Mortality Weekly Report, v.69. Available on: https://www.cdc.gov/mmwr/volumes/69/wr/mm6915e3.htm. Accessed on: 04/24/2020.

Han, F. et al. (2011) "Narcolepsy onset is seasonal and increased following the 2009 H1N1 pandemic in China". Annals of neurology, v.70, n.3, p.410-417.

Nilashi, M., bin Ibrahim, O., Ahmadi, H., Shahmoradi, L. (2017) "An analytical method for diseases prediction using machine learning techniques". Computers & Chemical Engineering, v.106, p.212-223.

Promprou, S., Jaroensutasinee, M., Jaroensutasinee, K. (2006) "Forecasting Dengue haemorrhagic fever cases in Southern Thailand using ARIMA models". Dengue Bulletin, v.30, p.99-106.

Santillana, M., Nguyen, A.T., Dredze, M., Paul, M.J., Nsoesie, E.O., Brownstein, J.S. (2015) "Combining search, social media, and traditional data sources to improve influenza surveillance". PLoS computational biology, v.11, n.10, p.1-15.

Shafaf, N., Malek, H. (2019) “Applications of Machine Learning Approaches in Emergency Medicine; a Review Article”. Archives of academic emergency medicine, v.7, n.1, p.1-9.

Soebiyanto, R.P., Adimi, F., Kiang, R.K. (2010) "Modeling and predicting seasonal influenza transmission in warm regions using climatological parameters". PloS one, v.5, n.3 p.1-10.

Weiss, H.H. (2013) “The SIR model and the foundations of public health”. Materials matematics, n.3, p.1-17.

Zhang, B., Ren, J., Cheng, Y., Wang, B., Wei, Z. (2019) "Health data driven on continuous blood pressure prediction based on gradient boosting decision tree algorithm". IEEE Access, v.7, p.32423-32433.
Publicado
15/09/2020
SILVA, Roberto; BARREIRA, Bruna; XAVIER, Fernando; SARAIVA, Antonio; CUGNASCA, Carlos. Use of econometrics and machine learning models to predict the number of new cases per day of COVID-19. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 20. , 2020, Evento Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2020 . p. 332-343. ISSN 2763-8952. DOI: https://doi.org/10.5753/sbcas.2020.11525.