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.

Background:Faecalibacterium prausnitzii(Fp)is a commensal intestinal bacterium that exhibits anti-inflammatory and immunomodulatory capacity in vivo and in vitro. It has been reported that Fp in intestinal lumen was reduced in patients with colorectal cancer,which might be a factor associated with cancer development. Aims:To investigate the effect and immunological mechanism of Fp and its genomic DNA(fDNA)on the killing activity of peripheral blood mononuclear cells (PBMCs)against human colon cancer LoVo cells. Methods:PBMCs derived from healthy adults were co-cultured in vitro with Fp,fDNA,or the digested fDNA(d-fDNA),respectively. Killing activity of PBMCs against LoVo cells was measured by MTT assay;concentrations of interferon-gamma(INF-γ),a Th1-type cytokine and interleukin-4(IL-4),a Th2-type cytokine in culture supernatant of PBMCs were determined by ELISA;and expressions of T-bet and GATA3,the transcription factors specific for Th1 and Th2 cells,were measured by real-time PCR. Results:Compared with the PBMCs not treated,fDNA could significantly enhance the killing activity of PBMCs against LoVo cells(P < 0. 05);meanwhile,it promoted IFN-γ secretion,up-regulated T-bet mRNA expression and inhibited IL-4 secretion and GATA3 mRNA expression in PBMCs(P < 0. 05). Similar effects were not observed in PBMCs treated with Fp and d-fDNA. Conclusions:fDNA enhances the killing activity of PBMCs against human colon cancer cells by up-regulating Th1 immune response.

Background:Faecalibacterium prausnitzii( Fp) is one of the most abundant bacterium in human intestinal microbiota,and is closely correlated with the process of colitis-associated colorectal cancer(CAC). Aims:To observe the effect of Fp on CAC,and investigate the possible mechanism. Methods:The model of CAC was induced by azoxymethane (AOM)and dextran sodium sulfate( DSS). Fifty-two C57BL/ 6J mice were randomly divided into 4 groups:group A (AOM + DSS),group B(AOM + DSS + Fp),group C(AOM + DSS + Fp supernatant)and group D(control group). All the mice were sacrificed on day 92. DAI was assessed,serum levels of TNF-α and IL-10 were determined by ELISA. HE staining was used to examine the grade of tumor. Expressions of VEGF,COX-2,NF-κB in tumor tissue were measured by immunohistochemistry. Results:The tumorigenesis rates of group A,B,C were 100% ,100% and 77. 8% ,respectively;mainly were high-grade intraepithelial neoplasia. The tumor load in group A was significantly higher than that in group B (P < 0. 01),and the spleen index in group B was significantly higher than that in group C(P < 0. 01). Serum level of TNF-α was significantly lower(P < 0. 05)and IL-10 was significantly higher(P < 0. 05)in group A than that in group B. No significant differences in expressions of VEGF,COX-2,NF-κB were found among group A,B and C. Conclusions:Fp had no obvious effect on the occurrence rate of CAC,and Fp supernatant could decrease the incidence of CAC in mice. Fp and its supernatant could reduce the tumor load via regulating the expressions of TNF-α,IL-10.