Leonardo Seixas de Oliveira
- COVID-19 and healthcare impacts
- COVID-19 Clinical Research Studies
- Machine Learning in Healthcare
- COVID-19 diagnosis using AI
- Long-Term Effects of COVID-19
- Venous Thromboembolism Diagnosis and Management
- Sepsis Diagnosis and Treatment
- Global Health Care Issues
- SARS-CoV-2 and COVID-19 Research
- Explainable Artificial Intelligence (XAI)
- Artificial Intelligence in Healthcare
- COVID-19 epidemiological studies
Santa Rosa Memorial Hospital
2021-2022
Hospital Santa Paula
2021
Hospital Ernesto Dornelles
2021
To describe the clinical characteristics, laboratory results, imaging findings, and in-hospital outcomes of COVID-19 patients admitted to Brazilian hospitals.A cohort study laboratory-confirmed who were hospitalized from March 2020 September in 25 hospitals. Data collected medical records using Research Electronic Capture (REDCap) tools. A multivariate Poisson regression model was used assess risk factors for mortality.For a total 2,054 (52.6% male; median age 58 years), mortality 22.0%;...
Abstract The majority of early prediction scores and methods to predict COVID-19 mortality are bound by methodological flaws technological limitations (e.g., the use a single model). Our aim is provide thorough comparative study that tackles those issues, considering multiple techniques build models, including modern machine learning (neural) algorithms traditional statistical techniques, as well meta-learning (ensemble) approaches. This used dataset from multicenter cohort 10,897 adult...
The COVID-19 pandemic caused unprecedented pressure over health care systems worldwide. Hospital-level data that may influence the prognosis in patients still needs to be better investigated. Therefore, this study analyzed regional socioeconomic, hospital, and intensive units (ICU) characteristics associated with in-hospital mortality admitted Brazilian institutions. This multicenter retrospective cohort is part of Registry. We enrolled ≥ 18 years old laboratory-confirmed participating...
Despite no evidence showing benefits of hydroxychloroquine and chloroquine with or without azithromycin for COVID-19 treatment, these medications have been largely prescribed in Brazil.To assess outcomes, including in-hospital mortality, electrocardiographic abnormalities, hospital length-of-stay, admission to the intensive care unit, need dialysis mechanical ventilation, hospitalized patients who received hydroxychloroquine, compare outcomes between those their matched controls.A...
Abstract Objective To provide a thorough comparative study among state-of-the-art machine learning methods and statistical for determining in-hospital mortality in COVID-19 patients using data upon hospital admission; to the reliability of predictions most effective by correlating probability outcome accuracy methods; investigate how explainable are produced methods. Materials Methods De-identified were obtained from positive 36 participating hospitals, March 1 September 30, 2020....
Background:The COVID-19 pandemic caused unprecedented pressure over health care systems, but hospital-level data that may influence the prognosis are not well-studied. Therefore, this study analyzed regional socioeconomic, hospital, and intensive units (ICU) characteristics associated with mortality in patients admitted to Brazilian institutions.Methods:This is a multicenter retrospective cohort. Patients from March September 2020, were enrolled. Data collected through hospital records,...
Abstract The majority prognostic scores proposed for early assessment of coronavirus disease 19 (COVID-19) patients are bounded by methodological flaws. Our group recently developed a new risk score - ABC 2 SPH using traditional statistical methods (least absolute shrinkage and selection operator logistic regression LASSO). In this article, we provide thorough comparative study between modern machine learning (ML) state-of-the-art methods, represented SPH, in the task predicting in-hospital...
Background: Previous studies that assessed risk factors for venous thromboembolism (VTE) in COVID-19 patients have shown inconsistent results. Our aim was to investigate VTE predictors by both logistic regression (LR) and machine learning (ML) approaches, due their potential complementarity.Methods: This substudy of a large Brazilian Registry included adult from 16 hospitals. Symptomatic confirmed objective imaging. LR analysis, tree-based boosting bagging were used the association variables...