Succinct Approach to Delirium in the Emergency Department

An Outcome Comparison Between Geriatric and Nongeriatric Emergency Departments

STUDY OBJECTIVE

We sought to describe diagnosis rates and compare common process outcomes between geriatric emergency departments (EDs) and nongeriatric EDs participating in the American College of Emergency Physicians Clinical Emergency Data Registry (CEDR).

METHODS

We conducted an observational study of ED visits in calendar year 2021 within the CEDR by older adults. The analytic sample included 6,444,110 visits at 38 geriatric EDs and 152 matched nongeriatric EDs, with the geriatric ED status determined based on linkage to the American College of Emergency Physicians' Geriatric ED Accreditation program. Stratified by age, we assessed diagnosis rates (X/1000) for 4 common geriatric syndrome conditions and a set of common process outcomes including the ED length of stay, discharge rates, and 72-hour revisit rates.

RESULTS

Across all age categories, geriatric EDs had higher diagnosis rates than nongeriatric EDs for 3 of the 4 following geriatric syndrome conditions of interest: urinary tract infection, dementia, and delirium/altered mental status. The median ED site-level length of stay for older adults was lower at geriatric EDs compared with that at nongeriatric EDs, whereas 72-hour revisit rates were similar across all age categories. Geriatric EDs exhibited a median discharge rate of 67.5% for adults aged 65 to 74 years, 60.8% for adults aged 75 to 84 years, and 55.6% for adults aged >85 years. Comparatively, the median discharge rate at nongeriatric ED sites was 69.0% for adults aged 65 to 74 years, 64.2% for adults aged 75 to 84 years, and 61.3% for adults aged >85 years.

CONCLUSION

Geriatric EDs had higher geriatric syndrome diagnosis rates, lower ED lengths of stay, and similar discharge and 72-hour revisit rates when compared with nongeriatric EDs in the CEDR. These findings provide the first benchmarks for emergency care process outcomes in geriatric EDs compared with nongeriatric EDs.

A Lethal Combination of Delirium and Overcrowding in the Emergency Department

Delirium is a common public health concern that significantly impacts older patients admitted to the Emergency Department (ED). This condition is linked to adverse outcomes such as reduced long-term functionality, higher mortality rates, extended hospital stays, and increased medical costs. The identification of risk factors is crucial for the early recognition and management of delirium in ED patients. Aging, cognitive decline, polypharmacy, and sensory impairment are some of the most common general risk factors described in the literature. Although validated delirium assessment tools already exist, they are not practical for the fast-paced ED environment because of their extended evaluation period or specialized training request. Moreover, clear guidance is needed to select the most suitable tool for detecting delirium, balancing between the accuracy and the swiftness required in an overcrowded, high-stress, and understaffed healthcare setting. This narrative review aims to analyze the updated literature on delirium risk factors in older ED patients and focuses on the methods for better screening, managing, and treating this condition in the ED.

Evaluating the performance of machine learning methods for risk estimation of delirium in patients hospitalized from the emergency department

INTRODUCTION

Delirium is a cerebral dysfunction seen commonly in the acute care setting. It is associated with increased mortality and morbidity and is frequently missed in the emergency department (ED) and inpatient care by clinical gestalt alone. Identifying those at risk of delirium may help prioritize screening and interventions in the hospital setting.

OBJECTIVE

Our objective was to leverage electronic health records to identify a clinically valuable risk estimation model for prevalent delirium in patients being transferred from the ED to inpatient units.

METHODS

This was a retrospective cohort study to develop and validate a risk model to detect delirium using patient data available from prior visits and ED encounter. Electronic health records were extracted for patients hospitalized from the ED between January 1, 2014, and December 31, 2020. Eligible patients were aged 65 or older, admitted to an inpatient unit from the emergency department, and had at least one DOSS assessment or CAM-ICU recorded within 72 h of hospitalization. Six machine learning models were developed to estimate the risk of delirium using clinical variables including demographic features, physiological measurements, medications administered, lab results, and diagnoses.

RESULTS

A total of 28,531 patients met the inclusion criteria with 8057 (28.4%) having a positive delirium screening within the outcome observation period. Machine learning models were compared using the area under the receiver operating curve (AUC). The gradient boosted machine achieved the best performance with an AUC of 0.839 (95% CI, 0.837-0.841). At a 90% sensitivity threshold, this model achieved a specificity of 53.5% (95% CI 53.0%-54.0%) a positive predictive value of 43.5% (95% CI 43.2%-43.9%), and a negative predictive value of 93.1% (95% CI 93.1%-93.2%). A random forest model and L1-penalized logistic regression also demonstrated notable performance with AUCs of 0.837 (95% CI, 0.835-0.838) and 0.831 (95% CI, 0.830-0.833) respectively.

CONCLUSION

This study demonstrated the use of machine learning algorithms to identify a combination of variables that enables an estimation of risk of positive delirium screens early in hospitalization to develop prevention or management protocols.