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 investigate the causal relationship between walking pace(WP)with interver-tebral disc degeneration(IVDD)and low back pain(LBP)by using two-sample Mendelian randomisation(MR)analysis method.Methods A genome-wide association study database of WP,IVDD and LBP was ob-tained,and single nucleotide polymorphisms(SNP)strongly associated with exposure were obtained as the in-strumental variables.The two confounders of smoking and sedentary were conservatively removed,and the MR analyses were performed by inverse variance weighting(IVW),weighted median,and MR-Egger methods to assess the causal relationship between WP with IVDD and LBP.The consistency and accuracy of results were ensured by heterogeneity,diversity tests,MR-PRESSO and negative control.Results The I VW results showed a significant negative correlation between WP and IVDD(OR=0.348,95％CI:0.183-0.661,P=0.001)and vice versa(OR=0.972,95％CI:0.953-0.992,P=0.007).Meanwhile there was also a significant negative correlation between WP and LBP(OR=0.214,95％CI:0.119-0.385,P＜0.001),but no causal re-lationship was found between LBP and WP.Conclusion Faster WP could effectively prevent the occurrence of IVDD and LBP,and IVDD may contribute to the occurrence of slow walking.

Occupational exposure limits for hazardous agents in the workplace—Part 1: Chemical hazardous agents (GBZ 2.1—2019) has been implemented since April 1, 2020. The document redefines the evaluation of occupational exposure by introducing a "reduction factor" to adjust the occupational exposure limits of chemical hazardous agents for long working hour systems to ensure a protection level reasonable for the workers and equivalent to conventional occupational exposure limits. This paper discussed common problems encountered in the context of using this adjustment strategy, such as the adjustment being unable to cover all working hours, and the adjustment of values of terms associated with occupational exposure limits. Corresponding solutions were proposed. Working cycle and average exposure time of each working cycle were introduced to evaluate the actual working hours of workers. Regarding involved terms, adjustments of their corresponding values were clarified according to their definitions and application scenarios. Examples were provided for occupational health service providers so that their occupational health practices could be carried out in a more scientific and reasonable manner.