Emergency medicine Australasia : EMA
-
Emerg Med Australas · Feb 2024
End-of-life care: A retrospective cohort study of older people who died within 48 hours of presentation to the emergency department.
To describe the characteristics of, and care provided to, older people who died within 48 h of ED presentation. ⋯ Identification of patients at end-of-life (EoL) is not always straightforward; consider recent reduction in independence and recent ED visits/hospital admissions. System-based strategies that span pre-hospital, ED and in-patient care are recommended to facilitate EoL pathway implementation and care continuity.
-
Emerg Med Australas · Feb 2024
Paediatric diabetes-related presentations to emergency departments in Victoria, Australia from 2008 to 2018.
Despite significant treatment advances in paediatric diabetes management, ED presentations for potentially preventable (PP) complications such as diabetic ketoacidosis (DKA) remains a major issue. We aimed to examine the characteristics, rates and trends of diabetes-related ED presentations and subsequent admissions in youth aged 0-19 years from 2008 to 2018. ⋯ Although the rates of diabetes-related ED presentations declined, PP diabetes-related presentations and subsequent hospitalisation remain high. Patient level research is required to understand the increased DKA presentations in rural youth.
-
Emerg Med Australas · Feb 2024
Machine learning in clinical practice: Evaluation of an artificial intelligence tool after implementation.
Artificial intelligence (AI) has gradually found its way into healthcare, and its future integration into clinical practice is inevitable. In the present study, we evaluate the accuracy of a novel AI algorithm designed to predict admission based on a triage note after clinical implementation. This is the first of such studies to investigate real-time AI performance in the emergency setting. ⋯ Our study showed the diagnostic evaluation of a real-time AI clinical decision-support tool became less accurate than the original. Although real-time sensitivity and specificity of the AI tool was still acceptable as a decision-support tool in the ED, we propose that continuous training and evaluation of AI-enabled clinical support tools in healthcare are conducted to ensure consistent accuracy and performance to prevent inadvertent consequences.