The American journal of emergency medicine
-
Artificial Intelligence (AI) models like GPT-3.5 and GPT-4 have shown promise across various domains but remain underexplored in healthcare. Emergency Departments (ED) rely on established scoring systems, such as NIHSS and HEART score, to guide clinical decision-making. This study aims to evaluate the proficiency of GPT-3.5 and GPT-4 against experienced ED physicians in calculating five commonly used medical scores. ⋯ While AI models demonstrated some level of concordance with human expertise, they fell short in emulating the complex clinical judgments that physicians make. The study suggests that current AI models may serve as supplementary tools but are not ready to replace human expertise in high-stakes settings like the ED. Further research is needed to explore the capabilities and limitations of AI in emergency medicine.
-
The goal of this study is to demonstrate the feasibility of referring patients for lung cancer screening (LCS) from the emergency department (ED) as a method to increase the uptake of LCS. ⋯ This pilot study suggests the feasibility and suggests initial indications of the efficacy of referring ED patients for LCS.
-
Ultrasound is an integral part of evaluating for acute cholecystitis and choledocholithiasis in pediatric patients. Finding the common bile duct (CBD), a structure which is normally <4 mm in children, can be very challenging. ⋯ The prevalence of isolated sonographic CBD dilation in pediatric patients with cholecystitis and/or choledocholithiasis was 1.1%. Thus, biliary ultrasound without CBD measurement is unlikely to result in missed cholecystitis and/or choledocholithiasis if the biliary ultrasound does not demonstrate GWT, PCF, SMS, or choledocholithiasis, and the patient has normal laboratory values.
-
The European Society of Cardiology (ESC) 0/1-h high sensitivity troponin T (hs-cTnT) algorithm does not differentiate risk based on known coronary artery disease (CAD: prior myocardial infarction [MI], coronary revascularization, or ≥ 70% coronary stenosis). We recently evaluated its performance among patients with known CAD at 30-days, but little is known about its longer-term risk prediction. The objective of this study is to determine and compare the performance of the algorithm at 90-days among patients with and without known CAD. ⋯ Patients with known CAD who were ruled-out using the ESC 0/1-h hs-cTnT algorithm had a high rate of missed 90-day cardiac events, suggesting that the ESC 0/1-h hs-cTnT algorithm may not be safe for use among patients with known CAD.