Physiological and socioeconomic characteristics predict COVID-19 mortality and resource utilization in Brazil

Abstract

Background Given the severity and scope of the current COVID-19 pandemic, it is critical to determine predictive features of COVID-19 mortality and medical resource usage to effectively inform health, risk-based physical distancing, and work accommodation policies. Non-clinical sociodemographic features are important explanatory variables of COVID-19 outcomes, revealing existing disparities in large health care systems.

Comparing Decision Tree-Based Ensemble Machine Learning Models for COVID-19 Death Probability Profiling

“…The fact that males with no underlying comorbidity or disease also tend to have higher death risk than females as age progresses also reinforces the findings of an asymmetric impact of COVID-19 in regards to sex and is consistent with previous studies' results [1][2][3][4][5]. A possible explanation provided in [5], regarding male infectiousness, relates to smoking and higher circulating angiotensin converting enzyme 2 (ACE2) levels in men, SARS-CoV-2 utilizes ACE2 receptors found at the surface of the host cells to get inside the cell, this is also an important factor in specific underlying comorbidities or diseases.…”

“…Different studies have identified age group, sex and underlying comorbidity or disease as critical factors for disease severity and mortality risk [1][2][3][4][5]. In the current work, we use these three factors as feature variables in machine learning models for extracting a profile for COVID-19 death probability, conditional on these three risk factors, using the US Centers for Disease Control and Prevention (CDC)'s COVID-19 case surveillance data sample 1 which contains a large sample of COVID-19 confirmed cases with records for these three factors.…”

“…In regards to the age group variable, the CDC defined an ordinal scale of nine age groups, we use this ordinal feature variable along with the qualitative variables sex and underlying comorbidity or disease 2 . Together, these feature variables provide a set of 36 alternative configurations for the three critical factors, age group, sex and having an underlying comorbidity or disease.…”

Hospital load and increased COVID-19 related mortality in Israel

“…The Israeli healthcare system is universal and mandates all citizens to join one of the official non-profit health insurance organizations. Regional 11 or financial 12 disparities affecting the availability of health-care resources in other countries as well as racial variation 13 may affect COVID-19-related mortality. Future studies should be conducted in order to determine if this effect is also observed in other countries with different healthcare systems, and the specific threshold of patients representing healthcare capacity in each healthcare system.…”

Socioeconomic inequalities associated with mortality for COVID-19 in Colombia: A cohort nation-wide study

“…[21] In Brazil, income and education inequalities were positively associated with COVID-19 incidence and mortality rates. [22,23] Our results showed that living in areas of very low or low SES is associated with higher COVID-19 mortality risk with a consistent dose-response effect pattern. These results are consistent with a previous report of inequalities in mortality by SES levels among COVID-19 confirmed cases in Bogotá.…”