The American journal of emergency medicine
-
Multicenter Study
Supervised classification techniques for prediction of mortality in adult patients with sepsis.
Sepsis mortality is still unacceptably high and an appropriate prognostic tool may increase the accuracy for clinical decisions. ⋯ Deep learning and AI are increasingly used as support tools in clinical medicine. Their performance in a syndrome as complex and heterogeneous as sepsis may be a new horizon in clinical research. SVM and ANN seem promising for improving sepsis classification and prognosis.
-
Despite the advantages of bone marrow transplantation (BMT), patients receiving this intervention visit the emergency department (ED) frequently and for various reasons. Many of those ED visits result in hospitalization, and the length of stay varies. ⋯ In our study, we have shown that BMT patients visit the ED frequently and many of those visits result in a short hospitalization. Our study showed that patients presenting with fever/chills are less likely to have a short hospitalization. We also showed a significant association between a short hospitalization and BMT patients without GvHD, with normal RR, normal T °C and a normal platelet count.
-
Children with traumatic head injury are often transferred from community Emergency Departments (ED) to a Pediatric Emergency Department (PED). The primary objective of this study was to describe the outcomes of minor head injury (MHI) transfers to a PED. The secondary objective was to report Computed Tomography (CT) utilization rates for MHI. ⋯ The majority of pediatric MHI transfers are discharged home following a subspecialty consultation and/or neuroimaging. Despite guidelines and a low incidence of ciTBI, CT utilization remains high in the intermediate and low risk MHI groups, especially in the community settings. Targeted interventions are needed to reduce the potentially avoidable transfers and low-value performance of CT in children with MHI.
-
While significant racial inequities in health outcomes exist in the United States, these inequities may also exist in healthcare processes, including the Emergency Department (ED). Additionally, gender has emerged in assessing racial healthcare disparity research. This study seeks to determine the association between race and the number and type of ED consultations given to patients presenting at a safety-net, academic hospital, which includes a level-one trauma center. ⋯ Future work should focus on both healthcare practice improvements, as well as explanatory and preventive research practices. Healthcare practice improvements can encompass development of appropriate racial bias trainings and institutionalization of conversations about race in medicine.