AUTHOR=da Silva Cecilia Cordeiro , de Lima Clarisse Lins , da Silva Ana Clara Gomes , Silva Eduardo Luiz , Marques Gabriel Souza , de Araújo Lucas Job Brito , Albuquerque Júnior Luiz Antônio , de Souza Samuel Barbosa Jatobá , de Santana Maíra Araújo , Gomes Juliana Carneiro , Barbosa Valter Augusto de Freitas , Musah Anwar , Kostkova Patty , dos Santos Wellington Pinheiro , da Silva Filho Abel Guilhermino 

TITLE=Covid-19 Dynamic Monitoring and Real-Time Spatio-Temporal Forecasting

JOURNAL=Frontiers in Public Health

VOLUME=Volume 9 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2021.641253

DOI=10.3389/fpubh.2021.641253

ISSN=2296-2565

ABSTRACT=Background: Periodically, humanity is often faced with new and emerging viruses that can be a significant global threat. It has already been over a century post- the Spanish Flu pandemic, and we are witnessing a new type of coronavirus, the SARS-CoV-2, which is responsible for Covid-19. It emerged from the city of Wuhan (China) in December 2019, and within a few months, the virus propagated itself globally now resulting more than 50 million cases with over 1 million deaths. The high rate of infections, combined with the dynamics of population movements, demands tools that support health managers to develop policies to control and combat the virus that integrate both spatial and temporal analysis. 

Methods: In this work we propose a tool for real-time spatio-temporal analysis using machine learning and public databases. The COVID-SGIS system daily collects information from public databases of the public health system and combines geographic information to generate temporal and spatial predictions. As a case study, we made spatio-temporal predictions of the distribution of cases and deaths in Brazil and in each federative unit. Four regression methods were investigated: linear regression, support vector machines (polynomial kernels and RBF), multilayer perceptrons, and random forests. We use the percentage RMSE and the correlation coefficient as quality metrics.

Results: For qualitative evaluation, we made spatio-temporal predictions for the period from 25 to 27 May 2020. Considering qualitatively and quantitatively the case of the State of Pernambuco and Brazil as a whole, linear regression presented the best prediction results (thematic maps with good data distribution, correlation coefficient greater than 0.99 and RMSE (%) less than 4% for Pernambuco and around 5% for Brazil) with low training time: [0.00ms; 0.04ms], CI 95%. 

Conclusion: Spatio-temporal analysis provided a broader assessment of those in the regions where the accumulated confirmed cases of Covid-19 were concentrated. It was possible to differentiate in the thematic maps the regions with the highest concentration of cases from the regions with low concentration and regions in the transition range. This approach is fundamental to support health managers and epidemiologists to elaborate policies and plans to control the Covid-19 pandemics.