OxCOVID19 Database: a multimodal data repository for better understanding the global impact of COVID-19

Oxford COVID-19 Database (OxCOVID19 Database) is a comprehensive source of information related to the COVID-19 pandemic. This relational database contains time-series data on epidemiology, government responses, mobility, weather and more across time and space for all countries at the national level, and for more than 50 countries at the regional level. It is curated from a variety of (wherever available) official sources. Its purpose is to facilitate the analysis of the spread of SARS-CoV-2 virus and to assess the effects of non-pharmaceutical interventions to reduce the impact of the pandemic. Our database is a freely available, daily updated tool that provides unified and granular information across geographical regions.

Early risk assessment for COVID-19 patients from emergency department data using machine learning

BackgroundSince its emergence in late 2019, the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused a pandemic, with more than 4.8 million reported cases and 310 000 deaths worldwide. While epidemiological and clinical characteristics of COVID-19 have been reported, risk factors underlying the transition from mild to severe disease among patients remain poorly understood. MethodsIn this retrospective study, we analysed data of 820 confirmed COVID-19 positive patients admitted to a two-site NHS Trust hospital in London, England, between January 1st and April 23rd, 2020, with a majority of cases occurring in March and April. We extracted anonymised demographic data, physiological clinical variables and laboratory results from electronic healthcare records (EHR) and applied multivariate logistic regression, random forest and extreme gradient boosted trees. To evaluate the potential for early risk assessment, we used data available during patients initial presentation at the emergency department (ED) to predict deterioration to one of three clinical endpoints in the remainder of the hospital stay: A) admission to intensive care, B) need for mechanical ventilation and C) mortality. Based on the trained models, we extracted the most informative clinical features in determining these patient trajectories. ResultsConsidering our inclusion criteria, we have identified 126 of 820 (15%) patients that required intensive care, 62 of 808 (8%) patients needing mechanical ventilation, and 170 of 630 (27%) cases of in-hospital mortality. Our models learned successfully from early clinical data and predicted clinical endpoints with high accuracy, the best model achieving AUC-ROC scores of 0.75 to 0.83 (F1 scores of 0.41 to 0.56). Younger patient age was associated with an increased risk of receiving intensive care and ventilation, but lower risk of mortality. Clinical indicators of a patients oxygen supply and selected laboratory results were most predictive of COVID-19 patient trajectories. ConclusionAmong COVID-19 patients machine learning can aid in the early identification of those with a poor prognosis, using EHR data collected during a patients first presentation at ED. Patient age and measures of oxygenation status during ED stay are primary indicators of poor patient outcomes.

Risk factors for clinical progression in patients with COVID-19: a retrospective study of electronic health record data in the United Kingdom

BackgroundThe novel coronavirus disease 2019 (COVID-19) outbreak presents a significant threat to global health. A better understanding of patient clinical profiles is essential to drive efficient and timely health service strategies. In this study, we aimed to identify risk factors for a higher susceptibility to symptomatic presentation with COVID-19 and a transition to severe disease. MethodsWe analysed data on 2756 patients admitted to Chelsea & Westminster Hospital NHS Foundation Trust between 1st January and 23rd April 2020. We compared differences in characteristics between patients designated positive for COVID-19 and patients designated negative on hospitalisation and derived a multivariable logistic regression model to identify risk factors for predicting risk of symptomatic COVID-19. For patients with COVID-19, we used univariable and multivariable logistic regression to identify risk factors associated with progression to severe disease defined by: 1) admission to the hospitals AICU, 2) the need for mechanical ventilation, 3) in-hospital mortality, and 4) at least one measurement of elevated D-dimer ([≥]1,000 g/L) indicative of increased risk of venous thromboembolism. ResultsThe patient population consisted of 1148 COVID-19 positive and 1608 COVID-19 negative patients. Age, sex, self-reported ethnicity, C-reactive protein, white blood cell count, respiratory rate, body temperature, and systolic blood pressure formed the most parsimonious model for predicting risk of symptomatic COVID-19 at hospital admission. Among 1148 patients with COVID-19, 116 (10.1%) were admitted to the AICU, 71 (6.2%) required mechanical ventilation, 368 (32.1%) had at least one record of D-dimer levels [≥]1,000 g/L, and 118 patients died. In the multivariable logistic regression, age (OR = 0.953 per 1 year, 95% CI: 0.937-0.968) C-reactive protein (OR = 1.004 per 1 mg/L, 95% CI: 1.002-1.007), and white blood cell counts (OR = 1.059 per 109/L, 95% CI: 1.010-1.111) were found to be associated with admission to the AICU. Age (OR = 0.973 per 1 year, 95% CI: 0.955-0.990), C-reactive protein (OR = 1.003 per 1 mg/L, 95% CI: 1.000-1.006) and sodium (OR = 0.915 per 1 mmol/L, 0.868-0.962) were associated with mechanical ventilation. Age (OR = 1.023 per 1 year, 95% CI: 1.004-1.043), CRP (OR = 1.004 per 1 mg/L, 95% CI: 1.002-1.006), and body temperature (OR = 0.723 per 1{degrees}C, 95% CI: 0.541-0.958) were associated with elevated D-dimer. For mortality, we observed associations with age (OR = 1.060 per 1 year, 95% CI: 1.040-1.082), female sex (OR = 0.442, 95% CI: 0.442, 95% CI: 0.245-0.777), Asian ethnic background (OR = 2.237 vs White ethnic background, 95% CI: 1.111-4.510), C-reactive protein (OR = 1.004 per 1 mg/L, 95% CI: 1.001-1.006), sodium (OR = 1.038 per 1 mmol/L, 95% CI: 1.001-1.006), and respiratory rate (OR = 1.054 per 1 breath/min, 95% CI: 1.024-1.087). ConclusionOur analysis suggests there are several demographic, clinical and laboratory findings associated with a symptomatic presentation of COVID-19. Moreover, significant associations between patient deterioration were found with age, sex and specific blood markers, chiefly C-reactive protein, and could help early identification of patients at risk of poorer prognosis. Further work is required to clarify the extent to which our observations are relevant beyond current settings.