Dataset Information

Predicting intensive care unit admission and death for COVID-19 patients in the emergency department using early warning scores.

ABSTRACT:

Aims

To identify the most accurate early warning score (EWS) for predicting an adverse outcome in COVID-19 patients admitted to the emergency department (ED).

Methods

In adult consecutive patients admitted (March 1-April 15, 2020) to the ED of a major referral centre for COVID-19, we retrospectively calculated NEWS, NEWS2, NEWS-C, MEWS, qSOFA, and REMS from physiological variables measured on arrival. Sensitivity, specificity, positive (PPV) and negative predictive value (NPV), and the area under the receiver operating characteristic (AUROC) curve of each EWS for predicting admission to the intensive care unit (ICU) and death at 48?h and 7 days were calculated.

Results

We included 334 patients (119 [35.6%] females, median age 66 [54-78] years). At 7 days, the rates of ICU admission and death were 56/334 (17%) and 26/334 (7.8%), respectively. NEWS was the most accurate predictor of ICU admission within 7 days (AUROC 0.783 [95% CI, 0.735-0.826]; sensitivity 71.4 [57.8-82.7]%; NPV 93.1 [89.8-95.3]%), while REMS was the most accurate predictor of death within 7 days (AUROC 0.823 [0.778-0.863]; sensitivity 96.1 [80.4-99.9]%; NPV 99.4[96.2-99.9]%). Similar results were observed for ICU admission and death at 48?h. NEWS and REMS were as accurate as the triage system used in our ED. MEWS and qSOFA had the lowest overall accuracy for both outcomes.

Conclusion

In our single-centre cohort of COVID-19 patients, NEWS and REMS measured on ED arrival were the most sensitive predictors of 7-day ICU admission or death. EWS could be useful to identify patients with low risk of clinical deterioration.

SUBMITTER: Covino M

PROVIDER: S-EPMC7480278 | biostudies-literature | 2020 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting intensive care unit admission and death for COVID-19 patients in the emergency department using early warning scores.

Covino Marcello M Sandroni Claudio C Santoro Michele M Sabia Luca L Simeoni Benedetta B Bocci Maria Grazia MG Ojetti Veronica V Candelli Marcello M Antonelli Massimo M Gasbarrini Antonio A Gasbarrini Antonio A Franceschi Francesco F

Resuscitation 20200909

<h4>Aims</h4>To identify the most accurate early warning score (EWS) for predicting an adverse outcome in COVID-19 patients admitted to the emergency department (ED).<h4>Methods</h4>In adult consecutive patients admitted (March 1-April 15, 2020) to the ED of a major referral centre for COVID-19, we retrospectively calculated NEWS, NEWS2, NEWS-C, MEWS, qSOFA, and REMS from physiological variables measured on arrival. Sensitivity, specificity, positive (PPV) and negative predictive value (NPV), an ...[more]

PMID: 32918985

Similar Datasets

Project description:INTRODUCTION:Syncope is common among emergency department (ED) patients with acute pulmonary embolism (PE) and indicates a higher acuity and worse prognosis than in patients without syncope. Whether presyncope carries the same prognostic implications has not been established. We compared incidence of intensive care unit (ICU) admission in three groups of ED PE patients: those with presyncope; syncope; and neither. METHODS:This retrospective cohort study included all adults with acute, objectively confirmed PE in 21 community EDs from January 2013-April 2015. We combined electronic health record extraction with manual chart abstraction. We used chi-square test for univariate comparisons and performed multivariate analysis to evaluate associations between presyncope or syncope and ICU admission from the ED, reported as adjusted odds ratios (aOR) with 95% confidence intervals (CI). RESULTS:Among 2996 PE patients, 82 (2.7%) had presyncope and 109 (3.6%) had syncope. ICU admission was similar between groups (presyncope 18.3% vs syncope 25.7%) and different than their non-syncope counterparts (either 22.5% vs neither 4.7%; p<0.0001). On multivariate analysis, both presyncope and syncope were independently associated with ICU admission, controlling for demographics, higher-risk PE Severity Index (PESI) class, ventilatory support, proximal clot location, and submassive and massive PE classification: presyncope, aOR 2.79 (95% CI, 1.40, 5.56); syncope, aOR 4.44 (95% CI 2.52, 7.80). These associations were only minimally affected when excluding massive PE from the model. There was no significant interaction between either syncope or presyncope and PESI, submassive or massive classification in predicting ICU admission. CONCLUSION:Presyncope appears to carry similar strength of association with ICU admission as syncope in ED patients with acute PE. If this is confirmed, clinicians evaluating patients with acute PE may benefit from including presyncope in their calculus of risk assessment and site-of-care decision-making.

Project description:ObjectivePaediatric Early Warning Scores (PEWS) are widely used in the UK, but the heterogeneity across tools and the limited data on their predictive performance represent obstacles to improving best practice. The standardisation of practice through the proposed National PEWS will rely on robust validation. Therefore, we compared the performance of the National PEWS with six other PEWS currently used in NHS hospitals, for their ability to predict critical care (CC) admission in febrile children attending the emergency department (ED).DesignRetrospective single-centre cohort study.SettingTertiary hospital paediatric ED.ParticipantsA total of 11 449 eligible febrile ED attendances were identified from the electronic patient record over a 2-year period. Seven PEWS scores were calculated (Alder Hey, Bedside, Bristol, National, Newcastle and Scotland PEWS, and the Paediatric Observation Priority Score, using the worst observations recorded during their ED stay.OutcomesThe primary outcome was CC admission within 48 hours, the secondary outcomes were hospital length of stay (LOS) >48 hours and sepsis-related mortality.ResultsOf 11 449 febrile children, 134 (1.2%) were admitted to CC within 48 hours of ED presentation, 606 (5.3%) had a hospital LOS >48 hours. 10 (0.09%) children died, 5 (0.04%) were sepsis-related. All seven PEWS demonstrated excellent discrimination for CC admission (range area under the receiver operating characteristic curves (AUC) 0.91-0.95) and sepsis-related mortality (range AUC 0.95-0.99), most demonstrated moderate discrimination for hospital LOS (range AUC 0.69-0.75). In CC admission threshold analyses, bedside PEWS (AUC 0.90; 95% CI 0.86 to 0.93) and National PEWS (AUC 0.90; 0.87-0.93) were the most discriminative, both at a threshold of ≥6.ConclusionsOur results support the use of the proposed National PEWS in the paediatric ED for the recognition of suspected sepsis to improve outcomes, but further validation is required in other settings and presentations.

Project description:BackgroundMany studies have explored the accuracy of the National Early Warning Score 2 (NEWS2) in predicting mortality in prehospital and emergency settings, but their findings are inconsistent. Whether NEWS2 is reliable for the pre-examination and triage of patients in prehospital settings and emergency departments remains debatable. Hence, this study aimed to evaluate the accuracy of NEWS2 in predicting mortality in prehospital settings and emergency departments.MethodsWe searched PubMed, Embase, Cochrane Library, Web of Science, CNKI, Wan Fang Data, Vip Database and SinoMed from the inception of each database to January 2023. The inclusion criteria: (I) patients in the prehospital settings or emergency departments; (II) the NEWS2 for predicting 2-day mortality, 30-day mortality, and in-hospital mortality; (III) sufficient data, such as sensitivity, specificity, overall survival, and deaths, were provided for the study; (IV) the type of study was accuracy prediction study. Two authors independently extracted data, including authors, year of publication, country of origin, study design, sample size, threshold cutoff values of NEWS2, and mortality. The PROBAST was used to assess the risk of bias in the included studies.ResultsThirty studies with 185,835 participants were included. Among the 30 included studies, 13 have a high risk of bias, and 17 have a low risk of bias. The pooled sensitivity, specificity and AUC of 2-day mortality (early mortality), 30-day mortality and in-hospital mortality were 0.81 vs. 0.76 vs. 0.72 (95% CI: 0.61, 0.80), 0.81 vs. 0.69 vs. 0.78 (95% CI: 0.49, 0.93) and 0.88 vs. 0.80 vs. 0.78 (95% CI: 0.74, 0.82), respectively.ConclusionsNEWS2 has excellent sensitivity and specificity in predicting early mortality in patients in the prehospitals setting and emergency departments. Nonetheless, it has poor performance in predicting in-hospital mortality and 30-day mortality. Our findings underpin the use of NEWS2 as a pre-examination and triage tool to predict early death in the prehospital settings and emergency departments. To improve the predictive accuracy, it should be used to monitor patients continuously rather than at a single point-in-time.

Project description:ObjectiveTo predict hospital admission at the time of ED triage using patient history in addition to information collected at triage.MethodsThis retrospective study included all adult ED visits between March 2014 and July 2017 from one academic and two community emergency rooms that resulted in either admission or discharge. A total of 972 variables were extracted per patient visit. Samples were randomly partitioned into training (80%), validation (10%), and test (10%) sets. We trained a series of nine binary classifiers using logistic regression (LR), gradient boosting (XGBoost), and deep neural networks (DNN) on three dataset types: one using only triage information, one using only patient history, and one using the full set of variables. Next, we tested the potential benefit of additional training samples by training models on increasing fractions of our data. Lastly, variables of importance were identified using information gain as a metric to create a low-dimensional model.ResultsA total of 560,486 patient visits were included in the study, with an overall admission risk of 29.7%. Models trained on triage information yielded a test AUC of 0.87 for LR (95% CI 0.86-0.87), 0.87 for XGBoost (95% CI 0.87-0.88) and 0.87 for DNN (95% CI 0.87-0.88). Models trained on patient history yielded an AUC of 0.86 for LR (95% CI 0.86-0.87), 0.87 for XGBoost (95% CI 0.87-0.87) and 0.87 for DNN (95% CI 0.87-0.88). Models trained on the full set of variables yielded an AUC of 0.91 for LR (95% CI 0.91-0.91), 0.92 for XGBoost (95% CI 0.92-0.93) and 0.92 for DNN (95% CI 0.92-0.92). All algorithms reached maximum performance at 50% of the training set or less. A low-dimensional XGBoost model built on ESI level, outpatient medication counts, demographics, and hospital usage statistics yielded an AUC of 0.91 (95% CI 0.91-0.91).ConclusionMachine learning can robustly predict hospital admission using triage information and patient history. The addition of historical information improves predictive performance significantly compared to using triage information alone, highlighting the need to incorporate these variables into prediction models.

Dataset Information

Predicting intensive care unit admission and death for COVID-19 patients in the emergency department using early warning scores.

Aims

Methods

Results

Conclusion

Publications

Predicting intensive care unit admission and death for COVID-19 patients in the emergency department using early warning scores.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets