Objective: To investigate methods for constructing a high-quality instructional dataset for traditional Chinese medicine (TCM) mental disorders and to validate its efficacy. Methods: We proposed the Fine-Med-Mental-T&P methodology for constructing high-quality instruction datasets in TCM mental disorders. This approach integrates theoretical knowledge and practical case studies through a dual-track strategy. (i) Theoretical track: textbooks and guidelines on TCM mental disorders were manually segmented. Initial responses were generated using DeepSeek-V3, followed by refinement by the Qwen3-32B model to align the expression with human preferences. A screening algorithm was then applied to select 16 000 high-quality instruction pairs. (ii) Practical track: starting from over 600 real clinical case seeds, diagnostic and therapeutic instruction pairs were generated using DeepSeek-V3 and subsequently screened through manual evaluation, resulting in 4 000 high-quality practice-oriented instruction pairs. The integration of both tracks yielded the Med-Mental-Instruct-T&P dataset, comprising a total of 20 000 instruction pairs. To validate the dataset’s effectiveness, three experimental evaluations (both manual and automated) were conducted: (i) comparative studies to compare the performance of models fine-tuned on different datasets; (ii) benchmarking to compare against mainstream TCM-specific large language models (LLMs); (iii) data ablation study to investigate the relationship between data volume and model performance. Results: Experimental results demonstrate the superior performance of T&P-model fine-tuned on the Med-Mental-Instruct-T&P dataset. In the comparative study, the T&P-model significantly outperformed the baseline models trained solely on self-generated or purely human-curated baseline data. This superiority was evident in both automated metrics (ROUGE-L > 0.55) and expert manual evaluations (scoring above 7/10 across accuracy). In benchmark comparisons, the T&P-model also excelled against existing mainstream TCM LLMs (e.g., HuatuoGPT and ZuoyiGPT). It showed particularly strong capabilities in handling diverse clinical presentations, including challenging disorders such as insomnia and coma, showcasing its robustness and versatility. Data ablation studies showed that T&P-model performance had an overall upward trend with minor fluctuations when training data increased from 10% to 50%; beyond 50%, performance improvement slowed significantly, with metrics plateauing and approaching a saturation point. Conclusion This study has successfully constructed the specialized Med-Mental-Instruct-T&P instruction dataset for TCM mental disorders proposed the systematic Fine-Med-Mental-T&P methodology for its development, effectively addressing the critical challenge of high-quality, domain-specific data scarcity in TCM, and providing essential data support for developing intelligent TCM diagnostic and therapeutic systems.

Objective To accumulate operating experience and background data for housing mice in individually ventilated cages (IVC).Methods 5 weeks old Balb /c male mice(n =80) were allocated to 8 groups(n =10), which then housed in 5 or 10 per cage in 3 IVC systems(30,50 and 70 air changes /h, respectively) and one open-top cages (OTC) shelf for 8 weeks.Body weight was assessed at the initial date and every week .By the end of the experiment, necropsy was done and organs were separated and weighed .Excelland SPSS software statistics was made to draw the growth curve, and comparative analysis of body weight and organ coefficients was performed between the groups .Results 1.The growth curves of 5-mice per cage were better than that of 10-mice per cage.2.In the IVC groups, the curves trend and fluency of 50 air changes /h were more similar to that of 5-mice housed OTC group.3.The previously mentioned differences were statistically not significant (P >0.05).4.In the liver coefficients, there was a statistically significant difference between the 10-mice housed OTC group and 5-mice housed IVC group with 30 air changes /h(P <0.05), there wasn`t any other significant statistically difference with the organ coefficients between groups (P >0.05).Conclusions Based on the results of this study, the air change frequency on 50 times per hour and keeping 5 Balb/c mice per cage is recommended as the best condition for mouse housing in IVC .