Background/aim: This study evaluated the accuracy rates and response consistency of four different large language models (ChatGPT- 4o, Gemini 2.0, Claude 3.5, and DeepSeek R1) in answering questions from the Emergency Medicine Fellowship Examination (YDUS), which was administered for the first time in Türkiye. Materials and methods: In this observational study, 60 multiple-choice questions from the Emergency Medicine YDUS administered on 15 December 2024, were classified as knowledge-based (n = 26), visual content (n = 2), and case-based (n = 32). Each question was presented three times to the four large language models. The models’ accuracy rates were evaluated according to overall accuracy, strict accuracy, and ideal accuracy criteria. Response consistency was measured using Fleiss’ Kappa test. Results: The ChatGPT-4o model was the most successful in terms of overall accuracy (90.0%), while DeepSeek R1 showed the lowest performance (76.7%). Claude 3.5 (83.3%) and Gemini 2.0 (80.0%) demonstrated moderate success. When analyzed by category, ChatGPT-4o achieved the highest success with 92.3% accuracy in knowledge-based questions and 90.6% in case-based questions. In terms of response consistency, the Claude 3.5 model (Fleiss’ Kappa = 0.68) showed the highest consistency, while Gemini 2.0 (Fleiss’ Kappa = 0.49) showed the lowest. Inconsistent hallucinations were more frequent in the Gemini 2.0 and DeepSeek R1 models, whereas persistent hallucinations were less common in the ChatGPT-4o and Claude 3.5 models. Conclusion: Large language models can achieve high accuracy rates for knowledge and clinical reasoning questions in emergency medicine but show differences in terms of response consistency and hallucination tendency. While these models have significant potential for use in medical education and as clinical decision support systems (CDSS), they need further development to provide reliable, up-to-date, and accurate information.

Thoracic trauma is a significant cause of mortality, especially among those arriving at hospitals. This study explores the associations between mortality, the shock index (SI), and specific metabolic and biochemical markers in patients with isolated thoracic trauma. This retrospective cross-sectional study included all consecutive adult patients presenting with isolated thoracic trauma to a high-volume emergency department from January 2019 to December 2023. The predictive capability of SI levels and selected biomarkers upon admission for estimating mortality was assessed by determining the areas under the receiver operating characteristic curves (AUCs). Optimal cutoff values were determined using the Youden index method. The study involved 352 patients, with 285 (81%) being males and an average age of 50.0±17.7 years. The mortality rate was 9.6%. Mortality was significantly associated with higher shock index (odds ratio [OR]: 14.02, [95% confidence interval [CI] 0.847-0.916], AUC=0.885, p=0.001), glucose/potassium ratio (OR: 1.24 [95% CI 1.14-1.35], AUC=0.869, p<0.001), and lactate levels (OR: 4.30 [95% CI 2.29-8.07], AUC=0.832, p<0.001). The optimal cutoff values determined for the shock index, glucose/potassium ratio, ionized calcium, and lactate were 1.02 (sensitivity, 94.1%; specificity 69.5%; positive predictive value [PPV], 24.8; negative predictive value [NPV], 99.1), 36.85 (sensitivity, 76.5%; specificity, 87.7%; PPV, 40.0; NPV, 97.2), 1.23 (sensitivity, 94.1%; specificity, 56.0%; PPV, 18.6; NPV, 98.9), and 1.98 (sensitivity, 70.6%; specificity, 80.5%; PPV, 27.9; NPV, 96.2), respectively. This study demonstrates that higher shock index, glucose/potassium ratio, and lactate levels are significantly associated with increased mortality in patients with isolated thoracic trauma. These findings suggest that these markers can be effective prognostic indicators, potentially guiding clinical decision-making and improving patient outcomes.

Background: Crush syndrome is a life-threatening consequence of prolonged muscle compression, and acute kidney injury (AKI) is a major determinant of morbidity and mortality. Rapid AKI risk stratification at emergency department (ED) presentation remains challenging. We evaluated whether the lactate dehydrogenase-to-albumin ratio (LDAR) measured at ED admission could discriminate creatinine-defined AKI among patients with crush syndrome. Methods: We conducted a retrospective cohort study in the ED of a Level I trauma center from 1 January 2019 to 31 December 2025. Adults (≥ 18 years) meeting a predefined operational definition of crush syndrome, including traumatic compression injury, biochemical rhabdomyolysis, and compatible clinical or systemic features, were included. AKI was defined using serum creatinine-based Kidney Disease: Improving Global Outcomes criteria with a predefined approach for baseline creatinine determination. LDAR was calculated as admission lactate dehydrogenase divided by admission albumin. Discrimination was assessed using receiver operating characteristic (ROC) analysis with area under the curve (AUC) and 95% confidence intervals. Independent associations with AKI and RRT were examined using multivariable logistic regression. Results: Among 512 patients, 180 (35.2%) were classified as having creatinine-defined AKI; 374 (73.0%) were male. Hemodialysis was required in 78/180 (43.3%) patients with AKI, and in-hospital mortality was higher in patients with AKI (15.0% vs. 0.6%). Creatine kinase (CK) showed the highest discrimination for AKI (AUC 0.977, 95% CI 0.964–0.989), followed by LDAR (AUC 0.966, 95% CI 0.953–0.980). A Youden-derived LDAR cut-off of ≥ 23.59 yielded 86.7% sensitivity and 96.7% specificity. In addition, an LDAR cut-off of ≥ 22.68 predicted RRT requirement in patients with CS with 97.4% sensitivity and 77.6% specificity. Conclusions: LDAR measured at ED presentation showed high discrimination for AKI and RRT in crush syndrome. Although not a stand-alone treatment trigger, it may support early renal risk stratification when interpreted together with CK, renal function, electrolyte status, and clinical severity. Clinical trial number: Not applicable.