Dataset Information

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

ABSTRACT: Since its emergence in late 2019, the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused a pandemic with more than 55 million reported cases and 1.3 million estimated 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. In this retrospective study, we analysed data of 879 confirmed SARS-CoV-2 positive patients admitted to a two-site NHS Trust hospital in London, England, between January 1st and May 26th, 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: admission to intensive care, need for invasive mechanical ventilation and in-hospital mortality. Based on the trained models, we extracted the most informative clinical features in determining these patient trajectories. Considering our inclusion criteria, we have identified 129 of 879 (15%) patients that required intensive care, 62 of 878 (7%) patients needing mechanical ventilation, and 193 of 619 (31%) cases of in-hospital mortality. Our models learned successfully from early clinical data and predicted clinical endpoints with high accuracy, the best model achieving area under the receiver operating characteristic (AUC-ROC) scores of 0.76 to 0.87 (F1 scores of 0.42-0.60). Younger patient age was associated with an increased risk of receiving intensive care and ventilation, but lower risk of mortality. Clinical indicators of a patient's oxygen supply and selected laboratory results, such as blood lactate and creatinine levels, were most predictive of COVID-19 patient trajectories. Among COVID-19 patients machine learning can aid in the early identification of those with a poor prognosis, using EHR data collected during a patient's first presentation at ED. Patient age and measures of oxygenation status during ED stay are primary indicators of poor patient outcomes.

SUBMITTER: Heldt FS

PROVIDER: S-EPMC7892838 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Heldt Frank S FS Vizcaychipi Marcela P MP Peacock Sophie S Cinelli Mattia M McLachlan Lachlan L Andreotti Fernando F Jovanović Stojan S Dürichen Robert R Lipunova Nadezda N Fletcher Robert A RA Hancock Anne A McCarthy Alex A Pointon Richard A RA Brown Alexander A Eaton James J Liddi Roberto R Mackillop Lucy L Tarassenko Lionel L Khan Rabia T RT

Scientific reports 20210218 1

Since its emergence in late 2019, the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused a pandemic with more than 55 million reported cases and 1.3 million estimated 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. In this retrospective study, we analysed data of 879 confirmed SARS-CoV-2 positive patients admitted to ...[more]

PMID: 33603086

Similar Datasets

Project description:IntroductionWithin a few months coronavirus disease 2019 (COVID-19) evolved into a pandemic causing millions of cases worldwide, but it remains challenging to diagnose the disease in a timely fashion in the emergency department (ED). In this study we aimed to construct machine-learning (ML) models to predict severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) infection based on the clinical features of patients visiting an ED during the early COVID-19 pandemic.MethodsWe retrospectively collected the data of all patients who received reverse transcriptase polymerase chain reaction (RT-PCR) testing for SARS-CoV-2 at the ED of Baylor Scott & White All Saints Medical Center, Fort Worth, from February 23-May 12, 2020. The variables collected included patient demographics, ED triage data, clinical symptoms, and past medical history. The primary outcome was the confirmed diagnosis of COVID-19 (or SARS-CoV-2 infection) by a positive RT-PCR test result for SARS-CoV-2, and was used as the label for ML tasks. We used univariate analyses for feature selection, and variables with P<0.1 were selected for model construction. Samples were split into training and testing cohorts on a 60:40 ratio chronologically. We tried various ML algorithms to construct the best predictive model, and we evaluated performances with the area under the receiver operating characteristic curve (AUC) in the testing cohort.ResultsA total of 580 ED patients were tested for SARS-CoV-2 during the study periods, and 98 (16.9%) were identified as having the SARS-CoV-2 infection based on the RT-PCR results. Univariate analyses selected 21 features for model construction. We assessed three ML methods for performance: of the three methods, random forest outperformed the others with the best AUC result (0.86), followed by gradient boosting (0.83) and extra trees classifier (0.82).ConclusionThis study shows that it is feasible to use ML models as an initial screening tool for identifying patients with SARS-CoV-2 infection. Further validation will be necessary to determine how effectively this prediction model can be used prospectively in clinical practice.

Project description:ObjectivesEmergency department (ED) health care personnel (HCP) are at risk of exposure to SARS-CoV-2. The objective of this study was to determine the attributable risk of SARS-CoV-2 infection from providing ED care, describe personal protective equipment use, and identify modifiable ED risk factors. We hypothesized that providing ED patient care increases the probability of acquiring SARS-CoV-2 infection.MethodsWe conducted a multicenter prospective cohort study of 1,673 ED physicians, advanced practice providers (APPs), nurses, and nonclinical staff at 20 U.S. centers over 20 weeks (May to December 2020; before vaccine availability) to detect a four-percentage point increased SARS-CoV-2 incidence among HCP related to direct patient care. Participants provided monthly nasal and serology specimens and weekly exposure and procedure information. We used multivariable regression and recursive partitioning to identify risk factors.ResultsOver 29,825 person-weeks, 75 participants (4.5%) acquired SARS-CoV-2 infection (31 were asymptomatic). Physicians/APPs (aOR 1.07; 95% CI 0.56-2.03) did not have higher risk of becoming infected compared to nonclinical staff, but nurses had a marginally increased risk (aOR 1.91; 95% CI 0.99-3.68). Over 99% of participants used CDC-recommended personal protective equipment (PPE), but PPE lapses occurred in 22.1% of person-weeks and 32.1% of SARS-CoV-2-infected patient intubations. The following factors were associated with infection: household SARS-CoV-2 exposure; hospital and community SARS-CoV-2 burden; community exposure; and mask non-use in public. SARS-CoV-2 intubation was not associated with infection (attributable risk fraction 13.8%; 95% CI -2.0-38.2%), and nor were PPE lapses.ConclusionsAmong unvaccinated U.S. ED HCP during the height of the pandemic, the risk of SARS-CoV-2 infection was similar in nonclinical staff and HCP engaged in direct patient care. Many identified risk factors were related to community exposures.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets