Predicting 30-day return hospital admissions in patients with COVID-19 discharged from the emergency department: A national retrospective cohort study.

OBJECTIVES: Identification of patients with coronavirus disease 2019 (COVID-19) at risk for deterioration after discharge from the emergency department (ED) remains a clinical challenge. Our objective was to develop a prediction model that identifies patients with COVID-19 at risk for return and hospital admission within 30 days of ED discharge. METHODS: We performed a retrospective cohort study of discharged adult ED patients (n = 7529) with SARS-CoV-2 infection from 116 unique hospitals contributing to the National Registry of Suspected COVID-19 in Emergency Care. The primary outcome was return hospital admission within 30 days. Models were developed using classification and regression tree (CART), gradient boosted machine (GBM), random forest (RF), and least absolute shrinkage and selection (LASSO) approaches. RESULTS: Among patients with COVID-19 discharged from the ED on their index encounter, 571 (7.6%) returned for hospital admission within 30 days. The machine-learning (ML) models (GBM, RF, and LASSO) performed similarly. The RF model yielded a test area under the receiver operating characteristic curve of 0.74 (95% confidence interval [CI], 0.71-0.78), with a sensitivity of 0.46 (95% CI, 0.39-0.54) and a specificity of 0.84 (95% CI, 0.82-0.85). Predictive variables, including lowest oxygen saturation, temperature, or history of hypertension, diabetes, hyperlipidemia, or obesity, were common to all ML models. CONCLUSIONS: A predictive model identifying adult ED patients with COVID-19 at risk for return for return hospital admission within 30 days is feasible. Ensemble/boot-strapped classification methods (eg, GBM, RF, and LASSO) outperform the single-tree CART method. Future efforts may focus on the application of ML models in the hospital setting to optimize the allocation of follow-up resources.

Lung Base Findings of Coronavirus Disease (COVID-19) on Abdominal CT in Patients With Predominant Gastrointestinal Symptoms.

OBJECTIVE. This series of patients presented to the emergency department (ED) with abdominal pain, without the respiratory symptoms typical of coronavirus disease (COVID-19), and the abdominal radiologist was the first to suggest COVID-19 infection because of findings in the lung bases on CT of the abdomen. CONCLUSION. COVID-19 infection can present primarily with abdominal symptoms, and the abdominal radiologist must suggest the diagnosis when evaluating the lung bases for typical findings.

Emergency Department-initiated High-flow Nasal Cannula for COVID-19 Respiratory Distress.

INTRODUCTION: Patients with coronavirus disease 2019 (COVID-19) can develop rapidly progressive respiratory failure. Ventilation strategies during the COVID-19 pandemic seek to minimize patient mortality. In this study we examine associations between the availability of emergency department (ED)-initiated high-flow nasal cannula (HFNC) for patients presenting with COVID-19 respiratory distress and outcomes, including rates of endotracheal intubation (ETT), mortality, and hospital length of stay. METHODS: We performed a retrospective, non-concurrent cohort study of patients with COVID-19 respiratory distress presenting to the ED who required HFNC or ETT in the ED or within 24 hours following ED departure. Comparisons were made between patients presenting before and after the introduction of an ED-HFNC protocol. RESULTS: Use of HFNC was associated with a reduced rate of ETT in the ED (46.4% vs 26.3%, P <0.001) and decreased the cumulative proportion of patients who required ETT within 24 hours of ED departure (85.7% vs 32.6%, P <0.001) or during their entire hospitalization (89.3% vs 48.4%, P <0.001). Using HFNC was also associated with a trend toward increased survival to hospital discharge; however, this was not statistically significant (50.0% vs 68.4%, P = 0.115). There was no impact on intensive care unit or hospital length of stay. Demographics, comorbidities, and illness severity were similar in both cohorts. CONCLUSIONS: The institution of an ED-HFNC protocol for patients with COVID-19 respiratory distress was associated with reductions in the rate of ETT. Early initiation of HFNC is a promising strategy for avoiding ETT and improving outcomes in patients with COVID-19.

Translating COVID-19 knowledge to practice: Enhancing emergency medicine using the "wisdom of crowds".

In the spring of 2020, emergency physicians found themselves in new, uncharted territory as there were few data available for understanding coronavirus disease 2019 (COVID-19), the disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus. In response, knowledge was being crowd sourced and shared across online platforms. The "wisdom of crowds" is an important vehicle for sharing information and expertise. In this article, we explore concepts related to the social psychology of group decisionmaking and knowledge translation. We then analyze a scenario in which the American College of Emergency Physicians (ACEP), a professional medical society, used the wisdom of crowds (via the EngagED platform) to disseminate clinically relevant information and create a useful resource called the "ACEP COVID-19 Field Guide." We also evaluate the crowd-sourced approach, content, and attributes of EngagED compared to other social media platforms. We conclude that professional organizations can play a more prominent role using the wisdom of crowds for augmenting pandemic response efforts.