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 relationship between 24 hour activity behaviors and fine motor development in preschool children, and to simulate the effects of reallocating time among different activity behaviors on fine motor development using isotemporal substitution analysis. Methods: From March to July 2022, a stratified cluster random sampling method was used to recruit 447 preschool children aged 3-6 years (254 boys and 193 girls) from Pingxiang City, Jiangxi Province. The 24 hour activity behaviors in preschool children were measured using ActiGraph wGT3-BT accelerometers and subjective sleep reports. Fine motor development was assessed using the Gesell Developmental Schedules. A component linear regression model was employed to analyze the impact of 24 hour activity behaviors on the development of fine motor activities, and the potential effects of adjusting activity behaviors were simulated through an isochoric substitution model. Results: The daily durations of sedentary behavior (SB) was ( 572.92 ±102.96) min (accounting for 39.79% of 24 h), the duration of light physical activity (LPA) was (131.21± 38.11 ) min ( 9.11% ), the duration of moderate to vigorous physical activity (MVPA) was (65.61±22.21) min (4.56%), and sleep duration was (670.65±57.58) min (46.82%). Sleep composition was positively associated with fine motor development ( β =2.74), while MVPA ( β =-0.84) and SB ( β =-1.93) compositions were negatively associated with fine motor development (all P <0.01). Isochoric substitution analysis showed that sleep had positive effects on the development of fine motor skills when replacing other activity behaviors (all P < 0.05), with the substitution effect for MVPA being the most significant and gradually increasing with the duration of substitution (60 min: β =28.66); sleep replacement of SB and LPA also showed positive effects (60 min: β =4.25, 2.00) (all P < 0.05). On the contrary, the substitution of sleep with MVPA showed negative effects (60 min: β =-7.86), and the substitution of LPA and SB with MVPA also showed negative effects (60 min: β =-5.65, -3.40) (all P <0.05). Conclusions The overall composition of 24 hour activity behaviors is associated with fine motor development in preschool children, with sleep playing a crucial role. Ensuring adequate sleep and optimizing the structure of activity behaviors may effectively promote the development of fine motor skills in preschool children.

Objective: To investigate the development status and associated factors of social emotional competence(SEC) among disadvantaged children aged 3-6 in rural areas of Guangxi, so as to provide empirical evidence to address the negative impacts of their disadvantaged circumstance. Methods: In May 2025, using convenience sampling, a study was conducted with 1 426 children aged 3-6 from disadvantaged backgrounds attending 11 rural kindergartens in Guilin, Liuzhou, and Qinzhou, Guangxi. A self designed questionnaire was used to investigate children s personal basic information, family situation (parents education level, family structure, parent-child separation status, family poverty status, multiple disadvantaged situations, family function) and kindergarten situation. Social Emotional Learning Rating Form-Parent (SELRF-P) was used to assess their social emotional competence. Latent profile analysis (LPA) and multiple Logistic regression were applied for data classification and related factor analysis, respectively. Results: The social emotional competence of disadvantaged children was categorized into four groups: well adjusted group (4.77%, n =68), basically adjusted group (38.43%, n =548), potential risk group (25.11%, n =358), and high risk delayed development group (31.69%, n = 452). Multinomial Logistic regression analysis revealed that family poverty ( OR = 1.98 ), parental education level of high school/technical secondary school or below ( OR =2.89), non parental caregivers ( OR = 3.81 ), private and non model kindergartens ( OR =1.96, 3.52), younger age (3 or 4 years old) ( OR =2.61, 2.79), low family cohesion ( OR =4.05), weak family adaptability ( OR =3.95), and multiple disadvantages ( OR =2.35) were more likely to lead children into the high risk delayed group; children seperated from parents were more likely to fall into the potential risk group ( OR = 1.82), while children from divorced families were less likely to enter the basically adjusted group ( OR =0.45) (all P <0.05). Conclusions Social emotional competence among disadvantaged children aged 3-6 years in rural areas shows significant group heterogeneity. Age, specific types of disadvantage, family functioning, and kindergarten characteristics are the main related factors. Precise intervention measures should be paid to improve the social emotional developmental difficulties of various disadvantaged children.

Objective To explore the influencing factors of acute kidney injury in severe burn patients,and to construct a visual risk nomogram model.Methods A total of 390 patients with severe burn admitted to the Institute of Burn Frostbite and Tissue Function Reconstruction of Chinese People's Armed Police Force Specialty Medical Center from January 2018 to January 2022 were collected as an internal training data set,and 50 patients with severe burn admitted from February to December 2022 were collected as an external validation data set.The 390 patients of the internal training data set were divided into the acute kidney injury group and the non-acute kidney injury group according to the occurrence of acute kidney injury,and the baseline data of patients in the two groups were compared.Univariate and multivariate Logistic regression were used to analyze the risk factors of acute kidney injury in severe burn patients of the internal training data set,and a nomogram model was drawn.Subsequently,the model was verified both internally and externally.Kaplan-Meier analysis and Log-rank test were used to compare the 90-day survival rate of patients between the acute kidney injury group and the non-acute kidney injury group.Results The burn area(OR=1.18,95%CI:1.06 to 2.36,P=0.004),sequential organ failure assessment(SOFA)score(OR=1.81,95%CI:1.21 to 5.92,P<0.001),inhalation injury(OR=3.21,95%CI:1.23 to 6.35,P<0.001),neutrophil to lymphocyte ratio(NLR)(OR=1.22,95%CI:1.05 to 3.65,P<0.001)and albumin(ALB)(OR=0.78,95%CI:0.57 to 0.92,P=0.011)were the independent risk factors for the development of acute kidney injury in severe burn patients.The nomogram model was established by the above factors.The area under the receiver operating characteristic curve(AUC)of the internal training data set was 0.833(95%CI:0.752 to 0.935),the sensitivity was 81.2%,and the specificity was 83.2%.The AUC of the external validation data set was 0.842(95%CI:0.762 to 0.912),the sensitivity 87.2%,and the specificity was 78.7%.The 90-day survival rate of patients in the acute kidney injury group after burns was significantly lower than that in the non-acute kidney injury group(P<0.001).Conclusion Larger burn area,higher SOFA score,combined inhalation injury,increased NLR,and decreased ALB level are the risk factors for the occurrence of acute kidney injury in severe burn patients,which are related to the 90-day survival rate of patients after burns.The nomogram model based on the risk factors can provide certain reference for clinical individualized prevention and treatment of acute kidney injury in severe burn patients.

Objective To analyze the risk factors and effective predictive indicators for postpartum hemor-rhage(PPH)in pregnant women with severe pre-eclampsia(sPE)in singleton pregnancies.The findings will serve as a valuable reference for the clinical prevention and management of PPH in these patients.Methods A retrospective analysis was conducted on 932 pregnant women with sPE at two tertiary hospitals in Guangzhou from January 1,2016,to December 31,2022.Among these,95 cases were complicated by PPH.A comparative analysis was performed between the sPE group and the sPE with PPH group.Results(1)The incidence of assisted reproductive technology,intrapartum blood loss,placental abruption,elevated D-dimer levels,increased monocyte counts,and higher SIRI levels were significantly higher in the PPH group,whereas platelet counts were significantly lower(P<0.05).(2)The results indicated that intrapartum blood loss,D-dimer levels,and platelet counts were inde-pendently associated with PPH in pregnant women with sPE.(3)The area under the curve(AUC)for intrapartum blood loss,D-dimer,and platelet counts were 0.805,0.717,and 0.571,respectively.The optimal cutoff value for D-dimer was determined to be 2.295 μg/mL.The combined AUC for intrapartum blood loss and D-dimer was 0.859.(4)Intrapartum blood loss values were significantly higher in the PPH group for both vaginal delivery and cesarean section(P<0.001).The corresponding optimal cutoff values were 285 mL and 375 mL,respectively.Conclusions Intrapartum haemorrhage,D-dimer levels,and platelet count were identified as independent risk factors for PPH in pregnant women with sPE.Specifically,pregnant women with sPE who experienced blood loss exceeding 285 mL during vaginal delivery or 375 mL during caesarean section,along with a D-dimer level greater than 2.295 μg/mL,demonstrated an increased likelihood of developing PPH.Therefore,it is crucial to enhance clinical monitoring of these relevant indicators in high-risk populations.

Objective To analyze the risk factors and effective predictive indicators for postpartum hemor-rhage(PPH)in pregnant women with severe pre-eclampsia(sPE)in singleton pregnancies.The findings will serve as a valuable reference for the clinical prevention and management of PPH in these patients.Methods A retrospective analysis was conducted on 932 pregnant women with sPE at two tertiary hospitals in Guangzhou from January 1,2016,to December 31,2022.Among these,95 cases were complicated by PPH.A comparative analysis was performed between the sPE group and the sPE with PPH group.Results(1)The incidence of assisted reproductive technology,intrapartum blood loss,placental abruption,elevated D-dimer levels,increased monocyte counts,and higher SIRI levels were significantly higher in the PPH group,whereas platelet counts were significantly lower(P<0.05).(2)The results indicated that intrapartum blood loss,D-dimer levels,and platelet counts were inde-pendently associated with PPH in pregnant women with sPE.(3)The area under the curve(AUC)for intrapartum blood loss,D-dimer,and platelet counts were 0.805,0.717,and 0.571,respectively.The optimal cutoff value for D-dimer was determined to be 2.295 μg/mL.The combined AUC for intrapartum blood loss and D-dimer was 0.859.(4)Intrapartum blood loss values were significantly higher in the PPH group for both vaginal delivery and cesarean section(P<0.001).The corresponding optimal cutoff values were 285 mL and 375 mL,respectively.Conclusions Intrapartum haemorrhage,D-dimer levels,and platelet count were identified as independent risk factors for PPH in pregnant women with sPE.Specifically,pregnant women with sPE who experienced blood loss exceeding 285 mL during vaginal delivery or 375 mL during caesarean section,along with a D-dimer level greater than 2.295 μg/mL,demonstrated an increased likelihood of developing PPH.Therefore,it is crucial to enhance clinical monitoring of these relevant indicators in high-risk populations.

Objective This study aimed to explore the ability of ultrasonographic radiomics in predicting the occurrence of in-stent restenosis(ISR)after carotid artery stenting(CAS)by analyzing the correlation between radiomic features of responsible plaques in carotid artery stenosis and the incidence of ISR.Methods A retrospective collection was conducted on 206 cases that underwent CAS treatment at our hospital.The enrolled patients were randomly split into a training set(144 cases)and a test set(62 cases)at a 7∶3 ratio.We utilized the Darwin Intelligent Research Platform to extract radiomic features from each region of interest,and then screened 1125 ultrasonographic radiomic features.Different machine learning algorithms were employed to construct diagnostic models,and the best-performing classifier was selected.Various prediction models were established,including a clinical-ultrasonographic feature model,a radiomic model,and a combined clinical-ultrasonographic-radiomic model.Results Multivariate logistic regression analysis in the training set revealed that hypertension,hyperuricemia,triglycerides,and plaque location were independent risk factors for ISR after CAS.For the clinical-ultrasonographic model,the area under the curve(AUC)values for the training and validation sets were 0.896 and 0.644,respectively.The corresponding AUC values for the radiomic model were 0.961 and 0.715,while those for the combined model were 0.947 and 0.727.Conclusion The radiomic model demonstrates superior performance in predicting ISR compared to the traditional clinical-ultrasonographic model.The combined model exhibited an enhanced ability to predict ISR occurrence,thereby improving the diagnostic performance of traditional assessments.

Objective To explore the influencing factors of acute kidney injury in severe burn patients,and to construct a visual risk nomogram model.Methods A total of 390 patients with severe burn admitted to the Institute of Burn Frostbite and Tissue Function Reconstruction of Chinese People's Armed Police Force Specialty Medical Center from January 2018 to January 2022 were collected as an internal training data set,and 50 patients with severe burn admitted from February to December 2022 were collected as an external validation data set.The 390 patients of the internal training data set were divided into the acute kidney injury group and the non-acute kidney injury group according to the occurrence of acute kidney injury,and the baseline data of patients in the two groups were compared.Univariate and multivariate Logistic regression were used to analyze the risk factors of acute kidney injury in severe burn patients of the internal training data set,and a nomogram model was drawn.Subsequently,the model was verified both internally and externally.Kaplan-Meier analysis and Log-rank test were used to compare the 90-day survival rate of patients between the acute kidney injury group and the non-acute kidney injury group.Results The burn area(OR=1.18,95%CI:1.06 to 2.36,P=0.004),sequential organ failure assessment(SOFA)score(OR=1.81,95%CI:1.21 to 5.92,P<0.001),inhalation injury(OR=3.21,95%CI:1.23 to 6.35,P<0.001),neutrophil to lymphocyte ratio(NLR)(OR=1.22,95%CI:1.05 to 3.65,P<0.001)and albumin(ALB)(OR=0.78,95%CI:0.57 to 0.92,P=0.011)were the independent risk factors for the development of acute kidney injury in severe burn patients.The nomogram model was established by the above factors.The area under the receiver operating characteristic curve(AUC)of the internal training data set was 0.833(95%CI:0.752 to 0.935),the sensitivity was 81.2%,and the specificity was 83.2%.The AUC of the external validation data set was 0.842(95%CI:0.762 to 0.912),the sensitivity 87.2%,and the specificity was 78.7%.The 90-day survival rate of patients in the acute kidney injury group after burns was significantly lower than that in the non-acute kidney injury group(P<0.001).Conclusion Larger burn area,higher SOFA score,combined inhalation injury,increased NLR,and decreased ALB level are the risk factors for the occurrence of acute kidney injury in severe burn patients,which are related to the 90-day survival rate of patients after burns.The nomogram model based on the risk factors can provide certain reference for clinical individualized prevention and treatment of acute kidney injury in severe burn patients.

A subset of patients with multiple myeloma(MM)present with reduced serum vitamin B12 levels at initial diagnosis;however,its clinical significance and underlying mechanisms remain unclear.Vitamin B12 plays a crucial role in hematopoiesis and immune regulation.This study aims to elucidate its association with extramedullary diseases,immune function,and prognosis in MM patients.A retrospec-tive analysis was conducted of 92 newly diagnosed MM patients,who received treatment at the Second Af-filiated Hospital of Soochow University between January 2020 and December 2023.Patients were classi-fied into a low vitamin B12 group(n=37)and a normal vitamin B12 group(n=55)based on their ser-um vitamin B12 levels.The findings revealed that the incidence of extramedullary infiltration was signifi-cantly higher in the low vitamin B12 group than in the normal group(26.5％vs.17.0％,P=0.031).Survival analysis demonstrated that patients with low vitamin B12 levels had significantly shorter overall survival(OS)and progression-free survival(PFS)(OS:P=0.0123;PFS:P=0.0136).Additionally,these patients showed a decreasing trend in peripheral blood total T cell,CD4+T cell,and CD8+T cell counts,with serum vitamin B12 levels showing a significant positive correlation with the total T cell count(R=0.2717,P=0.0135)and CD4+T cell count(R=0.2175,P=0.0497).In conclusion,reduced serum vitamin B12 levels at initial diagnosis are significantly associated with poor prognosis in MM pa-tients and may serve as a potential prognostic biomarker.Furthermore,vitamin B12 deficiency may con-tribute to immune dysfunction,particularly impaired T cell immunity,and a higher incidence of extr-amedullary diseases.

Objective:To observe the signal intensity and homogeneity of subretinal hyperreflective material (SHRM) in neovascular age-related macular degeneration (nAMD) and preliminarily analyze its relationship with macular neovascularization (MNV) morphology.Methods:A prospective cross-sectional observational study. Forty-six eyes of 46 nAMD patients with SHRM who initially visited Zhongshan Ophthalmic Center, Sun Yat-sen University from January 1, 2022 to March 31, 2023 were enrolled. Optical coherence tomography (OCT) examination was performed according to a standardized protocol, and 3D Slicer software was used for three-dimensional reconstruction of SHRM lesions. Signal intensity was represented by the mean gray value (mGV) of the three-dimensional lesion area, and homogeneity was represented by the standard deviation of gray values (GV-SD). OCT angiography (OCTA) was used to scan the 6 mm×6 mm area of the macula. FIJI and Angio Tool software were used to measure MNV vascular network total area, perimeter, maximum and minimum diameters, maximum vessel diameter, vascular component area, total number of vascular network junctions and endpoints, vessel dispersion, and mean lacunarity. The ratio of maximum to minimum diameter of the vascular network, average vessel length, vessel density, and vessel fractal index were calculated. Using the mean mGV of the total sample as the standard, the eyes were divided into low-density SHRM group (20 eyes) and high-density SHRM group (26 eyes); using the mean GV-SD of the total sample as the standard, the eyes were divided into homogeneous SHRM group (29 eyes) and non-homogeneous SHRM group (17 eyes). The morphological characteristics of MNV between groups were compared. Independent samples t-test or Mann-Whitney U test was used for between-group comparisons; a multivariate regression model was established to analyze independent factors affecting SHRM signal characteristics. Results:Among the 46 eyes of 46 patients, there were 26 eyes of 26 males (56.52%, 26/46) and 20 eyes of 20 females (43.48%, 20/26). The mean age was (65.61±7.50) years. The average vessel length and vessel dispersion in the high-density SHRM group and low-density SHRM group were (6.88±4.56), (11.30±6.31) mm ?1 and 41.30±67.26, 13.22±11.34, respectively. Compared with the low-density SHRM group, the high-density SHRM group had significantly lower average vessel length ( t=2.645) and higher vessel dispersion ( t=?2.090), with statistically significant differences ( P=0.012, 0.046). Compared with the homogeneous SHRM group, the non-homogeneous SHRM group had significantly higher total area ( t=?2.338), maximum diameter ( t=?3.137), and minimum diameter ( t=?2.173), with statistically significant differences ( P<0.05). The total number of vascular network junctions in the non-homogeneous SHRM group and homogeneous SHRM group were (90.71±67.34) and (49.34±41.91), respectively; the non-homogeneous SHRM group had significantly more junctions than the homogeneous SHRM group, with a statistically significant difference ( t=?2.286, P=0.032). Multivariate regression analysis showed that average vessel length was an independent factor affecting SHRM intensity (odds ratio=0.819, 95% confidence interval 0.705-0.951, P=0.009); there were no independent vascular indicators affecting SHRM reflectivity homogeneity ( P>0.05). Conclusion:In nAMD, compared with low-density SHRM, high-density SHRM has significantly lower average vessel length and higher vessel dispersion; compared with homogeneous SHRM, non-homogeneous SHRM has a larger spatial dimension of the vascular network.