OBJECTIVE To evaluate the clinical comprehensive value of four Chinese patent medicines （Xuezhikang， Zhibitai， Zhibituo， Jiangzhiling） in the treatment of hyperlipidemia， and provide a reference for rational clinical drug use. METHODS A clinical comprehensive evaluation index system was established in accordance with the Evidence and Value： Impact on Decision-Making （EVIDEM） framework and Technical Guideline for Clinical Comprehensive Evaluation of Cardiovascular Drugs （2022 edition， trial implementation）. CNKI， Wanfang data， VIP， PubMed， ScienceDirect， Embase and official websites were retrieved to collect the literature such as drug instructions， guidelines and consensus statements， and systematic reviews/meta-analyses for the four Chinese patent medicines. A comprehensive evaluation was conducted from seven dimensions： effectiveness， safety， economy， suitability， accessibility， innovation and characteristics of traditional Chinese medicine. RESULTS This evaluation index system included 7 first-level indicators， 15 second-level indicators and 30 third-level indicators. Xuezhikang achieved the highest comprehensive evaluation score of 81.4 points， and was classified as class Ⅰ recommendation. Zhibitai with 76.0 points and Zhibituo with 60.9 points were both classified as class Ⅱ recommendation. Jiangzhiling with 48.8 points was classified as class Ⅳ recommendation. CONCLUSIONS Xuezhikang demonstrates the optimal clinical comprehensive value for treating hyperlipidemia. Zhibitai exhibits certain advantages in terms of safety and characteristics of traditional Chinese medicine； Zhibituo shows a moderate performance in all aspects； Jiangzhiling has a relatively low score. Appropriate medicines can be selected clinically according to actual conditions and patients’ characteristics.

Objective To evaluate the performance of lightweight Chinese large language models (LLMs) in answering specialized lung cancer questions, and to explore the impact of retrieval-augmented generation (RAG) on model performance. Methods Eleven lightweight Chinese LLMs with parameter sizes ranging from 7B to 32B were included. A lung cancer-specific evaluation dataset consisting of 200 questions [100 A1-type (basic knowledge) and 100 A2-type (clinical case) questions], constructed based on clinical guidelines and thoracic surgery textbooks, was used for assessment. Model performance was evaluated under two conditions (with and without RAG). Accuracy was used to assess model performance, and response latency was recorded to reflect inference efficiency. An accuracy–latency scatter plot was constructed for descriptive analysis of overall model performance. Results All models successfully completed the evaluation. With the introduction of RAG, the overall average accuracy improved from 61.68% to 76.36%. Smaller models demonstrated the most significant improvement (e.g., the accuracy of DeepSeek-7B increased from 32.50% to 60.00%, P<0.001). The average response latency increased from 12.58 s to 13.80 s. The Qwen3 series showed the best overall performance, and Qwen3-32B achieved the highest accuracy under both conditions (76.50% and 84.00%, respectively). After RAG integration, performance differences among model families were markedly reduced. Based on the accuracy-latency trade-off, Qwen3-32B achieved the best balance between accuracy and response latency under the baseline condition, whereas Qwen3-14B demonstrated superior overall performance in terms of accuracy, latency, and computational cost after RAG integration. Conclusion The integration of RAG technology improves the ability of lightweight Chinese LLMs to answer specialized lung cancer questions. Under the dual practical constraints of limited computational resources and medical data security requirements, the "lightweight model+RAG" technical framework may represent a promising deployment solution.

Objective To explore the reasonable radiologic nodal size criterion of retropharyngeal lymph node (RLN) metastasis in patients with nasopharyngeal cancer (NPC).Methods Imaging and clinical data of 817 NPC patients were analyzed retrospectively.The patients with RLN metastasis were classified into two groups according to the nodal size of 5 mm or 6 mm as standard in diagnosis.Overall survival (OS),distant metastasis-free survival (DMFS) and the local-relapse-free survival (LRFS) were assessed between the two groups taking 5 mm or 6 mm as standard in diagnosis of RLN.Results No significant difference was found for OS,DMFS,LRFS between nodal size ＜5 mm group and ≥5 mm group.Difference of OS (P＜0.001),DMFS (P=0.001) were significant statistical and difference of LRFS (P=0.380) had no significant statistical between nodal size ＜6 mm group and ≥6 mm group.OS,DMFS,LRFS were not an independent prognostic factor for NPC.Conclusion Using the minimal axial diameter of 6 mm as the nodal size criterion in diagosis of RLN metastasis in patients with NPC may be more reasonable.