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 analyze the influencing factors for achieving target plasma drug concentration （trough） （abbreviated as “PDC”） of vancomycin in patients from high-altitude regions and establish a predictive model for PDC using single- center data， providing references for rational clinical drug use. METHODS Inpatients with vancomycin （1 g， q12 h） administered intravenously in our hospital from January 2021 to June 2024 were retrospectively included. Demographic data， liver and kidney function and hematological indexes were collected. Spearman correlation analysis was used to evaluate the correlation between vancomycin PDC and each detection index. Univariate analysis was used to evaluate the differences of each index in patients with different PDC， and the effects of different gender， body mass index， age and underlying diseases （hypertension/diabetes） on vancomycin PDC. Based on the results of correlation analysis and univariate analysis， multiple linear stepwise regression analysis was used to obtain the independent predictors of vancomycin PDC and construct the prediction model. RESULTS A total of 141 patients were included， with an overall attainment rate of 46.81% for the target PDC of vancomycin. Correlation analysis showed that the vancomycin PDC was positively correlated with age， blood urea nitrogen， uric acid （UA）， serum creatinine （CRE） and β2- microglobulin （β2-MG）， and negatively correlated with height， weight， creatinine clearance rate （CCR）， glomerular filtration rate （GFR）， alanine transaminase （ALT）， hemoglobin （HGB）， white blood cell count and neutrophils （P＜0.05）. There were significant differences in age， CRE and other 14 indexes among different PDC groups （P＜0.05 or P＜0.01）. Age and underlying diseases had significant effects on vancomycin PDC （P＜0.05 or P＜0.01）. CCR， direct bilirubin （DBil）， β2-MG， UA， HGB and height （standardized coefficients were －0.371， 0.367， 0.169， 0.232， －0.140， －0.132； P＜0.05） were independent predictors of vancomycin PDC. The F value of the regression equation was 34.858 （P＜0.05）， the R2 was 0.610， and the adjusted R2 was 0.592. CONCLUSIONS The vancomycin PDC of patients in high-altitude regions is affected by multiple factors such as renal function， liver function and hematological indexes. CCR， HGB and height could be used to predict vancomycin PDC negatively， while DBil， β2-MG and UA could be used to predict vancomycin PDC positively. The variables of the established prediction model could explain 59.2% of the variation of vancomycin PDC.

BACKGROUND:Psoralen has a strong anti-osteoporotic activity and may have a restorative effect on chemotherapy-induced osteoporosis. OBJECTIVE:To explore the restorative effect of psoralen on the osteogenic differentiation of bone marrow mesenchymal stem cells in mice inhibited by cyclophosphamide and its mechanism. METHODS:C57BL/6 mouse bone marrow mesenchymal stem cells were isolated and cultured.Effect of psoralen on viability of bone marrow mesenchymal stem cells was detected by MTT assay.Osteogenic induction combined with alkaline phosphatase staining was used to determine the optimal dose of psoralen to restore the osteogenic differentiation of bone marrow mesenchymal stem cells inhibited by cyclophosphamide.The mRNA expression levels of Runx2,alkaline phosphatase,Osteocalcin,osteoprotegerin,and Wnt/β-catenin signaling pathway-related genes Wnt1,Wnt4,Wnt10b,β-catenin,and c-MYC were measured by RT-qPCR at different time points under the intervention with psoralen.The protein expression of osteogenic specific transcription factor Runx2 and Wnt/β-catenin signaling pathway related genes Active β-catenin,DKK1,c-MYC,and Cyclin D1 was determined by western blot assay at different time points under the intervention with psoralen. RESULTS AND CONCLUSION:(1)There was no significant effect of different concentrations of psoralen on the viability of bone marrow mesenchymal stem cells.The best recovery of the inhibition of osteogenic differentiation of bone marrow mesenchymal stem cells caused by cyclophosphamide was under the intervention of psoralen at a concentration of 200 μmol/L.(2)Psoralen reversed the reduction in osteogenic differentiation marker genes Runx2,alkaline phosphatase,Osteocalcin and osteoprotegerin mRNA expression and Runx2 protein expression in bone marrow mesenchymal stem cells caused by cyclophosphamide conditioned medium.(3)Psoralen reversed the decrease in Wnt/β-catenin pathway-related genes Wnt4,β-catenin,c-MYC mRNA and Active β-catenin,c-MYC,and Cyclin D1 protein expression and the increase in DKK1 protein expression in bone marrow mesenchymal stem cells caused by cyclophosphamide conditioned medium.(4)The results showed that cyclophosphamide inhibited osteogenic differentiation of bone marrow mesenchymal stem cells in mice,and psoralen had a restorative effect on it.The best intervention effect was achieved at a concentration of 200 μmol/L psoralen,and this protective effect might be related to the activation of Wnt4/β-catenin signaling pathway by psoralen.

ObjectiveTo assess the predictive value of the bladder deformation index (BDI) in determining upper urinary tract (UUT) damage among patients with neurogenic bladder (NB). MethodsClinical data of 132 NB patients admitted to Beijing Bo'ai Hospital from January, 2015 to December, 2018 were retrospectively analyzed. Patients were divided into UUT damage group and normal UUT group according to the presence or absence of hydronephrosis. The demographics, biochemical parameters and video-urodynamics (VUDS) findings were collected, and BDI was calculated. Receiver operating characteristic (ROC) curves were utilized to evaluate the predictive capability. ResultsThere were 54 patients in UUT damage group and 33 in normal UUT group. The course of disease, creatinine level and BDI were siginificantly different between two groups (P < 0.05), while the area under the curve were 0.686, 0.836 and 0.928, respectively. ConclusionCourse of disease, creatinine level and BDI are associated with UUT damage in NB patients, and BDI demonstrates the highest sensitivity and specificity, which may play a role in diagnosis of UUT damage.

Purpose: Biomarkers predicting clinically significant prostate cancer (sPC) before biopsy are currently lacking. This study aimed to develop a non-invasive urine test to predict sPC in at-risk men using urinary metabolomic profiles. Materials and Methods: Urine samples from 934 at-risk subjects and 268 treatment-naïve PC patients were subjected to liquid chromatography/mass spectrophotometry (LC-MS)-based metabolomics profiling using both C18 and hydrophilic interaction liquid chromatography (HILIC) column analyses. Four models were constructed (training cohort [n=647]) and validated (validation cohort [n=344]) for different purposes. Model I differentiates PC from benign cases. Models II, III, and a Gleason score model (model GS) predict sPC that is defined as National Comprehensive Cancer Network (NCCN)-categorized favorable-intermediate risk group or higher (Model II), unfavorable-intermediate risk group or higher (Model III), and GS ≥7 PC (model GS), respectively. The metabolomic panels and predicting models were constructed using logistic regression and Akaike information criterion. Results: The best metabolomic panels from the HILIC column include 25, 27, 28 and 26 metabolites in Models I, II, III, and GS, respectively, with area under the curve (AUC) values ranging between 0.82 and 0.91 in the training cohort and between 0.77 and 0.86 in the validation cohort. The combination of the metabolomic panels and five baseline clinical factors that include serum prostate-specific antigen, age, family history of PC, previously negative biopsy, and abnormal digital rectal examination results significantly increased AUCs (range 0.88–0.91). At 90% sensitivity (validation cohort), 33%, 34%, 41%, and 36% of unnecessary biopsies were avoided in Models I, II, III, and GS, respectively. The above results were successfully validated using LC-MS with the C18 column. Conclusions Urinary metabolomic profiles with baseline clinical factors may accurately predict sPC in men with elevated risk before biopsy.

ObjectiveTo evaluate pharmacological effects of Shengmai injection（SMI）on cerebral ischemia and study its neuroprotective mechanism. MethodsMale specific pathogen-free （SPF） Sprague-Dawley （SD） rats were randomly divided into a sham group， a model group， a low-dose SMI group（3 mL·kg^-1）， a middle-dose SMI group（6 mL·kg^-1）， a high-dose SMI group（12 mL·kg^-1）， and a Ginaton group（4 mL·kg^-1）according to the random number table method， with 12 rats in each group. The rat model of cerebral ischemia-reperfusion（MCAO/R）was prepared via the suture method. The administration groups were intraperitoneally injected with corresponding concentrations of SMI or Ginaton injection after reperfusion， which was conducted for 3 consecutive days. The sham group and model group were administered the equivalent volume of physiological saline. The pharmacological effects of SMI on brain injury in MCAO/R rats were evaluated by neurological function scores， cerebral infarction area， hematoxylin-eosin （HE） staining， Nissl staining， terminal deoxynucleotidyl transferase dUTP nick-end labeling （TUNEL） staining， and Western blot. The dominant link and key protein of SMI treating cerebral injury were explored using proteomic analysis. The related mechanisms of SMI were further validated using enzyme-linked immunosorbent assay （ELISA）， Western blot， and chloride ion fluorescence probe with oxygen-glucose deprivation/reoxygenation（OGD/R）-treated PC12 cells and MCAO/R rats. ResultsCompared with the sham group， the model group showed significantly increased neurological function scores， cerebral infarction area， neuronal apoptosis rate， and expression levels of apoptosis related proteins （P<0.05， P<0.01）and significantly decreased density of Nissl bodies and neurons（P<0.01）. Compared with the model group， the SMI groups exhibited significantly decreased neurological function scores， cerebral infarction area， neuronal apoptosis rate， and expression levels of apoptosis related proteins （P<0.05， P<0.01）and significantly increased density of Nissl bodies and neurons （P<0.05）. The proteomic analysis results showed that oxidative stress and inflammatory response were important processes of SMI intervening in MCAO/R injury， and the chloride intracellular channel protein 1 （CLIC1） was one of key proteins in its action network. The levels of representative indicators of oxidative stress and inflammatory response in the MCAO/R rats of the SMI groups were significantly reduced， compared with those in the model group（P<0.05， P<0.01）， and the expression levels of CLIC1 and downstream NOD-like receptor protein 3 （NLRP3） decreased （P<0.01）. In addition， the experimental results based on the OGD/R PC12 cells showed that SMI significantly increased the cell survival rate（P<0.01） and significantly decreased the intracellular chloride ion concentration（P<0.05）. ConclusionSMI has neuroprotective effects. Oxidative stress and inflammatory response are key processes of SMI intervening in MCAO/R injury. The potential mechanism is closely related to the regulation of CLIC1.

ObjectiveTo investigate the mechanism by which 2，3，5，4'-tetrahydroxyldiphenylethylene-2-O-glucoside （THSG） mitigates cerebral ischemia/reperfusion （CI/R） injury by regulating mitochondrial calcium overload and promoting mitophagy. MethodsSixty male SD rats were randomized into sham， model， SAS （40 mg·kg^-1）， and low-， medium- and high-dose （10， 20， 40 mg·kg^-1， respectively） THSG groups， with 10 rats in each group. The middle cerebral artery occlusion/reperfusion （MCAO/R） model was established by the modified Longa suture method. An oxygen-glucose deprivation/reoxygenation （OGD/R） model was constructed in PC12 cells. Neurological deficits were assessed via Zea Longa scoring， and cerebral infarct volume was measured by 2，3，5-triphenyltetrazolium chloride （TTC） staining. Structural and functional changes of cortical neurons in MCAO/R rats were assessed by hematoxylin-eosin and Nissl staining. PC12 cell viability was detected by cell counting kit-8 （CCK-8） assay， and mitochondrial calcium levels were quantified by Rhod-2 AM. Immunofluorescence was used to detect co-localization of PTEN-induced kinase 1 （PINK1） and leucine zipper/EF-hand-containing transmembrane protein 1 （LETM1） in neurons. Transmission electron microscopy （TEM） was employed to observe mitochondrial morphology in neurons. Western blot was employed to analyze the expression of translocase of outer mitochondrial membrane 20 （TOMM20）， autophagy-associated protein p62， microtubule-associated protein light chain 3 （LC3）， cysteinyl aspartate-specific proteinase-9 （Caspase-9）， B-cell lymphoma 2-associated protein X （Bax）， and cytochrome C （Cyt C）. ResultsCompared with the sham group， the model group exhibited increased infarct volume （P<0.01） and neurological deficit scores （P<0.01）， neuronal structure was disrupted with reduced Nissl bodies. （P<0.01）， mitochondrial swelling/fragmentation， decreased PINK1/LETM1 co-localization （P<0.01）， upregulated protein levels of LC3Ⅱ/LC3Ⅰ， TOMM20， Caspase-9， Bax， and Cyt C （P<0.01）， downregulated protein level of p62 （P<0.05）， weakened PC12 viability （P<0.01）， and elevated mitochondrial calcium level （P<0.01）. Compared with the model group， THSG and SAS groups showed reduced infarct volumes （P<0.05，P<0.01） and neurological deficit scores （P<0.05，P<0.01）， mitigated mitochondrial damage， and increased PINK1/LETM1 co-localization （P<0.01）. Medium/high-dose THSG and SAS alleviated the neurological damage， increased Nissl bodies （P<0.05，P<0.01）， downregulated the protein levels of p62， TOMM20， Caspase-9， Bax， and Cyt C （P<0.05，P<0.01）， and elevated the LC3Ⅱ/LC3Ⅰ level （P<0.05，P<0.01）. High-dose THSG enhanced PC12 cell viability （P<0.01）， increased PINK1/LETM1 co-localization （P<0.01）， and reduced mitochondrial calcium （P<0.01）. ConclusionTHSG may exert the neuroprotective effect on CI/R injury by activating the PINK1-LETM1 signaling pathway， reducing the mitochondrial calcium overload， and promoting mitophagy.

ObjectiveTo investigate the mechanism by which 2，3，5，4'-tetrahydroxyldiphenylethylene-2-O-glucoside （THSG） mitigates cerebral ischemia/reperfusion （CI/R） injury by regulating mitochondrial calcium overload and promoting mitophagy. MethodsSixty male SD rats were randomized into sham， model， SAS （40 mg·kg^-1）， and low-， medium- and high-dose （10， 20， 40 mg·kg^-1， respectively） THSG groups， with 10 rats in each group. The middle cerebral artery occlusion/reperfusion （MCAO/R） model was established by the modified Longa suture method. An oxygen-glucose deprivation/reoxygenation （OGD/R） model was constructed in PC12 cells. Neurological deficits were assessed via Zea Longa scoring， and cerebral infarct volume was measured by 2，3，5-triphenyltetrazolium chloride （TTC） staining. Structural and functional changes of cortical neurons in MCAO/R rats were assessed by hematoxylin-eosin and Nissl staining. PC12 cell viability was detected by cell counting kit-8 （CCK-8） assay， and mitochondrial calcium levels were quantified by Rhod-2 AM. Immunofluorescence was used to detect co-localization of PTEN-induced kinase 1 （PINK1） and leucine zipper/EF-hand-containing transmembrane protein 1 （LETM1） in neurons. Transmission electron microscopy （TEM） was employed to observe mitochondrial morphology in neurons. Western blot was employed to analyze the expression of translocase of outer mitochondrial membrane 20 （TOMM20）， autophagy-associated protein p62， microtubule-associated protein light chain 3 （LC3）， cysteinyl aspartate-specific proteinase-9 （Caspase-9）， B-cell lymphoma 2-associated protein X （Bax）， and cytochrome C （Cyt C）. ResultsCompared with the sham group， the model group exhibited increased infarct volume （P<0.01） and neurological deficit scores （P<0.01）， neuronal structure was disrupted with reduced Nissl bodies. （P<0.01）， mitochondrial swelling/fragmentation， decreased PINK1/LETM1 co-localization （P<0.01）， upregulated protein levels of LC3Ⅱ/LC3Ⅰ， TOMM20， Caspase-9， Bax， and Cyt C （P<0.01）， downregulated protein level of p62 （P<0.05）， weakened PC12 viability （P<0.01）， and elevated mitochondrial calcium level （P<0.01）. Compared with the model group， THSG and SAS groups showed reduced infarct volumes （P<0.05，P<0.01） and neurological deficit scores （P<0.05，P<0.01）， mitigated mitochondrial damage， and increased PINK1/LETM1 co-localization （P<0.01）. Medium/high-dose THSG and SAS alleviated the neurological damage， increased Nissl bodies （P<0.05，P<0.01）， downregulated the protein levels of p62， TOMM20， Caspase-9， Bax， and Cyt C （P<0.05，P<0.01）， and elevated the LC3Ⅱ/LC3Ⅰ level （P<0.05，P<0.01）. High-dose THSG enhanced PC12 cell viability （P<0.01）， increased PINK1/LETM1 co-localization （P<0.01）， and reduced mitochondrial calcium （P<0.01）. ConclusionTHSG may exert the neuroprotective effect on CI/R injury by activating the PINK1-LETM1 signaling pathway， reducing the mitochondrial calcium overload， and promoting mitophagy.

Objective: Negative symptoms in schizophrenia indicate a poor prognosis. However, the mechanisms underlying the development of negative symptoms remain unclear. This study investigated the relationship between negative symptoms in schizophrenia and frontal alpha asymmetry (FAA). Methods: The study used a 32-channel electroencephalography to acquire alpha power in 4 target-paired sites in each patient. Regional alpha asymmetry was calculated based on the alpha power using EEGLAB Frontal Alpha Asymmetry Toolbox. Results: Sixty schizophrenia patients with predominant negative symptoms (PNS), 72 stabilized schizophrenia (SS) patients, and 73 healthy control (HC) participants were enrolled in this study. No significant differences were observed in FAA between the PNS and SS groups, although both groups exhibited reduced P3-P4 alpha asymmetry compared to HCs. A positive correlation was found between F7-F8 alpha asymmetry and illness duration. Additionally, a predictive model based on P3-P4 alpha asymmetry scores was able to differentiate schizophrenia patients from HCs, achieving a sensitivity of 71.2% and a specificity of 72.6%. Conclusion This study highlighted that parietal alpha asymmetry could serve as a valuable diagnostic tool for schizophrenia.

Purpose: Biomarkers predicting clinically significant prostate cancer (sPC) before biopsy are currently lacking. This study aimed to develop a non-invasive urine test to predict sPC in at-risk men using urinary metabolomic profiles. Materials and Methods: Urine samples from 934 at-risk subjects and 268 treatment-naïve PC patients were subjected to liquid chromatography/mass spectrophotometry (LC-MS)-based metabolomics profiling using both C18 and hydrophilic interaction liquid chromatography (HILIC) column analyses. Four models were constructed (training cohort [n=647]) and validated (validation cohort [n=344]) for different purposes. Model I differentiates PC from benign cases. Models II, III, and a Gleason score model (model GS) predict sPC that is defined as National Comprehensive Cancer Network (NCCN)-categorized favorable-intermediate risk group or higher (Model II), unfavorable-intermediate risk group or higher (Model III), and GS ≥7 PC (model GS), respectively. The metabolomic panels and predicting models were constructed using logistic regression and Akaike information criterion. Results: The best metabolomic panels from the HILIC column include 25, 27, 28 and 26 metabolites in Models I, II, III, and GS, respectively, with area under the curve (AUC) values ranging between 0.82 and 0.91 in the training cohort and between 0.77 and 0.86 in the validation cohort. The combination of the metabolomic panels and five baseline clinical factors that include serum prostate-specific antigen, age, family history of PC, previously negative biopsy, and abnormal digital rectal examination results significantly increased AUCs (range 0.88–0.91). At 90% sensitivity (validation cohort), 33%, 34%, 41%, and 36% of unnecessary biopsies were avoided in Models I, II, III, and GS, respectively. The above results were successfully validated using LC-MS with the C18 column. Conclusions Urinary metabolomic profiles with baseline clinical factors may accurately predict sPC in men with elevated risk before biopsy.