Background: Deepseek-R1, an open-source large language model (LLM), has generated significant global interest in the past months. Objective: This study aimed to compare the performance of DeepSeek and OpenAI LLMs on the Chinese National Medical Licensing Examination (NMLE) and evaluate their potential in medical education. Methods: This cross-sectional study assessed 2 DeepSeek models (DeepSeek-R1 and DeepSeek-V3), 3 OpenAI models (ChatGPT-o1 pro, ChatGPT-o3 mini, and GPT-4o), and 2 additional Chinese LLMs (ERNIE 4.5 Turbo and Qwen 3) using the 2021 NMLE. Model performance was evaluated based on overall accuracy, accuracy across question types (A1, A2, A3 and A4, and B1), case analysis and non–case analysis questions, medical specialties, and accuracy consensus between different model combinations. Results: All LLMs successfully passed the NMLE. DeepSeek-R1 achieved the highest accuracy (573/597, 96%), followed by DeepSeek-V3 (558/600, 93%), both of which significantly outperformed ChatGPT-o1 pro (450/600, 75%), ChatGPT-o3 mini (455/600, 75.8%), and GPT-4o (452/600, 75.3%; P<.001 for all comparisons). Performance disparities were consistent across various question types (A1, A2, A3 and A4, and B1), case analysis and non–case analysis questions, different types of case analyses, and medical specialties. The accuracy consensus between DeepSeek-R1 and DeepSeek-V3 reached 97.7% (544/557), significantly outperforming DeepSeek-R1 alone (P=.04). Two additional Chinese LLMs, ERNIE 4.5 Turbo (572/600, 95.3%) and Qwen 3 (555/600, 92.5%), also exhibited significantly better performance compared to the 3 OpenAI models (all P<.001). Conclusions: This study demonstrates that DeepSeek-R1 and DeepSeek-V3 significantly outperform OpenAI models on the NMLE. DeepSeek models show promise as tools for medical education and exam preparation in the Chinese language.

Purpose: To validate the 2018 revised FIGO cervical cancer staging system for stage III patients with a cohort from China. Patients and Methods: Patients with stage III cervical cancer (FIGO 2018) treated with definitive radiotherapy at our institute were reviewed. Each patient was evaluated with both the 2014 and 2018 staging systems. Disease-free survival (DFS) was calculated with the Kaplan-Meier method. Receiver operative characteristic (ROC) curves for the predictive accuracy of DFS in patients with cervical cancer according to different FIGO staging systems were created. Results: Between January 2008 and December 2014, a total of 586 patients with FIGO stage IIIC cervical cancer (2018) were treated with definitive radiotherapy at our institute. The 3-year DFS for patients according to FIGO stage (2014) were as follows: IB2 73.2%, IIA 63.7%, IIB 66.7%, IIIA 64.7%, and IIIB 59.6% (P=0.580). The 3-year DFS according to FIGO stage (2018) were IIIA 79.9%, IIIB 70.4%, IIIC1 66.3% and IIIC2 29.8% (P< 0.001). The AUC values for DFS were 0.552 (95% CI: 0.503– 0.600, P=0.037) and 0.623 (95% CI: 0.575– 0.671, P< 0.001) for the 2014 and 2018 FIGO staging systems, respectively. Conclusion: The 2018 FIGO staging system of cervical cancer showed more distinction within stages and better predictive accuracy for DFS than the preceding staging system in patients with stage III disease from China.

The multifactorial nature of Alzheimer’s disease (AD) calls for the development of multitarget agents addressing key pathogenic processes. A total of 26 Claulansine F–donepezil hybrids were designed and synthesized as multitarget drugs. Among these compounds, six compounds exhibited excellent acetylcholinesterase (AChE) inhibitory activity (half maximal inhibitory concentration (IC₅₀) 1.63–4.62 μM). Moreover, (E)-3-(8-(tert-Butyl)-3,3-dimethyl-3,11-dihydropyrano[3,2-a]carbazol-5-yl)-N-((1-(2-chlorobenzyl)piperidin-4-yl)methyl)acrylamide (6bd) exhibited better neuroprotective effects against OGD/R (oxygen–glucose deprivation/reoxygenation) than lead compound Claulansine F. Furthermore, 6bd could cross the blood–brain barrier in vitro. More importantly, compared to edaravone, 6bd had stronger free-radical scavenging activity. Molecular docking studies revealed that 6bd could interact with the catalytic active site of AChE. All of these outstanding in vitro results indicate 6bd as a leading structure worthy of further investigation.