CJEM最新文献

Study objective: This study investigates the potential to improve emergency department (ED) triage using machine learning models by comparing their predictive performance with the Canadian Triage Acuity Scale (CTAS) in identifying the need for critical care within 12 h of ED arrival.

Methods: Three machine learning models (LASSO regression, gradient-boosted trees, and a deep learning model with embeddings) were developed using retrospective data from 670,841 ED visits to the Jewish General Hospital from June 2012 to Jan 2021. The model outcome was the need for critical care within the first 12 h of ED arrival. Metrics, including the areas under the receiver-operator characteristic curve (ROC) and precision-recall curve (PRC) were used for performance evaluation. Shapley additive explanation scores were used to compare predictor importance.

Results: The three machine learning models (deep learning, gradient-boosted trees and LASSO regression) had areas under the ROC of 0.926 ± 0.003, 0.912 ± 0.003 and 0.892 ± 0.004 respectively, and areas under the PRC of 0.27 ± 0.01, 0.24 ± 0.01 and 0.23 ± 0.01 respectively. In comparison, the CTAS score had an area under the ROC of 0.804 ± 0.006 and under the PRC of 0.11 ± 0.01. The predictors of most importance were similar between the models.

Conclusions: Machine learning models outperformed CTAS in identifying, at the point of ED triage, patients likely to need early critical care. If validated in future studies, machine learning models such as the ones developed here may be considered for incorporation in future revisions of the CTAS triage algorithm, potentially improving discrimination and reliability.

Background: ECGs performed at ED triage are mandatorily assessed by an emergency physician contributing to task interruptions, decreased quality of care and increased error risk. Recent literature suggests that a triage ECG interpreted as normal by the ECG machine software correlates with benign interpretation from attending cardiologists. Ambiguity persists regarding the safety of the normal computerized ECG interpretation and whether real-time physician review is needed.

Methods: In this prospective cohort study, we evaluated the GE Marquette 12SL ECG software's clinical accuracy for normal triage ECGs. We compared machine interpretation, ED physicians' real-time interpretation and management as well as cardiologists systematic but delayed review of the ECGs to establish diagnostic accuracy and safety of a normal software interpretation. Additional data were collected from the emergency department patient tracking system and charts to determine patient outcomes when machine normal interpretation differed from ED physicians and cardiologists' analysis.

Results: Between November 16th 2020 and November 19th 2021, we collected 1220 machine-normal ECGs performed at Charles-Le Moyne Hospital ED triage. 1051 ECGs were eligible for inclusion. ED physicians agreed with the machine for 1028 normal diagnoses (97.8% IC (0.95): 96.7-98.5) and cardiologists agreed with the machine for 1037 ECGs (98.7% IC (0.95) 97.8-99.2). Relevant changes in ED management were recorded in three patients (0.29% IC (0.95): 0.1-0.8) whose ECGs were read as normal by the software: two emergent referrals to the catheterization lab and one emergent transfer to the resuscitation bay with next day coronarography.

Conclusion: A normal ECG interpretation from the GE Marquette 12SL ECG software at ED triage has a very high accuracy and a very low probability of clinically relevant change in patient outcome and ED trajectory.

Objective: Our meta-analysis aimed to evaluate the safety of procedural sedation and analgesia in pediatric emergency department (ED) settings by investigating the incidence of cardiac, respiratory, gastrointestinal, and neurological adverse events associated with different sedation medications.

Methods: In accordance with PRISMA guidelines, a comprehensive database search for randomized controlled trials was performed across ten databases from January 2005 to June 2024. Our inclusion criteria included randomized controlled trials involving children under 18 years old undergoing pediatric sedation and analgesia in the ED. Data on medication types, dosages, administration routes, and adverse events were extracted and analyzed. Primary endpoints included cardiac, respiratory, gastrointestinal, and neurological adverse events.

Results: Seventeen studies met the inclusion criteria, a total of 2,302 procedural sedations. The most common adverse events were vomiting, agitation, and hypoxia, which occurred in 104.9 [95% CI = 76.9-132.9], 37.5 [95% CI = 20.6-54.4], 38.3 [95% CI = 23.9-52.6] of each 1000 sedations, respectively. Other adverse events included apnea, hypotension, and the need for bag-valve mask ventilation, which occurred in 8.6 [95% CI: 3.5-13.6], 9.3 [95% CI: -1.4 to 20.1], and 13.5 [95% CI: 3.2-23.8] of each 1,000 sedations, respectively. Severe adverse events were rare, with no reported instances of intubation and only one case of laryngospasm. Subgroup analyses revealed varying incidence rates of adverse events across different sedation protocols, with ketamine and its combinations showing higher rates of specific respiratory complications.

Conclusions: Procedural sedation in pediatric EDs is generally safe, with a low incidence of adverse events, such as vomiting, agitation, and hypoxia. Life-threatening respiratory adverse events are extremely rare. Our findings thus support the careful selection and monitoring of sedation protocols to minimize risks.

Introduction: Nonconvulsive status epilepticus is a severe complication of lithium intoxication that requires prompt diagnosis and treatment. While conventional electroencephalography (EEG) remains the gold standard for diagnosis for nonconvulsive status epilepticus, its implementation in emergency settings can be challenging and time-consuming. We present a case in which simplified EEG with six electrodes enabled rapid detection and monitoring of nonconvulsive status epilepticus in lithium intoxication in the emergency setting.

Case presentation: A 65-year-old woman with stable bipolar disorder presented to our emergency department with impaired consciousness. She had been maintained on lithium carbonate (1600 mg daily) and carbamazepine (400 mg daily) for over 10 years. Following two weeks of nausea and recent onset of agitation and slurred speech, she developed generalized convulsions. Laboratory examinations revealed elevated serum lithium (3.88 mEq/L) and acute renal dysfunction (creatinine 347.5 μmol/L). After resolving initial convulsions, a simplified sixelectrode EEG (Neurofax EEG-1250, Nihon Kohden Corporation, Tokyo, Japan), applied by an emergency physician, demonstrated generalized spike and wave patterns consistent with nonconvulsive status epilepticus. Despite initial seizure control with midazolam during intubation, continuous EEG monitoring revealed recurrent nonconvulsive status epilepticus. After hemodialysis and continued deep sedation, she was discharged on day 40 without neurological sequelae.

Discussion: This case demonstrates the utility of simplified EEG in emergency settings for early detection and monitoring of nonconvulsive status epilepticus in lithium intoxication. The ability of emergency physicians to apply and interpret simplified EEG enabled timely intervention and prevention of neurological complications. While further research is needed to validate interpretation protocols by non-EEG specialists, simplified EEG shows promise as an accessible tool for rapid assessment of neurotoxicity in lithium intoxication, potentially improving patient outcomes through earlier intervention.

Purpose: This study aimed to understand current prehospital trauma air-ambulance policies and triage guidelines across Canada. The research question centered on understanding the guidelines used by provinces and territories and identifying potential regional variations in air-ambulance triage.

Methods: We conducted a cross-sectional survey from November 2022 to May 2023, involving trauma leaders from Canada's 13 provinces and territories. Participants were identified via the Trauma Association of Canada and professional networks. The survey, developed with expert input and pilot tested for clarity, focused on prehospital trauma-triage guidelines, level of adoption of Center for Disease Control and Prevention (CDC) triage guidelines, and auto-launch air-ambulance policies. Data were collected using an 18-item electronic survey. Potential response bias was considered, and confidentiality was maintained. A cross-sectional qualitative analysis was used to evaluate the guidelines' adoption and variations, with responses compared across regions.

Results: The analysis revealed a nationwide adoption (11 of 11 respondents) of the CDC guidelines, indicating a standardized approach to patient transportation. Notably, many provinces and territories (5 of 11) endorse auto-launch protocols for air ambulances in specific scenarios. These policies offer advantages in geographically vast regions weighed against the cost of over-triage and inefficient resource allocation. Each province and territory tailors its approach based on factors such as geographic areas served, and available resources.

Conclusion: This study provides a snapshot of the current state of prehospital trauma-triage guidelines in Canada. With some differences in nomenclature, Canadian provinces and territories widely apply the CDC guidelines to serve their populations. There is some regional variation on how transport is initiated within their borders. The findings underscore the delicate balance required for optimizing air-ambulance policies, considering factors such as timely access, resource allocation, and the local application of guidelines.