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

Abstract

AbstractWe address the estimation of the effective reproductive numberRtbased on serological data using Bayesian inference. We also explore the Bayesian learning paradigm to estimateRt. We calculateRtfor 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.