AUTHOR=Méndez-Astudillo Jorge 

TITLE=The impact of comorbidities and economic inequality on COVID-19 mortality in Mexico: a machine learning approach

JOURNAL=Frontiers in Big Data

VOLUME=Volume 7 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024.1298029

DOI=10.3389/fdata.2024.1298029

ISSN=2624-909X

ABSTRACT=Studies from different parts of the world have shown that some comorbidities are associated with fatal cases of COVID-19. However, the prevalence rates of comorbidities are different around the world, therefore, their contribution to COVID-19 mortality is different.Socioeconomic factors may influence the prevalence of comorbidities; therefore, they may also influence COVID-19 mortality. This paper presents the results of a feature analysis, using supervised machine learning classification algorithms (Random Forest and XGBoost), of the comorbidities and the level of economic inequalities that defined fatal cases of COVID-19 in Mexico. The dataset used was collected by the National Epidemiology Center from February 2020 to November 2022, and includes more than 20 million observations and 40 variables describing the characteristics of the individuals who underwent COVID-19 testing or treatment. In addition, socioeconomic inequalities were measured using the normalized marginalization index calculated by the National Population Council and the deprivation index calculated by NASA. The results show that diabetes and hypertension were the main comorbidities defining the mortality of COVID-19, furthermore, socioeconomic inequalities were also important characteristics defining the mortality. Thus, it is imperative to implement programs aimed at reducing inequalities as well as preventable comorbidities to make the population more resilient to future pandemics. The results apply to regions or countries with similar levels of inequality or comorbidity prevalence.