Articles: emergency-department.
-
To assess whether a general emergency department's (ED) annual pediatric sepsis volume increases the odds of delivering care concordant with Surviving Sepsis pediatric guidelines. ⋯ Guideline-concordant sepsis care was delivered in 41% of pediatric sepsis cases in general EDs, and annual ED pediatric sepsis encounters had minimal association with the odds of concordant care. Care concordance improved over time. This study suggests that factors other than pediatric sepsis volume are important in driving care quality and identifying drivers of improvement is important for children first treated in general EDs.
-
There is increasing interest in harnessing artificial intelligence to virtually triage patients seeking care. The objective was to examine the reliability of a virtual machine learning algorithm to remotely predict acuity scores for patients seeking emergency department (ED) care by applying the algorithm to retrospective ED data. ⋯ This machine learning algorithm needs further refinement before being safely implemented for patient use.
-
In recent years, the academic medicine community has produced numerous statements and calls to action condemning racism. Though health equity work examining health disparities has expanded, few studies specifically name racism as an operational construct. As emergency departments serve a high proportion of patients with social and economic disadvantage rooted in structural racism, it is critically important that racism be a focus of our academic discourse. This study examines the frequency at which four prominent emergency medicine journals, Annals of Emergency Medicine, Academic Emergency Medicine, the American Journal of Emergency Medicine, and the Western Journal of Emergency Medicine, publish on health disparities and racism. ⋯ Our findings suggest that the national discourse on racism and calls to action within emergency medicine were followed by an increase in publications on health disparities and racism. Continued investigation is needed to evaluate these trends moving forward.
-
Observational Study
Assessing the precision of artificial intelligence in emergency department triage decisions: Insights from a study with ChatGPT.
The rise in emergency department presentations globally poses challenges for efficient patient management. To address this, various strategies aim to expedite patient management. Artificial intelligence's (AI) consistent performance and rapid data interpretation extend its healthcare applications, especially in emergencies. The introduction of a robust AI tool like ChatGPT, based on GPT-4 developed by OpenAI, can benefit patients and healthcare professionals by improving the speed and accuracy of resource allocation. This study examines ChatGPT's capability to predict triage outcomes based on local emergency department rules. ⋯ Our findings suggest GPT-4 possess outstanding predictive skills in triaging patients in an emergency setting. GPT-4 can serve as an effective tool to support the triage process.
-
Approximately 1 in 100 postpartum individuals visit an emergency department (ED) for a psychiatric reason. Repeat visits can signify problems with the quality of care received during or after the initial visit; this study aimed to understand risk for repeat postpartum psychiatric ED visits. ⋯ Over 1 in 10 postpartum psychiatric ED visits are followed by a repeat visit within 30 days. Targeted approaches are needed across clinical populations to reduce repeat ED visits in this population with young infants.