Factors associated with death in confirmed cases of COVID-19 in the state of Rio de Janeiro

BMC Infectious Diseases

Lucas Dalsenter Romano da Silva¹  Marlos Melo Martins²  Marcella Cini Oliveira³  Renata Coelho Rodrigues³  Bruna Andrade de Oliveira³  Roberto de Andrade Medronho⁴  Carlos Eduardo Raymundo⁴  Tatiana de Araujo Eleuterio⁵  Allan Bruno de Andrade Corrêa⁶ 

[1] Departamento de Medicina Preventiva, Instituto de Estudos em Saúde Pública / Faculdade de Medicina, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brasil;Department of Child Neurology, Martagão Gesteira Institute of Childcare and Pediatrics, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil;Faculdade de Medicina, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brasil;Instituto de Estudos em Saúde Pública / Faculdade de Medicina, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brasil;Instituto de Estudos em Saúde Pública / Faculdade de Medicina, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brasil;Faculdade de Enfermagem, Universidade do Estado do Rio de Janeiro, Rio de Janeiro, Brasil;Instituto de Física, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brasil;

关键词: COVID-19;    SARS-CoV-2;    XGBoost;    Machine learning;    Pandemic;    Coronavirus infection;    Coronavirus death;   

DOI  :  10.1186/s12879-021-06384-1

来源: Springer

【 摘 要 】

BackgroundCOVID-19 can occur asymptomatically, as influenza-like illness, or as more severe forms, which characterize severe acute respiratory syndrome (SARS). Its mortality rate is higher in individuals over 80 years of age and in people with comorbidities, so these constitute the risk group for severe forms of the disease. We analyzed the factors associated with death in confirmed cases of COVID-19 in the state of Rio de Janeiro. This cross-sectional study evaluated the association between individual demographic, clinical, and epidemiological variables and the outcome (death) using data from the Unified Health System information systems.MethodsWe used the extreme boosting gradient (XGBoost) model to analyze the data, which uses decision trees weighted by the estimation difficulty. To evaluate the relevance of each independent variable, we used the SHapley Additive exPlanations (SHAP) metric. From the probabilities generated by the XGBoost model, we transformed the data to the logarithm of odds to estimate the odds ratio for each independent variable.ResultsThis study showed that older individuals of black race/skin color with heart disease or diabetes who had dyspnea or fever were more likely to die.ConclusionsThe early identification of patients who may progress to a more severe form of the disease can help improve the clinical management of patients with COVID-19 and is thus essential to reduce the lethality of the disease.

【 授权许可】

CC BY