Abstract
There is an ongoing need for scientific analysis to help governments and public health authorities make decisions regarding the COVID-19 pandemic. This article presents a methodology based on data mining that can offer support for coping with epidemic diseases. The methodological approach was applied in São Paulo, Rio de Janeiro and Manaus, the cities in Brazil with the most COVID-19 deaths until the first half of 2021. We aimed to predict the evolution of COVID-19 in metropolises and identify air quality and meteorological variables correlated with confirmed cases and deaths. The statistical analyses indicated the most important explanatory environmental variables, while the cluster analyses showed the potential best input variables for the forecasting models. The forecast models were built by two different algorithms and their results have been compared. The relationship between epidemiological and environmental variables was particular to each of the three cities studied. Low solar radiation periods predicted in Manaus can guide managers to likely increase deaths due to COVID-19. In São Paulo, an increase in the mortality rate can be indicated by drought periods. The developed models can predict new cases and deaths by COVID-19 in studied cities. Furthermore, the methodological approach can be applied in other cities and for other epidemic diseases.
Highlights
There is an ongoing need for scientific analysis to help governments and public health authorities make decisions regarding the COVID-19 pandemic
The statistical analysis of the linear correlation coefficient showed that for the three cities studied it is challenging to identify a correlation between the epidemiological variables of COVID-19 and environmental variables
With the increase in the data series, the variability of epidemiological and environmental variables increased, revealing that the apparent correlation between some variables, in the first hundred days of the pandemic, did exist but was not as strong as the trend shown in the first wave
Summary
There is an ongoing need for scientific analysis to help governments and public health authorities make decisions regarding the COVID-19 pandemic. This article proposes a methodological approach that has been used to support decision-making in several areas[29,30,31,32], including recently in urban health[33,34] Such an approach used infrequently, it is a potential tool in the context of the current health crisis caused by COVID-19 and can contribute to decision-making in facing the virus and other epidemic diseases. This approach makes it possible to identify variables (environmental, climatic, social, etc.) correlated to the disease and allows the prediction of its evolution in a coordinated and agile way with a high degree of accuracy.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
