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 clinical features and prognosis of prolonged cytopenia (PC) in patients with large B-cell lymphoma (LBCL) undergoing anti-CD19 chimeric antigen receptor T (CAR-T) cell therapy.Methods:A retrospective case series study was conducted on LBCL patients who received CAR-T cell therapy with a survival time of over one month at the Hematology Department of Peking Union Medical College Hospital from March 2019 to December 2023. Statistical analyses were performed on hematologic changes at 1, 3, 6, and 12 months post-CAR-T infusion, as well as on the progression-free survival (PFS) and post-treatment adverse events, including infections. Patients were categorized into the PC and non-PC groups based on the occurrence of cytopenia at 90 days post-infusion. Differences between groups were compared, and univariate logistic regression analysis was used to identify risk factors.Results:The median age of 27 LBCL patients receiving CAR-T cell therapy was 58 years (range 27-69 years), with 18 males. Among the 27 LBCL patients who received CAR-T cell therapy, PC was observed in 19 patients (70.4%), with instances of neutropenia (48.1%, 13 cases), anemia (37.0%, 10 cases), and thrombocytopenia (22.2%, 6 cases). Univariate logistic regression analysis revealed that prior chemotherapy sensitivity ( OR=18.00, 95% CI 1.56-207.45, P=0.020) and bone marrow suppression ( OR=18.00, 95% CI 1.38-235.69, P=0.028) were associated with PC. The median follow-up time was 13.5 months. The PC group exhibited a higher risk of infection within 3 months (9/19 vs. 1/8) and a shorter mean PFS (19.3 months vs. 24.4 months), although the difference was not statistically significant (both P>0.05). Conclusions:PC is common following CAR-T cell therapy and is associated with an increased risk of infection and poorer prognosis. Prior treatment sensitivity and bone marrow suppression may serve as indicators of PC.

Objective To develop a software through which transfusion labels can be created and printed automatically based on No.1 Military Medical Project,in order to resolve the problems of time-and-labor-consuming and errors due to transcription. Methods Based on No.1 Military Medical Project,the software of creating and printing transfusion labels was developed using PB computer programming language. Results The software can effectively avoid the errors due to copying transfusion labels by hand and save much time and effort. It optimizes nurses' working procedure. Conclusion The software is very practical for all the hospitals using the No.1 Military Medical Project.