Current forecast of COVID-19: a Bayesian and Machine Learning approaches

Abstract

We address the estimation of the effective reproductive number Rt based on serological data using Bayesian inference. We also explore the Bayesian learning paradigm to estimate Rt. We calculate Rt for the top five most affected principal regions of Mexico. We present a forecast of the spread of coronavirus in Mexico based on a contact tracing model using Bayesian inference inspired in a data-driven approach. We investigate the health profile of individuals diagnosed with coronavirus in order to predict their type of patient care (inpatient or outpatient) and survival. Specifically, we analyze the comorbidity associated with coronavirus using Machine Learning. We implemented two classifiers, the first one, to predict the type of care procedure a diagnosed person with coronavirus presenting chronic diseases will obtain: outpatient or hospitalized. Second one, a classifier for the survival of the patient: survived or deceased. We present two techniques to deal with these kinds of unbalanced dataset related with outpatient/hospitalized and survived/deceased cases, occurring in general for these type coronavirus datasets in the world, in order obtain to a better performance for the classification.

On mobility trends analysis of COVID–19 dissemination in Mexico City

“…For parameter estimation, we use the daily reported dataset [ 23 ]. We use Bayesian inference to solve the inverse problem associated to the system of Ordinary Differential Equations (ODEs) given on ( 1 ), similarly to [ 33 ]. Some references using this method of parameter estimation can be found in [ 42 – 53 ].…”

“…Consequently, we first describe the mathematical model that we have used; then, we compute the number of trips that are produced and attracted in each borough of Mexico City using data about these trips in 2017 [ 24 ], which then we combine with the rates of reduction or increase in mobility during the pandemic reported by Google [ 25 ] and the government of Mexico City [ 26 ]. Later, by using Bayesian inference, we solve the associated inverse problem to predict the dynamics of the spread of cases, similar to the following references [ 27 – 33 ]. Our conclusions are presented in the last section.…”