ObjectiveTo address the challenges of unstructured classical Chinese expressions， nested entity relationships， and limited annotated data in famous traditional Chinese medicine（TCM） case records， this study proposes a joint relation extraction framework that integrates data augmentation and entity mapping， aiming to support the construction of TCM diagnostic knowledge graphs and clinical pattern mining. MethodsWe developed an annotation structure for entities and their relationships in TCM case texts and applied a data augmentation strategy by incorporating multiple ancient texts to expand the relation extraction dataset. A cascade binary tagging framework for relation triple extraction（CasRel） model for TCM semantics was designed， integrating a pre-trained bidirectional encoder representations from transformers（BERT） layer for classical TCM texts to enhance semantic representation， and using a head entity-relation-tail entity mapping mechanism to address entity nesting and relation overlapping issues. ResultsExperimental results showed that the CasRel model， combining data augmentation and entity mapping， outperformed the pipeline-based Bert-Radical-Lexicon（BRL）-bidirectional long short-term memory（BiLSTM）-Attention model. The overall precision， recall， and F₁-score across 12 relation types reached 65.73%， 64.03%， and 64.87%， which represent improvements of 14.26%， 7.98%， and 11.21% compared to the BRL-BiLSTM-Attention model， respectively. Notably， the F₁-score for tongue syndrome relations increased by 22.68%（69.32%）， and the prescription-syndrome relations performed the best with the F₁-score of 70.10%. ConclusionThe proposed framework significantly improves the semantic representation and complex dependencies in TCM texts， offering a reusable technical framework for structured mining of TCM case records. The constructed knowledge graph can support clinical syndrome differentiation， prescription optimization， and drug compatibility， providing a methodological reference for TCM artificial intelligence research.

This paper summarizes Professor LU Fang's clinical experience in treating systemic lupus erythematosus （SLE） based on the differentiation and treatment of heat-toxin and blood-stasis in the collaterals. SLE is generally characterized by deficiency in origin with excess in manifestation. The core pathogenesis is heat-toxin obstructing the collaterals. During the acute active stage， the predominant pattern is blazing heat-toxin causing blood stasis， while in the chronic remitting stage， the main pattern is toxic stasis blocking the collaterals with qi and yin deficiency. Clinical treatment follows the basic principle that treat with salty-cold herbs， when heat invades internally and that assist with acrid-dispersing herbs when stasis obstructs the collaterals. The self-formulated Yimian Decoction （抑免汤） serves as the base formula and is applied in stages. During the acute active stage， it is often combined with herbs for clearing heat and detoxifying， cooling blood and resolving stasis， and unblocking the collaterals. In the chronic remitting stage， it is often combined with herbs for activating blood circulation and unblocking the collaterals， as well as tonifying qi and nourishing yin.

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 predictive value of different machine learning models constructed in a multicenter environment for potential organ donors and verify their clinical application feasibility. Methods The study included 2 000 inpatients admitted to five domestic tertiary hospitals from January 2020 to December 2023, who met the criteria for potential organ donation assessment. They were randomly divided into a training set and an internal validation set (7∶3). Another 300 similar patients admitted to the First Affiliated Hospital of Harbin Medical University from January 2024 to April 2025 were included as an external validation set. The area under the curve (AUC), sensitivity, specificity, accuracy and F1-score of three models were compared, and the consistency of the potential organ donor determination process was tested. Multivariate logistic regression analysis was used to identify predictive factors of potential organ donors. Decision curve analysis (DCA) was employed to verify the resource efficiency of each model, and the threshold interval and intervention balance point were assessed. Results Apart from age, there were no significant differences in other basic characteristics among the centers (all P>0.05). The consistency of the potential organ donor determination process among researchers in each center was good [all 95% confidence interval (CI) lower limits >0]. In the internal validation set, the XGBoost model had the best predictive performance (AUC=0.92, 95% CI 0.89-0.94) and the best calibration (P=0.441, Brier score 0.099). In the external validation set, the XGBoost model also had the best predictive performance (AUC=0.91, 95% CI 0.88-0.94), outperforming logistic regression and random forest models. Multivariate logistic regression showed that mechanical ventilation had the greatest impact (odds ratio=2.06, 95% CI 1.54-2.76, P<0.001). DCA indicated that the XGBoost model had the highest net benefit in the threshold interval of 0.2-0.6. The “treat all” strategy only had a slight advantage at extremely low thresholds. The recommended threshold interval, which balances intervention costs and clinical benefits, considers ≥50% positive predictive value (PPV) and ≤50 referrals per 100 high-risk patients. Conclusions The XGBoost model established in a multicenter environment is accurate and well-calibrated in predicting potential organ donors. Combined with DCA, it may effectively guide the timing of clinical interventions and resource allocation, providing new ideas for the assessment and management of organ donation after brain death.

To explore the advantages of traditional Chinese medicine （TCM） and integrative TCM-Western medicine approaches in the treatment of diabetic microvascular complications （DMC）， refine key pathophysiological insights and treatment principles， and promote academic innovation and strategic research planning in the prevention and treatment of DMC. The 38th session of the Expert Salon on Diseases Responding Specifically to Traditional Chinese Medicine， hosted by the China Association of Chinese Medicine， was held in Beijing， 2024. Experts in TCM， Western medicine， and interdisciplinary fields convened to conduct a systematic discussion on the pathogenesis， diagnostic and treatment challenges， and mechanism research related to DMC， ultimately forming a consensus on key directions. Four major research recommendations were proposed. The first is addressing clinical bottlenecks in the prevention and control of DMC by optimizing TCM-based evidence evaluation systems. The second is refining TCM core pathogenesis across DMC stages and establishing corresponding "disease-pattern-time" framework. The third is innovating mechanism research strategies to facilitate a shift from holistic regulation to targeted intervention in TCM. The fourth is advancing interdisciplinary collaboration to enhance the role of TCM in new drug development， research prioritization， and guideline formulation. TCM and integrative approaches offer distinct advantages in managing DMC. With a focus on the diseases responding specifically to TCM， strengthening evidence-based support and mechanism interpretation and promoting the integration of clinical care and research innovation will provide strong momentum for the modernization of TCM and the advancement of national health strategies.

ObjectiveTo explore the effect of elbow-wrist functional orthosis on plantar pressure distribution and balance function in stroke patients with hemiplegia. MethodsFrom June, 2024 to April, 2025, 60 patients with post-stroke hemiplegia were recruited from Huashan Hospital, Fudan University, and Shanghai Hebin Rehabilitation Hospital. They were randomly divided into control group (n = 30) and intervention group (n = 30). The control group received routine neurological rehabilitation, while the intervention group received additional training with an elbow-wrist functional orthosis on the affected side, for eight weeks. Before and after intervention, the Modified Ashworth Scale (MAS) of the elbow joint, plantar pressure symmetry index (SI), plantar contact area and mean plantar pressure were recorded, and balance and mobility were assessed using the Berg Balance Scale (BBS), Timed Up & Go Test (TUGT) and 10-Meter Walk Test (10MWT). ResultsTwo cases dropped out in the control group. After treatment, MAS grades of the elbow joint, forefoot SI, affected side plantar pressure area, BBS scores, TUGT and 10MWT of both groups improved (|Z| > 3.969, |t| > 3.528, P < 0.01), while the hindfoot SI and average pressure of the affected foot improved in the intervention group (∣t∣ > 4.264, P < 0.001). Except for TUGT and 10MWT, the intervention group was superior to the control group (∣Z∣ > 2.030, ∣t∣ > 2.096, P < 0.05). ConclusionThe elbow-wrist functional orthosis can enhance balance function in stroke patients with hemiplegia by reducing upper-limb spasticity, optimizing center-of-gravity distribution, and improving postural control.

ObjectiveTo conduct a theoretical study on the medical-rehabilitation integration. MethodsStarting from the background, objectives and content of the medical-rehabilitation integration, this study analyzed its innovative points from the dimensions of conceptual innovation, organizational innovation, model innovation and technological innovation. Results and ConclusionThe medical-rehabilitation integration is an innovation in medical services that takes conceptual innovation as the forerunner, organizational innovation as the foundation, model innovation as the carrier and technological innovation as the core.

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.

Objective: To explore the relative importance of different food attributes and levels in food decision making of school aged children, and to understand their meal preferences, so as to provide the evidence for formulating precise intervention strategies for dietary behaviours of school aged children. Methods: From May to June 2024, a total of 854 children aged 11 to 15 years old were selected from 2 middle schools (each school in urban and rural areas) in both Hubei Province and Anhui Province by stratified cluster random sampling method to conduct a D-optimal discrete choice experiment. The mixed Logit model was used to analyze children s preference for meal attributes and different levels, and to calculate the relative importance (RI) of attributes and willingness to pay (WTP) in meal choices. Results: The included five food attributes had statistical significance on meal choice of school aged children ( P <0.05). The relative importance of food attributes affecting the meal choices of school aged children in descending order were dining mode ( RI =31.26%), food varieties ( RI =30.56%), cooking method( RI =23.84%), taste( RI =8.06%) and price ( RI =6.27%). Among them, school aged children preferred home cooked meals ( β =0.74) (WTP=86.3 yuan),varied foods(grain/tubers+vegetables+fish, meat, eggs and beans) ( β =0.61) (WTP=71.9 yuan), fried/roasted cooking ( β =0.51) and spicy taste ( β =0.33).Price was negatively correlated with meal choices( β =-0.01) ( P <0.05). Based on residential area and body mass index (BMI), the stratified analysis showed that dining mode was highest in the relative importance for rural children with overweight and obese children ( RI =31.28%,34.17%), both of whom preferred home cooked meals ( β =0.76, 0.91), and meals containing fish, meat, eggs and beans with grain/tubers or grain/tubers and vegetables in terms of food choice (area: β =0.53, 0.53 ; BMI: β =0.55, 0.56) ( P <0.05). Conclusions School aged children have different preferences for different attributes of meals. The quality of school meals should be improved,the cost of buying healthy meals should be reduced,targeted family health education should be carried out,and healthy cooking methods should be advocated.

OBJECTIVE To investigate the protective effect and mechanism of saikosaponin C （SSC） on acute liver injury （ALI） in mice induced by carbon tetrachloride （CCl4） based on serum metabolomics. METHODS Forty mice were divided into blank group （water）， model group （water）， positive control drug group （Biphenyl diester drop pills， 150 mg/kg）， and SSC low- and high-dose groups （2.5， 10 mg/kg） using the random number table method， with 8 mice in each group. They were given water/ relevant drugs， once a day， for 7 consecutive days. One hour after the last administration， all mice were intraperitoneally injected with 0.2% CCl4 olive oil to induce ALI model， except for the blank group. After 17 hours of the modeling， the liver index of mice was calculated. The levels of aspartate aminotransferase （AST）， alanine aminotransferase （ALT）， lactate dehydrogenase （LDH）， tumor necrosis factor-α （TNF-α）， interleukin-6 （IL-6）， and IL-1β in serum of mice were detected. The histopathological changes of liver tissue were observed. Meanwhile， the serum metabolomics of mice were analyzed by liquid chromatography-mass spectrometry. RESULTS Compared with the blank group， the levels of liver index， ALT， AST， LDH， TNF-α， IL-6， and IL-1β in the model group were significantly increased （P＜0.01）. Hepatocytes were edema， vacuolar degeneration， more necrosis， and a large number of inflammatory cells were infiltrated. Compared with the model group， liver index and serum index levels of mice were significantly decreased （P＜0.05 or P＜0.01）， accompanied by marked improvement in histopathological damage to the liver tissue. The metabolomics results showed that compared with the model group， there were 63 up-regulated and 256 down-regulated differential metabolites in the serum of mice in the SSC high-dose group， including prostaglandin B2， 20-hydroxy-leukotriene B4， 5- hydroxy-L-tryptophan， 7α -hydroxycholesterol， etc.； these metabolites were primarily involved in metabolic pathways such as arachidonic acid metabolism， 5-hydroxytryptamine synapse， primary bile acid biosynthesis. CONCLUSIONS SSC exerts a protective effect against CCl4-induced ALI by down-regulating the level of key metabolites such as prostaglandin B2 and 20-hydroxy-leukotriene B4， and then ruducing metabolic pathways such as arachidonic acid metabolism， 5- hydroxytryptamine synapse， and primary bile acid biosynthesis.