Developing a Probit Regression Model for Estimating the Chance of Mortality for Coronavirus Disease-2019 Patients

*Corresponding author: Abbas Mahmoudabadi*

Full-Text PDF:

retrospective study


Although the number of deaths of coronavirus disease-2019 (COVID-19) is decreasing over the world due to vaccination process, but appearing its new variants remain it as the remarkable challenge for health authorities.
The aim of this study is to develop a probit regression model to estimate the chance of mortality for the patients infected to COVID-19.
The contributing factors of age, symptoms and underlying diseases have been considered as independent variables as well as the clearance type of death as dependent variable have been studied for estimating the mortality rate. Patients have been divided into two categories; 1) recovered or transferred and 2) death, followed by developing a probit regression model by the well-known technique of Max likelihood method.
Data Collection
Data have been collected for 1015 patients tested positively to COVID-19 and subsequently received clinical treatment or intensive care.
The results revealed the model is capable of estimating the chance of mortality based on age, symptoms and underlying diseases. As implication, the health authorities ultumately can estimate the patient mortality rate prior to admission procedures in hospitals.
COVID-19; Mortality rate; Healthcare management; Probit regression; Maximum likelihood.