Academic emergency medicine : official journal of the Society for Academic Emergency Medicine
-
Review Meta Analysis
Using natural language processing in emergency medicine health service research: A systematic review and meta-analysis.
Natural language processing (NLP) represents one of the adjunct technologies within artificial intelligence and machine learning, creating structure out of unstructured data. This study aims to assess the performance of employing NLP to identify and categorize unstructured data within the emergency medicine (EM) setting. ⋯ Our analysis revealed a generally favorable performance accuracy in using NLP within EM research, particularly in the realm of radiologic interpretation. Consequently, we advocate for the adoption of NLP-based research to augment EM health care management.
-
The aim of this study was to describe the incidence of brief resolved unexplained events (BRUEs) and compare the impact of a national clinical practice guideline (CPG) on admission and diagnostic testing practices between general and pediatric emergency departments (EDs). ⋯ BRUEs remain a common pediatric problem at a population level and in EDs. Although a disproportionate number of infants present to general EDs, there is differential uptake of the CPG recommendations between pediatric and general EDs. These findings may support quality improvement opportunities aimed at improving care for these infants and decreasing unnecessary hospital admissions or transfers.
-
Timely administration of systemic corticosteroids is a cornerstone of asthma exacerbation treatment, yet little is known regarding potential benefits of prehospital administration by emergency medical services (EMS) clinicians. We examined factors associated with prehospital corticosteroid administration with hospitalization and hospital length of stay (LOS). ⋯ Prehospital systemic corticosteroid administration was not associated with hospitalization or LOS in the overall cohort of asthma patients treated by EMS, though they had a lower probability of admission within Bayesian models. Improved outcomes were noted among subgroups of longer EMS encounters, documented wheezing, and receipt of albuterol.
-
To combat increasing levels of violence in the emergency department (ED), hospitals have implemented several safety measures, including behavioral flags. These electronic health record (EHR)-based notifications alert future clinicians of past incidents of potentially threatening patient behavior, but observed racial disparities in their placement may unintentionally introduce bias in patient care. Little is known about how patients perceive these flags and the disparities that have been found in their placement. ⋯ Patient perspectives on the use of behavioral flags in the ED vary. While many saw flags as a helpful tool to mitigate violence, concerns around negative impacts on care, transparency, and equity were also shared. Insights from this stakeholder perspective may allow for health systems to make flags more effective without compromising equity or patient ideals.
-
Federal regulations allow exception from informed consent (EFIC) to study emergent conditions when obtaining prospective consent is not feasible. Little is known about public views on including children in EFIC studies. The Pediatric Dose Optimization for Seizures in EMS (PediDOSE) trial implements age-based, standardized midazolam dosing for pediatric seizures. The primary objective of this study was to determine public support for and concerns about the PediDOSE EFIC trial. The secondary objective was to assess how support for PediDOSE varied by demographics. ⋯ In communities where this study will occur, most respondents supported PediDOSE being conducted with EFIC and most approved of children being enrolled without prior consent. Support was lowest among non-Hispanic Black respondents and highest among health care providers. Further research is needed to determine optimal ways to address the concerns of specific racial and ethnic groups when conducting EFIC trials.