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 evaluate the long-term efficacy of intra-articular injection of hyaluronic acid （HA）， platelet-rich plasma （PRP）， and micro-fragmented adipose tissue （MFAT） in treatment of knee osteoarthritis （KOA）. METHODS Randomized controlled trials （RCTs） of KOA patients receiving intra-articular injection of the three agents were collected from PubMed， Web of Science， Embase， Cochrane Library， CNKI， Wanfang Data， VIP， Chinese Biomedical Literature Service System，and clinical trial registration platforms. The retrieval time limit was from January 2016 to December 2025. After screening the literature， extracting the data，and evaluating the quality of the literature， network meta-analysis was performed using RevMan 5.3 and Stata MP 16.0 software. RESULTS A total of 31 RCTs involving 2 964 patients were included. For pain relief， after 6 months of treatment， the Visual Analogue Scale （VAS） scores in the PRP+HA and PRP groups were significantly lower than those in the saline and HA groups （ P ＜0.05）， PRP+HA and PRP were ranked as the top two by surface under the cumulative ranking curve （SUCRA）. After 12 months of treatment， the VAS scores in the PRP group were significantly lower than those in the HA and saline groups （ P ＜0.05）， PRP and PRP+HA were ranked as the top two by SUCRA. For functional recovery， after 6 months of treatment， the Western Ontario and McMaster Universities Osteoarthritis Index （WOMAC） scores in the PRP group were significantly lower than those in the HA or saline groups （ P ＜0.05）. After 12 months of treatment， the WOMAC scores in the MFAT， PRP and PRP+HA groups were significantly lower than those in the HA or saline groups （ P ＜0.05）. After 6 and 12 months of treatment， International Knee Documentation Committee （IKDC） scores in the MFAT and PRP groups were significantly higher than the saline group （ P ＜0.05）， and after 12 months of treatment， the PRP group was significantly higher than the HA group （ P ＜0.05）. MFAT and PRP were ranked as the top two by SUCRA for both the WOMAC and IKDC scores. CONCLUSIONS For pain relief， PRP+HA showed a significant advantage at 6 months after treatment， whereas PRP alone demonstrated a notable superiority at 12 months after treatment. For functional recovery， MFAT exhibited a marked advantage at both 6 and 12 months after treatment.

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.

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.

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.

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.

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.

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.

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.