Artificial intelligence (AI) has emerged as a potentially transformative force, particularly in the realm of emergency medicine (EM). The implementation of AI in emergency departments (ED) has the ...potential to improve patient care through various modalities. However, the implementation of AI in the ED presents unique challenges that influence its clinical adoption. This scoping review summarizes the current literature exploring the barriers and facilitators of the clinical implementation of AI in the ED.
We systematically searched Embase (Ovid), MEDLINE (Ovid), Web of Science, and Engineering Village. All articles were published in English through November 20th, 2023. Two reviewers screened the search results, with disagreements resolved through third-party adjudication.
A total of 8172 studies were included in the preliminary search, with 22 selected for the final data extraction. 10 studies were reviews and the remaining 12 were primary quantitative, qualitative, and mixed-methods studies. Out of the 22, 13 studies investigated a specific AI tool or application. Common barriers to implementation included a lack of model interpretability and explainability, encroachment on physician autonomy, and medicolegal considerations. Common facilitators to implementation included educating staff on the model, efficient integration into existing workflows, and sound external validation.
There is increasing literature on AI implementation in the ED. Our research suggests that the most common barrier facing AI implementation in the ED is model interpretability and explainability. More primary research investigating the implementation of specific AI tools should be undertaken to help facilitate their successful clinical adoption in the ED.
Patients, families and community members would like emergency department wait time visibility. This would improve patient journeys through emergency medicine. The study objective was to derive, ...internally and externally validate machine learning models to predict emergency patient wait times that are applicable to a wide variety of emergency departments.
Twelve emergency departments provided 3 years of retrospective administrative data from Australia (2017-2019). Descriptive and exploratory analyses were undertaken on the datasets. Statistical and machine learning models were developed to predict wait times at each site and were internally and externally validated. Model performance was tested on COVID-19 period data (January to June 2020).
There were 1 930 609 patient episodes analysed and median site wait times varied from 24 to 54 min. Individual site model prediction median absolute errors varied from±22.6 min (95% CI 22.4 to 22.9) to ±44.0 min (95% CI 43.4 to 44.4). Global model prediction median absolute errors varied from ±33.9 min (95% CI 33.4 to 34.0) to ±43.8 min (95% CI 43.7 to 43.9). Random forest and linear regression models performed the best, rolling average models underestimated wait times. Important variables were triage category, last-k patient average wait time and arrival time. Wait time prediction models are not transferable across hospitals. Models performed well during the COVID-19 lockdown period.
Electronic emergency demographic and flow information can be used to approximate emergency patient wait times. A general model is less accurate if applied without site-specific factors.
To increase the percentage of patients who undergo rapid magnetic resonance imaging (rMRI) rather than computed tomography (CT) for evaluation of mild traumatic brain injury (TBI) from 45% in 2020 to ...80% by December 2021.
This was a quality improvement initiative targeted to patients presenting to the pediatric emergency department presenting with mild TBI, with baseline data collected from January 2020 to December 2020. From January 2021 to August 2021, we implemented a series of improvement interventions and tracked the percentage of patients undergoing neuroimaging who received rMRI as their initial study. Balancing measures included proportion of all patients with mild TBI who underwent neuroimaging of any kind, proportion of patients requiring sedation, emergency department length of stay, and percentage with clinically important TBI.
The utilization of rMRI increased from a baseline of 45% to a mean of 92% in the intervention period. Overall neuroimaging rates did not change significantly after the intervention (19.8 vs 23.2%, P = .24). There was no difference in need for anxiolysis (12 vs 7%, P = .30) though emergency department length of stay was marginally increased (1.4 vs 1.7 hours, P = < 0.01).
In this quality improvement initiative, transition to rMRI as the primary imaging modality for the evaluation of minor TBI was achieved at a level 1 pediatric trauma center with no significant increase in overall use of neuroimaging.
To compare sociodemographic factors in patients presenting to the emergency department (ED) with emergent and non-emergent eye-related concerns.
Cross-sectional multicenter study.
60,677 patients ...with eye-related concerns who visited EDs at Bascom Palmer Eye Institute, Wills Eye Hospital, Massachusetts Eye and Ear, and Johns Hopkins Hospital/Wilmer Eye Institute from January 1st, 2019 until December 31st, 2019.
Descriptive statistics were performed using STATA 17.
1) Sociodemographic factors associated with emergent diagnoses, 2) Visit patterns across ED settings (i.e. standard ED vs eye ED), and 3) the most common emergent and non-emergent diagnoses.
A total of 60,677 eye-related ED encounters were included in the study, including 22,434 at Bascom Palmer Eye Institute, 16,124 at Wills Eye Hospital, 15,487 at Massachusetts Eye and Ear, and 6,632 at Johns Hopkins Hospital/Wilmer Eye Institute. Most patients had non-emergent diagnoses (56.7%). Males (OR 1.85, 95% CI 1.79-1.92) were more likely to have an emergent diagnosis than females. Patients with private/employer-based insurance (OR 0.88, 95% CI 0.81-0.96), Medicare (OR 0.80, 95% CI 0.72-0.87), and Medicaid (OR 0.81, 95% CI 0.74-0.89) were all less likely to have an emergent diagnosis than uninsured patients. Those with veteran/military insurance (OR 1.08, 95% CI 0.87-1.34) were equally likely to have an emergent diagnosis compared to uninsured patients. Non-White Hispanic patients (OR 1.26, 95% CI 1.12-1.42) were more likely to present with an emergent condition than White patients. Patient seen in the standard ED setting were more likely to have emergent diagnoses than those who visited standalone eye EDs (P < 0.001). The most common emergent diagnoses were corneal abrasion (12.97%), extraocular foreign body (7.61%), and corneal ulcer (7.06%). The most common non-emergent diagnoses were dry eye (7.90%), posterior vitreous detachment (7.76%), and chalazion (6.57%).
ED setting was associated with the acuity of patient diagnoses. Lack of insurance coverage and non-White Hispanic race/ethnicity were associated with emergent eye-related ED visits. Improving access to ophthalmic care in these populations may reduce the incidence of preventable eye emergencies related to untreated chronic conditions. This combined with measures to redirect non-emergent issues to outpatient clinics may alleviate ED overload.
Posterior hip dislocation is commonly seen in the emergency department and requires urgent reduction to help avoid complications. Many techniques have been described to perform the reduction, all ...aimed at helping the physician gain a mechanical advantage to overcome the bony anatomy and large muscles groups involved. We describe a new technique that utilizes a hydraulic patient lift to help provide the traction force necessary to reduce posterior hip dislocations. The patient is secured to the bed with a strap or sheet tied over their pelvis and then a loop is secured under their popliteal region and secured to the hydraulic lift. The lift is engaged to create the desired traction, allowing the provider to manipulate the hip with adduction/abduction and/or internal/external rotation to achieve reduction. In addition, our method may also allow the provider to task switch more easily between other requirements, such as procedural sedation and attention to the patient's airway, especially in the single coverage emergency department.
Emergency medicine is a dynamically complex and well-coordinated specialty. However, paediatric emergency sub-specialty is not yet well developed in most low and middle income countries. The purpose ...of the present study is to analyze the pediatric patients who passed through the emergency department of the hospital. Results: Total examined children - 44547. Hospitalized – 12 062 - 30.7% of the total. Boys predominate (54.0%). Children in the age group 1-10 years - 81.8%. The patient flow in the pediatric emergency department from other districts increased by 35.8%. Conclusion: Children are a particularly vulnerable group of patients who go through the emergency department, which is related to the specifics of pediatric care. The results of the study show that the largest proportion of pediatric patients are children aged 1-10 years, males, who sought medical help in connection with respiratory infections.
Emergency Department admissions have changed significantly during the COVID-19 pandemic. Understanding this variation may play a crucial role in rearranging hospital resources for better outcome. In ...this study, we aimed to assess the impact of COVID-19 pandemic on emergency department admission and outcome.
This is a cross-sectional retrospective study conducted at Bharatpur Hospital, Nepal comparing pre- pandemic data of the 4 months (March 24 to July 21, 2019) with the initial 4 months of the pandemic (March 24 to July 21, 2020).
Admission in emergency ward decreased during covid period among female admission (47%vs43%), age-group(0-14)(18%vs12%), Dalit(17%vs11%) p<0.0001.Diagnosis increased during covid for acute abdomen(11%vs13%), animal and insect bite(10%vs13%), psychiatric illness(2%vs6%),poisoning and drug over dose(0.9%vs2.6%)(p<0.0001).The odds for referral(cOR 3.62,95% CI:2.70-4.84), Left against medical advice(cOR 6.03,95% CI:.06-8.94) and death(cOR 3.28,95% CI:1.64-6.68) increased during the covid respectively.
There was decrease in rates of emergency department utilization during the Covid-19 pandemic. Admissions due to trauma, gastrointestinal, respiratory, neurological, musculoskeletal and coronary artery disease showed a decline whereas psychiatric disorders, diabetes and hypertension, animal and insect bites cases increased. Overall, mortality rate was increased.