Dataset Information

COVID outcome prediction in the emergency department (COPE): using retrospective Dutch hospital data to develop simple and valid models for predicting mortality and need for intensive care unit admission in patients who present at the emergency department with suspected COVID-19.

ABSTRACT:

Objectives

Develop simple and valid models for predicting mortality and need for intensive care unit (ICU) admission in patients who present at the emergency department (ED) with suspected COVID-19.

Design

Retrospective.

Setting

Secondary care in four large Dutch hospitals.

Participants

Patients who presented at the ED and were admitted to hospital with suspected COVID-19. We used 5831 first-wave patients who presented between March and August 2020 for model development and 3252 second-wave patients who presented between September and December 2020 for model validation.

Outcome measures

We developed separate logistic regression models for in-hospital death and for need for ICU admission, both within 28 days after hospital admission. Based on prior literature, we considered quickly and objectively obtainable patient characteristics, vital parameters and blood test values as predictors. We assessed model performance by the area under the receiver operating characteristic curve (AUC) and by calibration plots.

Results

Of 5831 first-wave patients, 629 (10.8%) died within 28 days after admission. ICU admission was fully recorded for 2633 first-wave patients in 2 hospitals, with 214 (8.1%) ICU admissions within 28 days. A simple model-COVID outcome prediction in the emergency department (COPE)-with age, respiratory rate, C reactive protein, lactate dehydrogenase, albumin and urea captured most of the ability to predict death. COPE was well calibrated and showed good discrimination for mortality in second-wave patients (AUC in four hospitals: 0.82 (95% CI 0.78 to 0.86); 0.82 (95% CI 0.74 to 0.90); 0.79 (95% CI 0.70 to 0.88); 0.83 (95% CI 0.79 to 0.86)). COPE was also able to identify patients at high risk of needing ICU admission in second-wave patients (AUC in two hospitals: 0.84 (95% CI 0.78 to 0.90); 0.81 (95% CI 0.66 to 0.95)).

Conclusions

COPE is a simple tool that is well able to predict mortality and need for ICU admission in patients who present to the ED with suspected COVID-19 and may help patients and doctors in decision making.

SUBMITTER: van Klaveren D

PROVIDER: S-EPMC8449847 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundEmergency department (ED) crowding leads to prolonged emergency department length of stay (ED-LOS) and adverse patient outcomes. No uniform definition of ED crowding exists. Several scores have been developed to quantify ED crowding; the best known is the Emergency Department Work Index (EDWIN). Research on the EDWIN is often applied to limited settings and conducted over a short period of time.ObjectivesTo explore whether the EDWIN as a measure can track occupancy at a Dutch ED over the course of one year and to identify fluctuations in ED occupancy per hour, day, and month. Secondary objective is to investigate the discriminatory value of the EDWIN in detecting crowding, as compared with the occupancy rate and prolonged ED-LOS.MethodsA retrospective cohort study of all ED visits during the period from September 2010 to August 2011 was performed in one hospital in the Netherlands. The EDWIN incorporates the number of patients per triage level, physicians, treatment beds and admitted patients to quantify ED crowding. The EDWIN was adjusted to emergency care in the Netherlands: modified EDWIN (mEDWIN). ED crowding was defined as the 75th percentile of mEDWIN per hour, which was ≥0.28.ResultsIn total, 28,220 ED visits were included in the analysis. The median mEDWIN per hour was 0.15 (Interquartile range (IQR) 0.05-0.28); median mEDWIN per patient was 0.25 (IQR 0.15-0.39). The EDWIN was higher on Wednesday (0.16) than on other days (0.14-0.16, p<0.001), and a peak in both mEDWIN (0.30-0.33) and ED crowding (52.9-63.4%) was found between 13:00-18:00 h. A comparison of the mEDWIN with the occupancy rate revealed an area under the curve (AUC) of 0.86 (95%CI 0.85-0.87). The AUC of mEDWIN compared with a prolonged ED-LOS (≥4 hours) was 0.50 (95%CI 0.40-0.60).ConclusionThe mEDWIN was applicable at a Dutch ED. The mEDWIN was able to identify fluctuations in ED occupancy. In addition, the mEDWIN had high discriminatory power for identification of a busy ED, when compared with the occupancy rate.

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.