A comparative evaluation of the strengths of association between different emergency department crowding metrics and repeat visits within 72 hours

Prediction of high-risk emergency department revisits from a machine-learning algorithm: a proof-of-concept study

BACKGROUND

High-risk emergency department (ED) revisit is considered an important quality indicator that may reflect an increase in complications and medical burden. However, because of its multidimensional and highly complex nature, this factor has not been comprehensively investigated. This study aimed to predict high-risk ED revisit with a machine-learning (ML) approach.

METHODS

This 3-year retrospective cohort study assessed adult patients between January 2019 and December 2021 from National Taiwan University Hospital Hsin-Chu Branch with high-risk ED revisit, defined as hospital or intensive care unit admission after ED return within 72 hours. A total of 150 features were preliminarily screened, and 79 were used in the prediction model. Deep learning, random forest, extreme gradient boosting (XGBoost) and stacked ensemble algorithm were used. The stacked ensemble model combined multiple ML models and performed model stacking as a meta-level algorithm. Confusion matrix, accuracy, sensitivity, specificity and area under the receiver operating characteristic curve (AUROC) were used to evaluate performance.

RESULTS

Analysis was performed for 6282 eligible adult patients: 5025 (80.0%) in the training set and 1257 (20.0%) in the testing set. High-risk ED revisit occurred for 971 (19.3%) of training set patients vs 252 (20.1%) in the testing set. Leading predictors of high-risk ED revisit were age, systolic blood pressure and heart rate. The stacked ensemble model showed more favourable prediction performance (AUROC 0.82) than the other models: deep learning (0.69), random forest (0.78) and XGBoost (0.79). Also, the stacked ensemble model achieved favourable accuracy and specificity.

CONCLUSION

The stacked ensemble algorithm exhibited better prediction performance in which the predictions were generated from different ML algorithms to optimally maximise the final set of results. Patients with older age and abnormal systolic blood pressure and heart rate at the index ED visit were vulnerable to high-risk ED revisit. Further studies should be conducted to externally validate the model.

Overcrowding in emergency departments: an overview of reviews describing global solutions and their outcomes

Emergency Department (ED) crowding is defined as a situation wherein the demands of emergency services overcome the ability of a department to provide high-quality care within an appropriate time frame. There is a need for solutions, as the harms of crowding impact patients, staff, and healthcare spending. An overview of ED crowding was previously published by our group, which outlines these global issues. The problem of overcrowding in emergency departments has emerged as a global public health concern, and several healthcare agencies have addressed the issue and proposed possible solutions at each level of emergency care. There is no current literature summarizing the extensive research on interventions and solutions, thus there is a need for data synthesis to inform policymakers in this field. The aim of this overview was to summarize the interventions at each level of emergency care: input, throughput, and output. The methodology was supported by the current PRIOR statement for an overview of reviews. The study summarized twenty-seven full-text systematic reviews, which encompassed three hundred and eight primary studies. The results of the summary displayed a requirement for increasing studies in input and output interventions, as these showed the best outcomes with regard to ED crowding metrics. Moreover, the results displayed heterogeneous results at each level of ED care; these reflected that generally solutions have not been matched to specific problems facing regional centres. Thus, individual factors need to be considered when implementing solutions in Emergency Departments.

Prevalence and predictors of elder abuse among older adults attending emergency departments: a prospective cohort study

INTRODUCTION

Elder abuse is associated with impaired physical and psychological health. It is, however, rarely identified in emergency departments (EDs). The objective was to determine the prevalence and the predictors of elder abuse among older adults visiting EDs.

METHODS

This prospective cohort study was conducted in eight Canadian EDs between May and August 2021. Patients were eligible if they were ≥ 65 years old, oriented to time, and with a Canadian Triage and Acuity Scale score 3, 4 or 5. In a private setting, participants were questioned directly about abuse as part of a larger questionnaire exploring ten non-medical problems. We used multivariable logistic regression to identify predictors of elder abuse.

RESULTS

A total of 1061 participants were recruited (mean age: 77.1 (SD 7.6) years, female sex: 55.7%, lived alone: 42.5%). Patients mostly attended EDs for pain (19.6%), neurologic (11.3%) or cardiovascular (8.4%) symptoms. The most frequent pre-existing comorbidities were hypertension (67.2%), mental health conditions (33.3%) and cardiac insufficiency (29.6%). Mobility issues outside (41.0%) or inside their home (30.7%) and loneliness (29.4%) were also frequent. Fifty-four (5.1%) participants reported elder abuse, of which 34.3% were aware of available community-based resources. Identified predictors of elder abuse were female sex (OR 2.8 [95%CI 1.4; 5.6]), financial difficulties (OR 3.6 [95%CI 1.8; 7.3]), food insecurity (OR 2.7 [95%CI 1.2; 5.6]), need for a caregiver (OR 2.7 [95%CI 1.5; 5.0]) and at least one pre-existing mental health condition (OR 2.6 [95%CI 1.4; 4.9]).

CONCLUSION

When questioned directly, 5.1% of older adults attending EDs reported experiencing abuse. Female sex, functional impairment, social vulnerability, and mental health comorbidities are associated with elder abuse. Given its importance and relatively high prevalence, ED professionals should have a low threshold to ask directly about elder abuse.

The risk factors of the 72-h unscheduled return visit admission to emergency department in adults below 50 years old

BACKGROUND

An unscheduled return visit (URV) to the emergency department (ED) within 72-h is an indicator of ED performance. An unscheduled return revisit (URV) within 72-h was used to monitor adverse events and medical errors in a hospital quality improvement program. The study explores the potential factors that contribute to URV to the ED within 72-h and the unscheduled return revisit admission (URVA) in adults below 50 years old.

METHODS

The case-control study enrolled 9483 URV patients during 2015-2020 in National Cheng-Kung University Hospital. URVA and URV non-admission (URVNA) patients were analyzed. The Gini impurity index was calculated by decision tree (DT) to split the variables capable of partitioning the groups into URVA and URVNA. Logistic regression is applied to calculate the odds ratio (OR) of candidate variables. The α level was set at 0.05.

RESULTS

Among patients under the age of 50, the percentage of females in URVNA was 55.05%, while in URVA it was 53.25%. Furthermore, the average age of URVA patients was 38.20 ± 8.10, which is higher than the average age of 35.19 ± 8.65 observed in URVNA. The Charlson Comorbidity Index (CCI) of the URVA patients (1.59 ± 1.00) was significantly higher than that of the URVNA patients (1.22 ± 0.64). The diastolic blood pressure (DBP) of the URVA patients was 85.29 ± 16.22, which was lower than that of the URVNA (82.89 ± 17.29). Severe triage of URVA patients is 21.1%, which is higher than the 9.7% of URVNA patients. The decision tree suggests that the factors associated with URVA are "severe triage," "CCI higher than 2," "DBP less than 86.5 mmHg," and "age older than 34 years". These risk factors were verified by logistic regression and the OR of CCI was 2.42 (1.50-3.90), the OR of age was 1.84 (1.50-2.27), the OR of DBP less than 86.5 was 0.71 (0.58-0.86), and the OR of severe triage was 2.35 (1.83-3.03).

CONCLUSIONS

The results provide physicians with a reference for discharging patients and could help ED physicians reduce the cognitive burden associated with the diagnostic errors and stress.

Emergency department crowding: an overview of reviews describing measures causes, and harms

Crowding in Emergency Departments (EDs) has emerged as a global public health crisis. Current literature has identified causes and the potential harms of crowding in recent years. The way crowding is measured has also been the source of emerging literature and debate. We aimed to synthesize the current literature of the causes, harms, and measures of crowding in emergency departments around the world. The review is guided by the current PRIOR statement, and involved Pubmed, Medline, and Embase searches for eligible systematic reviews. A risk of bias and quality assessment were performed for each review, and the results were synthesized into a narrative overview. A total of 13 systematic reviews were identified, each targeting the measures, causes, and harms of crowding in global emergency departments. Key among the results is that the measures of crowding were heterogeneous, even in geographically proximate areas, and that temporal measures are being utilized more frequently. It was identified that many measures are associated with crowding, and the literature would benefit from standardization of these metrics to promote improvement efforts and the generalization of research conclusions. The major causes of crowding were grouped into patient, staff, and system-level factors; with the most important factor identified as outpatient boarding. The harms of crowding, impacting patients, healthcare staff, and healthcare spending, highlight the importance of addressing crowding. This overview was intended to synthesize the current literature on crowding for relevant stakeholders, to assist with advocacy and solution-based decision making.