Physiological and socioeconomic characteristics predict COVID-19 mortality and resource utilization in Brazil
| العنوان: | Physiological and socioeconomic characteristics predict COVID-19 mortality and resource utilization in Brazil |
|---|---|
| المؤلفون: | Julia L. Fleck, Ioannis Ch. Paschalidis, Amanda de Araújo Batista da Silva, Christos G. Cassandras, Salomón Wollenstein-Betech |
| المصدر: | PLoS ONE, Vol 15, Iss 10, p e0240346 (2020) PLoS ONE |
| بيانات النشر: | Public Library of Science (PLoS), 2020. |
| سنة النشر: | 2020 |
| مصطلحات موضوعية: | Viral Diseases, Critical Care and Emergency Medicine, Pulmonology, Epidemiology, Comorbidity, Disease, 030204 cardiovascular system & hematology, Logistic regression, Geographical locations, Medical Conditions, 0302 clinical medicine, Health care, Medicine and Health Sciences, Medicine, Public and Occupational Health, 030212 general & internal medicine, Acute Respiratory Distress Syndrome, Multidisciplinary, Socioeconomic Aspects of Health, Laboratory Equipment, Infectious Diseases, Engineering and Technology, Coronavirus Infections, Brazil, Research Article, Patients, Science, Pneumonia, Viral, Ventilators, Equipment, Respiratory Disorders, 03 medical and health sciences, Respiratory Failure, Humans, Healthcare Disparities, Pandemics, Socioeconomic status, Demography, Models, Statistical, Health Care Policy, business.industry, COVID-19, Covid 19, South America, medicine.disease, Obesity, Health Care, Socioeconomic Factors, Medical Risk Factors, Public hospital, Predictive power, People and places, business, Facilities and Services Utilization |
| الوصف: | BackgroundGiven 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.Methods and findingsWe use nation-wide multicenter data of COVID-19 patients in Brazil to predict mortality and ventilator usage. The dataset contains hospitalized patients who tested positive for COVID-19 and had either recovered or were deceased between March 1 and June 30, 2020. A total of 113,214 patients with 50,387 deceased, were included. Both interpretable (sparse versions of Logistic Regression and Support Vector Machines) and state-of-the-art non-interpretable (Gradient Boosted Decision Trees and Random Forest) classification methods are employed. Death from COVID-19 was strongly associated with demographics, socioeconomic factors, and comorbidities. Variables highly predictive of mortality included geographic location of the hospital (OR = 2.2 for Northeast region, OR = 2.1 for North region); renal (OR = 2.0) and liver (OR = 1.7) chronic disease; immunosuppression (OR = 1.7); obesity (OR = 1.7); neurological (OR = 1.6), cardiovascular (OR = 1.5), and hematologic (OR = 1.2) disease; diabetes (OR = 1.4); chronic pneumopathy (OR = 1.4); immunosuppression (OR = 1.3); respiratory symptoms, ranging from respiratory discomfort (OR = 1.4) and dyspnea (OR = 1.3) to oxygen saturation less than 95% (OR = 1.7); hospitalization in a public hospital (OR = 1.2); and self-reported patient illiteracy (OR = 1.1). Validation accuracies (AUC) for predicting mortality and ventilation need reach 79% and 70%, respectively, when using only pre-admission variables. Models that use post-admission disease progression information reach accuracies (AUC) of 86% and 87% for predicting mortality and ventilation use, respectively.ConclusionsThe results highlight the predictive power of socioeconomic information in assessing COVID-19 mortality and medical resource allocation, and shed light on existing disparities in the Brazilian health care system during the COVID-19 pandemic. |
| اللغة: | English |
| تدمد: | 1932-6203 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::13242d507a38eb60af3ed6d49a9c2a1a https://doaj.org/article/d07e0098a46240f2b1d63f6c837d711e |
| حقوق: | OPEN |
| رقم الأكسشن: | edsair.doi.dedup.....13242d507a38eb60af3ed6d49a9c2a1a |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 19326203 |
|---|