This study systematically evaluated the performance of three advanced large language models (LLMs)—GPT-4.0, ERNIE Bot 4.0, and GPT-4o—in the 2023 Chinese Medical Licensing Examination. Employing a dataset of 600 standardized questions, we analyzed the accuracy of each model in answering questions from three comprehensive sections: Basic Medical Comprehensive, Clinical Medical Comprehensive, and Humanities and Preventive Medicine Comprehensive. Our results demonstrate that both ERNIE Bot 4.0 and GPT-4o significantly outperformed GPT-4.0, achieving accuracies above the national pass mark. The study further examined the strengths and limitations of each model, providing insights into their applicability in medical education and potential areas for future improvement. These findings underscore the promise and challenges of deploying LLMs in multilingual medical education, suggesting a pathway towards integrating AI into medical training and assessment practices.

Introduction: The surgical anatomy of the right upper lobe pulmonary vein is variable and rare anomalies often go unnoticed in the first intraoperative exposure. Methods: 3D-CTBA reconstructions were performed on 307 right-sided contrast-enhanced chest CT data with full segmentation of the arterial, venous and bronchial systems. Results: Anomalous right upper lobe vein anatomy was detected in 23 cases (7.49%) consisting of 18 right top pulmonary veins (RTPVs) and 5 cases of proposed cranially displaced central vein (CDCV). In all 18 RTPVs, a single venous trunk collecting S2 drainage followed a retrobronchial course posterior to the right main bronchus or bronchus intermedius. Thirteen drained directly into left atrium. The other five had translobar confluence with the inferior pulmonary vein system; one drained first into V6 before joining the inferior pulmonary vein. Surgically relevant arterial anomalies were concentrated in the RTPV subgroup. A central vein configuration was also identified, in which the venous trunk coursed in the interval between B1 and the adjacent roots of B2 and B3, consistently more cranial than expected. This pattern is called the cranially displaced central vein (CDCV). Discussion: Recognizing these precise anatomical configurations via preoperative 3D-CTBA is essential to avoid unexpected intraoperative hemorrhage during thoracic procedures.