Forecasting Covid-19 Dynamics in Brazil: A Data Driven Approach

Abstract

The contribution of this paper is twofold. First, a new data driven approach for predicting the Covid-19 pandemic dynamics is introduced. The second contribution consists in reporting and discussing the results that were obtained with this approach for the Brazilian states, with predictions starting as of 4 May 2020. As a preliminary study, we first used an Long Short Term Memory for Data Training-SAE (LSTM-SAE) network model. Although this first approach led to somewhat disappointing results, it served as a good baseline for testing other ANN types. Subsequently, in order to identify relevant countries and regions to be used for training ANN models, we conduct a clustering of the world’s regions where the pandemic is at an advanced stage. This clustering is based on manually engineered features representing a country’s response to the early spread of the pandemic, and the different clusters obtained are used to select the relevant countries for training the models. The final models retained are Modified Auto-Encoder networks, that are trained on these clusters and learn to predict future data for Brazilian states. These predictions are used to estimate important statistics about the disease, such as peaks and number of confirmed cases. Finally, curve fitting is carried out to find the distribution that best fits the outputs of the MAE, and to refine the estimates of the peaks of the pandemic. Predicted numbers reach a total of more than one million infected Brazilians, distributed among the different states, with São Paulo leading with about 150 thousand confirmed cases predicted. The results indicate that the pandemic is still growing in Brazil, with most states peaks of infection estimated in the second half of May 2020. The estimated end of the pandemics (97% of cases reaching an outcome) spread between June and the end of August 2020, depending on the states.

BCG Vaccination and Mortality of COVID-19 across 173 Countries: An Ecological Study

“…On the other hand risk of in-hospital mortality increased only in aged patients and was not associated with the Black race, sex, comorbidities, obesity and other factors after multivariate adjustment [2]; this phenomenon was also confirmed in other races, i.e., Asians and Hispanics, compared with the White race [3,4]. Moreover, since COVID-19 is an infectious disease that spreads mainly through the droplet route by close contact in dense human societies, metropolitan areas, such as New York City in the USA [5] and Lombardy in Italy [6], Paris in France [7], Sao Paulo in Brazil [8], and so on, have tended to be regional epicenters. However, associations between population dynamics, e.g., population size, density, migrants and urbanization and the morbidity/mortality of COVID- 19 have not yet been well examined.…”

“…Marked differences in COVID-19 mortalities have been observed in different countries. For example, the mortality per million population is till now several tens of times or even higher in Western countries, e.g., Belgium (845), the United Kingdom (UK, 664), the United States of America (USA, 426) and Germany (109), than in Asian countries, e.g., India (19), Japan (8) and China (3), as of 17 July 2020. This is quite the opposite of what was reported during the 1918-20 influenza pandemic, the so called Spanish flu, in which the population mortality was over 30-fold higher, with excess death rates observed in low-income countries, such as India, than in high-income countries, such as those in the West [1].…”

Applications of artificial intelligence in battling against covid-19: A literature review

“…The countries are clustered based on disease prevalence estimates, air pollution, socio-economic status and health system coverage. In [448] , a clustering algorithm is applied to the world regions for which epidemic data are available and the pandemic is at an advanced stage. Then a set of features representing the countries response to the early spread of the pandemic are used to train an Auto-Encoder Network to predict the future of the pandemic in Brazil.…”

Waves of COVID-19 pandemic. Detection and SIR simulations

“…The dynamics of Covid-19 pandemic in different countries was simulated with the use of different mathematical models [23][24][25][26][27][28][29][30][31][32][33][34][35][36][37]. Nevertheless, in literature there are no long-time predictions for the final sizes and durations of the pandemic in Ukraine and in the world in order to compare with the presented results.…”