The American journal of emergency medicine
-
The number of emergency department (ED) visits has been on steady increase globally. Artificial Intelligence (AI) technologies, including Large Language Model (LLMs)-based generative AI models, have shown promise in improving triage accuracy. This study evaluates the performance of ChatGPT and Copilot in triage at a high-volume urban hospital, hypothesizing that these tools can match trained physicians' accuracy and reduce human bias amidst ED crowding challenges. ⋯ ChatGPT and Copilot outperform traditional nurse triage in identifying high-acuity patients, but real-time ED capacity data is crucial to prevent overcrowding and ensure high-quality of emergency care.
-
Neutropenia is defined as an absolute neutrophil count (ANC) < 1500 cells/microL and may be discovered incidentally in an asymptomatic, afebrile patient. ⋯ Understanding the approach to incidental neutropenia can improve patient care. Critically ill or febrile patients should be admitted, but select patients may be discharged.
-
To evaluate the comparative effectiveness of fentanyl and ketamine via Breath Actuated Nebulizer (BAN) for analgesia in the prehospital setting. ⋯ We found no statistically significant difference in the analgesic treatment effect for the overall fentanyl and ketamine groups. Subgroup analysis of patients treated for traumatic pain showed greater analgesia for ketamine via BAN over fentanyl. Given the ease of administration and lack of need for intravenous access, ketamine via BAN is a reasonable and effective choice for prehospital pain management.