Academic emergency medicine : official journal of the Society for Academic Emergency Medicine
-
Reliably abstracting outcomes from free-text electronic health records remains a challenge. While automated classification of free text has been a popular medical informatics topic, performance validation using real-world clinical data has been limited. The two main approaches are linguistic (natural language processing [NLP]) and statistical (machine learning). The authors have developed a hybrid system for abstracting computed tomography (CT) reports for specified outcomes. ⋯ A hybrid NLP and machine learning automated classification system shows promise in coding free-text electronic clinical data.
-
Studies focusing on minor head injury in intoxicated patients report disparate prevalences of intracranial injury. It is unclear if the typical factors associated with intracranial injury in published clinical decision rules for computerized tomography (CT) acquisition are helpful in differentiating patients with and without intracranial injuries, as intoxication may obscure particular features of intracranial injury such as headache and mimic other signs of head injury such as altered mental status. This study aimed to estimate the prevalence of intracranial injury following minor head injury (Glasgow Coma Scale [GCS] score ≥14) in intoxicated patients and to assess the performance of established clinical decision rules in this population. ⋯ In this study, the prevalence of clinically important injury in intoxicated patients with minor head injury was significant. While the presence of the common features associated with intracranial injury in nonintoxicated patients should raise clinical suspicion for intracranial injury in intoxicated patients, the Canadian CT Head Rule and NEXUS criteria do not have adequate sensitivity to be applied in intoxicated patients with minor head injury.
-
Severe sepsis remains a major public health problem both with a high hospital mortality rate and with staggering associated health care expenditures. The past decade has seen new insights into the early resuscitation of severe sepsis and this is an important, controversial, and constantly changing topic to emergency physicians. ⋯ As summarized in this article, the best available experimental evidence suggests that lactate clearance of at least 10% at a minimum of 2 hours after resuscitation initiation is a valid way to assess initial response to resuscitation in severe sepsis. Associative data suggest that lactate normalization during resuscitation is a more powerful indicator of resuscitative adequacy; however, further research on the optimal lactate clearance parameters to use during resuscitation is needed, and many other important questions have yet to be answered.
-
Barcode-assisted medication administration (BCMA) is technology with demonstrated benefit in reducing medication administration errors in hospitalized patients; however, it is not routinely used in emergency departments (EDs). EDs may benefit from BCMA, because ED medication administration is complex and error-prone. ⋯ Implementing BCMA in the ED was associated with significant reductions in the medication administration error rate and specifically wrong dose errors. The results of this study suggest a benefit of BCMA on reducing medication administration errors in the ED.
-
Multicenter Study Observational Study
Evaluating Current Patterns of Assessment for Self-harm in Emergency Departments: A Multicenter Study.
The objective was to describe self-harm assessment practices in U.S. emergency departments (EDs) and to identify predictors of being assessed. ⋯ Emergency department assessment of self-harm was highly variable among institutions. Presence of specific assessment policies was associated with higher assessment rates. Assessment varied based upon patient characteristics. The identification of self-harm in 2.7% of ED patients indicates that a substantial proportion of current risk of self-harm may go unidentified, particularly in certain patient groups.