This paper outlines the development of artificial intelligence （AI） and its applications in traditional Chinese medicine （TCM） research， and elucidates the roles and advantages of large language models， knowledge graphs， and natural language processing in advancing syndrome identification， prescription generation， and mechanism exploration. Using spleen-stomach diseases as an example， it demonstrates the empowering effects of AI in classical literature mining， precise clinical syndrome differentiation， efficacy and safety prediction， and intelligent education， highlighting an upgraded research paradigm that evolves from data-driven and knowledge-driven approaches to intelligence-driven models. To address challenges related to privacy protection and regulatory compliance in cross-institutional data collaboration， a "trusted federated evidence-based analysis platform for TCM spleen-stomach diseases" is proposed， integrating blockchain-based smart contracts， federated learning， and secure multi-party computation. The deep integration of AI with privacy-preserving computing is reshaping research and clinical practice in TCM spleen-stomach diseases， providing feasible pathways and a technical framework for building a high-quality， trustworthy TCM big-data ecosystem and achieving precision syndrome differentiation.

Objective To examine the impact and partial mechanism of bupivacaine sustained-release drug(code PB21)in combination with low-dose dexamethasone(Dex)on the analgesic time of rats with knee osteoarthritis(KOA).Methods Using the techniques of anterior cruciate ligament transection and meniscus instability,a rat KOA model was created.After eight weeks,SD mice were split into three groups at random:a group for the model,one for Dex(50 μg),one for PB21(1.5 mg),and one for combined administration(1.5 mg PB21/50 μg Dex),with a control group that received a sham operation.The pain thresholds of KOA rats were measured using a Pres-sure Application Measurement(PAM)at different intervals before to delivery and 4,24,36,and 48 hours following administration;to gauge changes in discomfort,a CatWalk was used to assess the rats'average foot strength and maximum contact area before,four,twenty-four,and forty-eight hours after treatment.A portion of the rats were put to sleep at four,twenty-four,and forty-eight hours following the injection,and the joint synovium was removed for paraffin sectioning.Immunohistochemistry was used to identify the expression of GAP43 in the synovium,whereas immunofluorescence was used to identify the expression of CGRP in the same tissue.Results The average strength and maximum contact area of the foot and claw decreased(P＜0.01),and the pain threshold decreased(P＜0.01)in the model group compared to the sham operation group.The PB21+Dex group experienced a delayed pain threshold lowering time delay when compared to the PB21 and Dex treatment groups alone.Up to 48 hours lat-er,the combination administration group's average strength and maximum contact area of the foot paw remained ele-vated,and there was a statistically significant difference(P＜0.05)between the combined administration group and PB21 and Dex alone.GAP43 and CGRP expression levels in synovial tissue were detected.The results indica-ted that PB21 and Dex alone could lower protein expression levels at 4 and 24 h at the two time points,and that the PB21+Dex group could still significantly lower GAP43 and CGRP expression levels at 48 h.At the 48 h time point,the PB21+Dex group was statistically significant when compared to the PB21 and Dex alone administration group(P＜0.05).Conclusion In summary low dose dexamethasone can prolong the analgesic effect of PB21 on KOA rats,which is connected to reducing the expression of pain related proteins CGRP and GAP43.

Objective To study serum levels of soluble intercellular adhesion molecule-1 (sICAM-1) and its correlation with accumulation degree of 99Tcm-MDP on bone and arthritis and to study the role of sICAM-1 in the diagnosis of patients with early RA. Methods Serum levels of sICAM-1 were measured by immunoenzymetic assay (ELISA). 99mTc-MDP scintigraphy was carried out for the same patients. The significant test between serum levels of sICAM-1 of three groups was performed with analysis of variance; Correlations between serum levels of sICAM-1 and index of semiquatitive 99Tcm-MDP were obtained using sperman's ranks correlation method. Results Compared with control group,serum levels of sICAM-1 were significantly higher in standard group (group A) (P<0.01) and non-standard group (group B) (P<0.05). No significant difference was found between group A and B(P>0.05). Serum levels of sICAM-1 were positively correlated with 99Tcm-MDP scintigraphy. Most patients of non-standard group and standard group showed visible medium-high uptake of 99Tcm-MDP. While control group had not obviously uptake of 99Tcm-MDP. Conclusion Serum levels of sICAM-1, semiquatitive 99Tcm-MDP scintigraphy, accumulation degree of radiopharmuceuutial on bone and arthritis are helpful for diagnosis of early rheumatoid arthritis and judge-ment of the clinical status and improvement of the prognosis.