Academic emergency medicine : official journal of the Society for Academic Emergency Medicine
-
Pediatric patients attended to by emergency medical services (EMS) but not transported to the hospital are an at-risk population. We aimed to evaluate risk factors associated with nontransport by EMS in pediatric patients. ⋯ Pediatric nontransports are associated with traumatic, respiratory, and toxicologic complaints and older age. These findings can facilitate development of refusal protocols and research on outcomes of these at-risk patients.
-
Pediatric emergency care research networks have evolved substantially over the past two decades. Some networks are specialized in specific areas (e.g., sedation, simulation) while others study a variety of medical and traumatic conditions. Given the increased collaboration between pediatric emergency research networks, the logical next step is the development of a research priorities agenda to guide global research in emergency medical services for children (EMSC). ⋯ The identification of pediatric emergency care network research priorities within the domains of clinical care, technology, knowledge translation and organization/administration of EMSC will facilitate and help focus collaborative research within and among research networks globally. Engagement of essential stakeholders including EMSC researchers, policy makers, patients, and their caregivers will stimulate advances in the delivery of emergency care to children around the globe.
-
Appointment of a pediatric emergency care coordinator (PECC) is considered the single best intervention to improve pediatric emergency care and has been recommended for all U.S. general emergency departments (EDs) for more than a decade. Unfortunately, many EDs do not adhere with this recommendation. In 2017, we performed a grassroots intervention to establish a PECC in every Massachusetts ED. ⋯ Through a relatively simple grassroots intervention, we increased the appointment of PECCs in Massachusetts EDs from 30% to 100%. In addition to providing PECCs with online educational materials, ongoing work is focused on building community, identifying best practices, and implementing interventions at the local level.
-
Pediatric asthma is a leading cause of emergency department (ED) utilization and hospitalization. Earlier identification of need for hospital-level care could triage patients more efficiently to high- or low-resource ED tracks. Existing tools to predict disposition for pediatric asthma use only clinical data, perform best several hours into the ED stay, and are static or score-based. Machine learning offers a population-specific, dynamic option that allows real-time integration of available nonclinical data at triage. Our objective was to compare the performance of four common machine learning approaches, incorporating clinical data available at the time of triage with information about weather, neighborhood characteristics, and community viral load for early prediction of the need for hospital-level care in pediatric asthma. ⋯ Three of the four machine learning models performed well with decision trees preforming the worst. The gradient boosting machines model demonstrated a slight advantage over other approaches at predicting need for hospital-level care at the time of triage in pediatric patients presenting with asthma exacerbation. The addition of weight, SES, and weather data improved the performance of this model.