OBJECTIVES: We aimed to evaluate the performance of a large language model (ChatGPT) in answering official sample questions from the Turkish Board of Emergency Medicine (TBEM). Two versions of the model, GPT-4 and GPT-4o, were assessed to explore consistency and accuracy across iterations. METHODS: A cross-sectional observational study was conducted using 25 standardized multiple-choice questions publicly released by TBEM. Each question was manually entered into GPT-4 and GPT-4o through the OpenAI interface. Both models were prompted to select the best single answer from the provided options without additional clarification or training context. Model responses were evaluated for accuracy, consistency upon repetition, and domain-specific error types. This study is compliant with the STROBE statement and the MedinAI reporting guidelines. RESULTS: GPT-4 correctly answered 20 out of 25 questions (80%) on the first attempt. On repetition, its score improved to 84%. GPT-4o also achieved a score of 88% (22/25) on its first attempt and showed consistent results upon a second evaluation, providing identical answers in both trials. Errors occurred in the domains of trauma during pregnancy, pediatric resuscitation, and adult resuscitation protocols. Both models demonstrated strong performance in fact-based domains and in questions involving image descriptions. CONCLUSION: GPT-4 and GPT-4o performed above the TBEM passing threshold, showing solid accuracy across a range of emergency medicine topics. Both excelled in fact-based and image-related questions. However, they showed limitations in clinical reasoning, particularly in scenarios requiring nuanced judgment. These tools may support examination preparation but should not replace the expertise of trained emergency physicians.

Background: The prognosis of traumatic dental injuries (TDIs) is highly time-dependent, and emergency departments are often the first point of care. Despite the availability of International Association of Dental Traumatology (IADT) guidelines and validated standardized documentation tools, emergency physicians’ knowledge of and awareness of these recommendations remain unclear. This multicenter study therefore aimed to assess emergency physicians’ knowledge, self-perceived competence, self-reported clinical approaches, and awareness of standardized documentation in the management of traumatic dental injuries. The study also sought to evaluate physicians’ self-reported approaches and to identify physicians’ preferred approaches for future training and education. Methods: This cross-sectional study was conducted between November and December 2025 among physicians working in the emergency departments of 10 hospitals in İzmir, Türkiye (2 university hospitals, 3 training and research hospitals, and 5 state hospitals). Data were collected using a structured questionnaire developed in accordance with the IADT recommendations and the national clinical protocol of the Turkish Ministry of Health, covering demographic characteristics, self-perceived competence, eight items assessing TDI management knowledge and guideline-related awareness and preferred educational methods. Group comparisons were performed using the Kruskal–Wallis test, the Mann–Whitney U test, or one-way ANOVA, as appropriate. Multivariable linear regression was used to identify factors independently associated with the guideline-related knowledge and awareness score. Reporting followed the STROBE guidelines. Results: A total of 145 physicians participated (52.1% emergency medicine residents, 22.2% specialists, 25.7% general practitioners). Participants reported inadequate theoretical knowledge (66.2%), lack of practical skills (46.2%), and low awareness of validated standardized dental trauma documentation tools: 77.2% were unaware of any such system, and only 2.8% reported occasional use. Pronounced knowledge gaps were observed in avulsion management, intrusion injuries, and the use of structured documentation. Guideline-related knowledge and awareness scores differed significantly by professional status ( p = 0.009) and institution type ( p = 0.042), but not by years of experience. In multivariable analysis, specialist status remained an independent predictor of higher knowledge (adjusted β = 1.11; 95% CI, 0.36–1.85), whereas the association with institution type was attenuated. Hands-on workshops and emergency department decision-making protocols were the most preferred educational strategies. Conclusions: A persistent gap in guideline awareness and self-reported knowledge exists in the emergency management of TDIs, characterized by limited theoretical knowledge, low self-perceived competence, and minimal awareness of validated documentation tools, despite the international and national publication of evidence-based recommendations. Targeted implementation strategies including hands-on training, structured emergency department decision-making pathways, and the active integration of validated documentation systems into routine workflows may help support more consistent guideline-informed management of dental trauma.