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:As a temporary matrix for new bone growth,the porous scaffold plays a key role in the process of bone repair.The structural design of porous scaffolds is a research priority in the process of bone repair.OBJECTIVE:To summarize traditional bone scaffolds(regular,uniform scaffolds)and bionic scaffolds(irregular,inhomogeneous scaffolds)in the field of bone tissue engineering research.METHODS:A computerized search was performed in the databases of CNKI,VIP,WanFang,Web of Science,Science Direct,PubMed,and EI.Literature published from January 2008 to March 2024 was selected.The search terms in Chinese included"bone tissue engineering,bionic scaffolds,bone trabeculae,traditional scaffolds,bone repair,triple-period minimal surfaces."The search terms in English were"bone tissue engineering,bionic scaffolds,bone trabeculae,traditional scaffolds,bone repair,TPMS."Finally,81 articles were included for review.RESULTS AND CONCLUSION:The structural design of bone scaffolds is the key to achieve bone repair and bone regeneration,and scaffold technology in bone tissue engineering has made remarkable progress.Traditional regular porous scaffolds are widely used due to their simple manufacturing process and good mechanical properties.However,these scaffolds often lack biological activity and are difficult to mimic the complex microenvironment of natural bone tissue,limiting their ability to promote cell proliferation and bone regeneration.On the contrary,bionic scaffolds provide a more suitable physiological microenvironment by mimicking the structural features of natural bone tissues,which promotes the proliferation and differentiation of osteoblasts,as well as the formation of new bone,and provides a new way of thinking for the effective treatment of bone defects.Despite the great potential of bionic scaffolds in theory,they still face many challenges in practical applications.Factors such as the scaffold's biocompatibility,bioactivity,and its long-term stability still need to be further verified through clinical trials.

OBJECTIVE To comprehensively evaluate the efficacy， safety and cost-effectiveness of insulin icodec in treating type 2 diabetes mellitus （T2DM）， providing evidence-based guidance for new drug selection in hospital and clinical medication decision-making. METHODS PubMed， Cochrane Library， Embase， CNKI， Wanfang， VIP and foreign health technology assessment （HTA） websites were searched by using rapid health technology assessment from inception to 15 July 2025 for systematic reviews/meta-analyses， pharmacoeconomic studies， and HTA reports on insulin icodec in the treatment of T2DM. After data extraction and quality assessment， the findings of the included studies were analyzed descriptively. RESULTS Ten systematic reviews/meta-analyses and three pharmacoeconomic studies were included. Among them， 4 systematic reviews/meta-analyses were of high quality； the overall quality of the 3 pharmacoeconomic studies was relatively good. Regarding efficacy， insulin icodec was superior to once-daily basal insulin in reducing glycated hemoglobin （HbA1c） and in achieving the target of HbA1c＜7% （P＜0.05）. No significant differences were observed between icodec insulin and comparators in lowering fasting plasma glucose （P＞0.05）. For safety， insulin icodec did not increase the incidence of any adverse events （AEs）， serious AEs， clinically significant hypoglycemia （random glucose＜3 mmol/L）， injection-site reactions， or allergic reactions， compared with once-daily basal insulin overall （P＞ 0.05）； however， insulin icodec was associated with a significant increase in body weight （P＜0.05）. Domestic economic evaluations indicated that insulin icodec was more cost-effective than insulin glargine and insulin degludec when its annual costs were in the range of 784.90-1 145.96 and 597.66-736.34 US dollars， respectively. CONCLUSIONS Insulin icodec demonstrates favorable efficacy and safety profiles in the treatment of T2DM； however， attention should be paid to the risk of weight gain. Under China’s healthcare system， insulin icodec demonstrates greater economic value only when the patient’s weekly required basal insulin dose falls within a specific range，and clinical practice requires individualization.

Objective To explore the effects and mechanisms of bone marrow mesenchymal stem cell(BMMSC)-derived exosomes(BMMSC-Exo)on hypoxia/reoxygenation(H/R)-induced injury in rat cardiomyocyte cell line(H9c2).Methods BMMSC-Exosomes were isolated by ultracentrifugation.The cells were divided into three groups:control,H/R,and H/R+BMMSC-Exo(H/R+Exo).A hypoxia/reoxygenation(H/R)injury model was es-tablished by exposing cells to 12 hours of hypoxia followed by 6 hours of reoxygenation.Flow cytometry was used to detect cell apoptosis,DHE staining was used to assess cellular ROS levels,JC-1 immunofluorescence staining was used to evaluate mitochondrial membrane potential,and Western blot was used to detect mitochondrial autophagy-re-lated proteins.Results BMMSC-Exo treatment significantly alleviated oxidative stress,restored mitochondrial mem-brane potential,reduced mitochondrial autophagy levels,and effectively decreased cardiomyocyte apoptosis.Conclu-sions Bone marrow mesenchymal stem cell-derived exosomes alleviate H/R-induced cardiomyocyte injury.

Objective To investigate the function and mechanism of miR-29 family in trauma induced coagulopathy(TIC).Methods Bioinformatics was used to analyze the targeting relationship between miR-29 family members and hepatocyte nuclear factor-4α(HNF-4α).HE staining results,TEG parameters and coagu-lation parameters were used to verify the TIC rat model construction.Real-time quantitative fluorescent PCR(RT-qPCR)and Western blot were used to detect the expression of miR-29 family,HNF-4α and coagulation factor Ⅹ(FⅩ)in rat liver tissues.Overexpression of miR-29b-3p(miR-29b-3p mimics)or silence of miR-29b-3p(miR-29b-3p inhibitor)was transfected into hepatocytes,and the levels of miR-29b-3p,HNF-4α and FⅩ in hepatocytes were detected by RT-qPCR and Western blot.Double lucifase reporter gene assay verified the targeted regulation of miR-29b-3p on HNF-4α.The miR-29b-3p mimics and/or HNF-4α overexpression vector were transfected into hepatocytes,and the levels of miR-29b-3p,HNF-4α and FⅩ in hepatocytes were detected by RT-qPCR and Western blot.Results Bioinformatic prediction results from the miRDIP database identified that multiple members of the miR-29 family(miR-29a-3p,miR-29b-3p,miR-29b-5p,and miR-29c-3p)contain potential binding sites with HNF-4α.Histopathological evaluation through HE staining,combined with TEG parameters and coagulation profiles,confirmed successful establishment of the TIC rat model.Quantitative analyses using RT-qPCR and Western blot revealed that compared to controls,both HNF-4α and coagulation FⅩ expression levels were markedly suppressed in the model group,while miR-29b-3p expression showed significant elevation in TIC rats(P＜0.01).In vitro functional studies demonstrated that neither overexpression nor silencing of miR-29b-3p significantly influenced hepatocyte proliferation(P＞0.05).How-ever,forced expression of miR-29b-3p effectively downregulated HNF-4α and its downstream target FⅩ,whereas miR-29b-3p knockdown substantially upregulated these molecules(P＜0.05).This regulatory rela-tionship was further validated by dual luciferase reporter assays confirming direct targeting between HNF-4α and miR-29b-3p.Notably,exogenous HNF-4α overexpression significantly rescued FⅩ suppression induced by miR-29b-3p overexpression(P＜0.05).Conclusion miR-29b-3p is up-regulated in TIC,which can promote the progression of TIC by targeting HNF-4α to regulate FⅩ expression.

Objective To identify the key points of forensic appraisal in ophthalmic medical-injury compensation cases and propose targeted measures to prevent disputes.Methods A retrospective analysis was conducted of the appraisal conclusions from 15 ophthalmology medical-injury liability lawsuits handled at a single tertiary hospital over the past five years.We summarized the constitutive characteristics of liability cases,causes of medical injury,and issues encountered during appraisal.Results Among cases undergoing medical-injury liability appraisal,retinal diseases and ocular tumors predominated.The main issues included inadequate informed consent,failure to exercise due care during surgery/treatment,non-standard medical record documentation,insufficient attention to medical risks,and inadequate clinical assessment.Conclusions By summarizing common faults in ophthalmic disputes and problems revealed by forensic appraisal,targeted responses can be implemented to ensure patient safety and promote high-quality medical services.

Accurate identification of the glomerular ultrastructure is critical for the diagnosis of chronic kidney diseases,but the high cost of acquiring high-quality annotated data limits the application of fully-supervised learning.Therefore,a multi-class semi-supervised semantic segmentation framework based on segment anything model(MC4S-SAM)is proposed.After improving the mask decoder of segment anything model to enable multi-class semantic segmentation without requiring prompt information,the improved model is used to generate and refine pseudo-labels through a self-training strategy,and multi-level consistency regularization constraints are incorporated to enhance the model's performance.Experimental results show that,in the task of segmenting the glomerular mesangial ultrastructure,MC4S-SAM outperformes the fully-supervised model by 11.72%in mean intersection over union(mIoU)and 11.45%in mean Dice similarity coefficient(mDSC)when the labeled data accountes for 1/16 of the total.When the labeled data proportion is 1/4,the mIoU and mDSC reach 68.91%and 78.73%,respectively,demonstrating its significant potential for aiding the diagnosis of chronic kidney diseases.

The research on medical image segmentation is of great significance in advancing efficient and accurate automated image processing techniques.To address the problem of inaccurate segmentation results caused by significant variations in organ tissue shapes and blurred boundaries present in medical images,a novel network named MFMANet is proposed.Built upon a"U"-shaped architecture,the network integrates multi-scale information fusion modules and multi-attention modules.Specifically,multi-scale information modules capture multi-scale information in the shallow layers of the network to bridge the semantic gap between encoder and decoder features,thereby enhancing the network's ability to handle large variations in organ sizes.Regarding the issue of blurred boundaries,multi-attention mechanism utilizes Swin Transformer as the deep encoder-decoder network,employing channel and spatial attention instead of traditional skip connections to achieve finer feature extraction.Experimental results on the ACDC and Synapse public datasets show that the proposed method achieves improvements of 1.51%and 1.29%in Dice similarity coefficient as compared with MTUNet,fully demonstrating its effectiveness in enhancing segmentation network accuracy.

Accurate identification of the glomerular ultrastructure is critical for the diagnosis of chronic kidney diseases,but the high cost of acquiring high-quality annotated data limits the application of fully-supervised learning.Therefore,a multi-class semi-supervised semantic segmentation framework based on segment anything model(MC4S-SAM)is proposed.After improving the mask decoder of segment anything model to enable multi-class semantic segmentation without requiring prompt information,the improved model is used to generate and refine pseudo-labels through a self-training strategy,and multi-level consistency regularization constraints are incorporated to enhance the model's performance.Experimental results show that,in the task of segmenting the glomerular mesangial ultrastructure,MC4S-SAM outperformes the fully-supervised model by 11.72%in mean intersection over union(mIoU)and 11.45%in mean Dice similarity coefficient(mDSC)when the labeled data accountes for 1/16 of the total.When the labeled data proportion is 1/4,the mIoU and mDSC reach 68.91%and 78.73%,respectively,demonstrating its significant potential for aiding the diagnosis of chronic kidney diseases.