COVID-19, Bacille Calmette-Guerin (BCG) and tuberculosis: Cases and recovery previsions with deep learning sequence prediction

Abstract

In this study, we use a Deep Learning sequence prediction models for the continuous monitoring of the infection and recovering processes while considering the potential impacts of Bacille Calmette-Guerin (BCG) vaccination and tuberculosis (TB) infection rates in populations. This model was built based on the epidemic data evolution in several countries between the date of then first case and March 13, 2020. The data was based on 14 variables for cases prediction and 15 variables for recoveries prediction. Prevision results were very promising and the suspicions on the BCG vaccination and TB infections rates' implications turned out to be quite warranted. The model can evolve by continuously updating and enriching data, adding experiences of all affected countries.