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.

ObjectiveTo investigate the mechanism of topical treatment of allergic contact dermatitis （ACD） mice with Portulacae Herba based on the nuclear factor E₂-related factor 2 （Nrf2）/heme oxygenase-1 （HO-1）/nuclear factor-κB （NF-κB） signaling pathway. MethodsA total of 70 6-week-old specific pathogen free （SPF） female Kunming mice were adaptively fed for 1 week and randomly divided into blank group， model group， compound dexamethasone acetate cream group （2.075×10^-2 g·g^-1）， blank matrix cream group， low-dose Portulacae Herba cream group （0.1 g·g^-1）， high-dose Portulacae Herba cream group （0.2 g·g^-1）， and Portulacae Herba + inhibitor group （0.2 g·g^-1 + 30 mg·kg^-1 ML385）， with 10 mice in each group. One day before the experiment， the mice were shaved on the neck and back. Except for the blank group， the mice in the other groups were treated with 2，4-dinitrochlorobenzene （DNCB） to establish an ACD model. After respective administration， the skin lesion of the mice was scored， and the histopathological changes of the skin were stained with hematoxylin-eosin （HE）. Enzyme-linked immunosorbent assay （ELISA） was used to detect the levels of interleukin-6 （IL-6）， interleukin-1β （IL-1β）， reactive oxygen species （ROS）， superoxide dismutase （SOD） activity， and malondialdehyde （MDA） in serum of mice. The expression of Nrf2/HO-1/NF-κB signaling pathway-related proteins in mouse skin tissue was detected by immunohistochemistry （IHC）， Western blot， and real-time fluorescence quantitative polymerase chain reaction （Real-time PCR）. ResultsCompared with the blank group， the mice in the model group had an increased skin lesion score （P<0.01）， severe pathological damage to skin tissue， increased content of IL-1β， IL-6， ROS， and MDA in their serum （P<0.01）， and decreased content of SOD （P<0.01）. In addition， the mRNA and protein expression levels of Nrf2， HO-1， and nuclear factor-κB inhibitor α （IκBα） in skin tissue were up-regulated （P<0.01）， while the protein expression levels of phosphorylated （p）-IκBα and p-NF-κB p65 and the mRNA expression of NF-κB p65 were down-regulated （P<0.01）. Compared with the model group and the blank matrix cream group， the mice treated with Portulacae Herba had a decreased skin lesion score （P<0.01）， reduced pathological damage to skin tissue， decreased content of IL-1β， IL-6， ROS， and MDA in their serum （P<0.01）， and increased content of SOD （P<0.01）. Additionally， the mRNA and protein expression levels of Nrf2， HO-1， and IκBα in skin tissue were down-regulated （P<0.05，P<0.01）， and the protein expression levels of p-IκBα and p-NF-κB p65 and the mRNA expression of NF-κB p65 were up-regulated （P<0.05，P<0.01）. Compared with the Portulacae Herba + inhibitor group， the high-dose Portulacae Herba cream group had a decreased skin lesion score （P<0.01）， alleviated pathological damage to skin tissue， decreased content of IL-1β， IL-6， ROS， and MDA in the serum of mice （P<0.05，P<0.01）， and increased content of SOD （P<0.01）. The protein expression levels of Nrf2， HO-1， and IκBα and the mRNA expression of Nrf2 and HO-1 in skin tissue were up-regulated （P<0.05，P<0.01）， and the protein expression levels of p-IκBα and p-NF-κB p65 and the mRNA expression of NF-κB p65 were down-regulated （P<0.05）. ConclusionPortulacae Herba can improve DNCB-induced ACD skin damage in mice by regulating the Nrf2/HO-1/NF-κB signaling pathway.

ObjectiveThe research focuses on developing modeling and evaluation methodologies for an animal model exhibiting spleen deficiency and dampness excess syndrome， with the aim of standardizing such animal models for future reference. MethodsBy conducting a literature search on animal models of spleen deficiency and dampness excess syndrome， relevant publications meeting inclusion and exclusion criteria will be identified based on publication date， data source， types of diseases involved， animal characteristics， modeling methods， modeling duration， macroscopic syndrome assessment indicators， macroscopic quantification indicators， laboratory testing parameters， intervention approaches， positive controls and application context. A database will be established to facilitate the extraction of this information for quantitative analysis， statistical evaluation， and visual representation. ResultsA total of 137 literature articles meeting the standards have been included in the research. The primary animal species used in animal models of spleen deficiency and dampness excess are SD rats. Modeling methods include single-factor， dual-factor composite， and triple-factor composite methods， with various models widely applied in validation of pharmacological effects and mechanistic explorations. Evaluation indices of animal models for spleen deficiency and dampness excess primarily consist of macroscopic syndrome evaluation indicators and macroscopic quantitative indicators. Laboratory testing indicators are mostly related to research areas such as fluid metabolism and gastrointestinal function. The most commonly studied herbal formulas currently include Shenling Baizhu San and Pingwei San， with natural recovery and the use of the western medicine metronidazole as the most frequently used positive controls. ConclusionThe application of animal models for spleen deficiency and dampness excess is gradually increasing， with various modeling methods already simulating the typical characteristics of this syndrome pattern. However， there are still many areas that are worth contemplating and improving. This study aims to provide reference and ideas for the standardization of symptom names in animal models of spleen deficiency and dampness excess， as well as for the improvement of model construction and evaluation systems.

ObjectiveTo explore the effect of modified Ditan Decoction （涤痰汤） on chronic intermittent hypoxia cognitive function and the potential function mechanism. MethodsTwenty-four Sprague-Dawley （SD） rats were randomly divided into a normal group， a model group， and a modified Ditan Decoction group， with eight rats in each group. Rats in the modified Ditan Decoction group were administered the decoction by gavage at 14.8 ml/（kg·d）， while the normal group and the model group received the same dose of normal saline. Thirty minutes after daily gavage， the rats in all three groups were placed in an intermittent hypoxia chamber. The oxygen concentration for the model group and the modified Ditan Decoction group was adjusted daily for 8 hours using a computer program to establish the model， while the normal group was exposed to the same airflow rate of ambient air. The intervention was continued for 12 weeks to establish a chronic intermittent hypoxia rat model. The Y-maze test was used to evaluate spatial working memory in the rats. Resting-state functional magnetic resonance imaging （rs-fMRI） was performed to detect whole-brain regional homogeneity （ReHo） and seed-based functional connectivity （FC）. Brain regions showing significant differences in rs-fMRI were selected for further analysis. Immunofluorescence was used to detect β-amyloid （Aβ） deposition and the number of ionized calcium-binding adapter molecule 1 （IBA1）-positive microglial cells. Immunohistochemistry was employed to assess the expression of synaptophysin （SYP）， the excitatory synapse marker vesicular glutamate transporter 1 （Vglut1）， and the inhibitory synapse marker vesicular γ-aminobutyric acid transporter （VGAT）. ResultsCompared with the normal group， the model group showed a reduced spontaneous alternation rate in the Y-maze test. The smoothed Z-score standardized regional homogeneity （SzReHo） value in the left entorhinal cortex significantly increased， and the FC value from this seed point to the left basal forebrain significantly reduced. Additionally， the model group exhibited significantly higher Aβ fluorescence intensity and Iba1 positivity in the left entorhinal cortex， decreased expression of SYP， Vglut1， and VGAT， along with an increased Vglut1/VGAT ratio （P＜0.05 or P＜0.01）. Compared to the model group， the modified Ditan Decoction group demonstrated an increased spontaneous alternation rate， a significantly reduced SzReHo value in the left entorhinal cortex， and a significantly increased FC value from this region to the left basal forebrain. Furthermore， this group showed significantly lower Aβ fluorescence intensity and Iba1 positivity in the left entorhinal cortex， increased levels of SYP， Vglut1， and VGAT， and a decreased Vglut1/VGAT ratio （P＜0.05 or P＜0.01）. ConclusionModified Ditan Decoction can reconstruct the projection from the left basal forebrain to the entorhinal cortex in chronic intermittent hypoxia， thereby reducing Aβ aggregation and excessive microglial activation in the left entorhinal cortex. This process improves the excitation/inhibition imbalance caused by synaptic remodeling， ultimately enhancing cognitive function in rats of chronic intermittent hypoxia.

By examining the records related to the Fengfu （GV 16） acupoint in BIAN Que Heart Book （《扁鹊心书》） compiled by the Song Dynasty physician DOU Cai， this study analyzed various aspects， including the differentiation of conditions treated with Fengfu （GV 16） acupoint， the theoretical foundation for selection of Fengfu （GV 16） acupoint， the application of needling manipulation， and the sensation of obtaining qi during acupuncture. The findings suggest that DOU Cai's approach to utilizing Fengfu （GV 16） acupoint differs from traditional methods， particularly emphasizing the effectiveness of achieving a sensation of heat and numbness. His unique techniques include transverse insertion at Fengfu （GV 16） acupoint and penetrated insertion to Fengchi （GB 20） and Yifeng （TE 17） acupoints. The records of Fengfu （GV 16） acupoint in BIAN Que Heart Book provide a valuable reference for its modern clinical application and further development.

ObjectiveTo explore the mechanism of Shaoyaotang in the prevention and treatment of colitis-associated carcinogenesis （CAC） based on myeloid-derived suppressor cells （MDSCs）-related immunosuppressive microenvironment. MethodsA total of 140 six-week-old SPF FVB male mice were randomly divided into seven groups： Blank group， Shaoyaotang without model group （7.12 g·kg^-1）， model group， sulfasalazine group （0.52 g·kg^-1）， Shaoyaotang low-dose group （3.56 g·kg^-1）， Shaoyaotang medium-dose group （7.12 g·kg^-1） and Shaoyaotang high-dose group （14.24 g·kg^-1）， with 20 mice in each group. The blank control group and the Shaoyaotang without model group received a single intraperitoneal injection of physiological saline （10 mg·kg^-1）， while the other five groups were given a single intraperitoneal injection of azoxymethane （AOM） （10 mg·kg^-1）. After 1 week， the mice were given drinking water containing 2% dextran sulfate sodium （DSS） for 1 week， followed by normal drinking water for 2 weeks. This cycle was repeated three times over a total period of 14 weeks to establish the CAC mouse model. Each group was administered gavage once daily for 2 weeks starting on the 14^th day of the experiment， followed by three times a week until the end of the experiment. The body weight of the mice was recorded weekly. Mice were sacrificed on the 28^th and 98^th days of the experiment. After dissection， the colon length， colon weight， spleen weight， tumor size， and tumor number were measured. Hematoxylin and eosin （HE） staining was used to assess the pathological morphology of colon tumor tissue. Flow cytometry was used to detect MDSCs， regulatory T cells （Tregs）， CD4⁺ T cells， CD8⁺ T cells， and the CD4⁺/CD8⁺ T cell ratio in the spleen. Immunohistochemistry was used to detect the expression levels of programmed cell death protein-1 （PD-1）， programmed cell death ligand 1 （PD-L1）， phosphorylated AMP-activated protein kinase （p-AMPK）， phosphorylated nuclear factor-κB （p-NF-κB）， and hypoxia-inducible factor 1α （HIF-1α） in the colon tissue. ResultsOn day 14， compared with the blank group， the body weight of the model group was significantly reduced （P<0.01）， reaching its lowest point on day 28 （23.39 ± 0.95 ） g. On days 28 and 98， compared with the blank group， the colon length in the model group was significantly shortened （P<0.01）， the colon index significantly increased （P<0.01）， the spleen index significantly increased （P<0.01）， and the tumor load significantly increased （P<0.01）. HE staining showed that in the model group， tumor cells， a large number of inflammatory cell infiltrates， goblet cell disappearance， and crypt loss were observed. In each dose group of Shaoyaotang， the damage to the colonic mucosa， inflammatory cell infiltration， and crypt structure destruction were alleviated. Compared with the model group， the body weight of mice in each dose group of Shaoyaotang increased. On day 98， the colon length was significantly increased （P<0.01）， the colon index significantly decreased （P<0.01）， the spleen index significantly decreased （P<0.01）， and the tumor burden significantly decreased （P<0.01） in each Shaoyaotang dose group. On days 28 and 98， MDSCs and Tregs in the spleen of the medium- and high-dose Shaoyaotang groups were significantly reduced （P<0.01）， while CD4⁺ T cells and the CD4⁺/CD8⁺ T cell ratio were significantly increased （P<0.01）. The proportion of CD8⁺ T cells in the spleen and the expression levels of PD-1 and PD-L1 in the colon tissues of mice in each Shaoyaotang dose group were significantly increased to varying degrees （P<0.05， P<0.01）. On days 28 and 98， the expression of p-AMPK-positive cells in the colon tissue of the medium- and high-dose Shaoyaotang groups was significantly increased （P<0.01）， while the expression of p-NF-κB and HIF-1α was significantly reduced （P<0.01）. ConclusionShaoyaotang can regulate MDSC recruitment and modulate the immune function of T lymphocyte subsets to inhibit the occurrence and development of AOM/DSS-induced CAC in mice. The mechanism may be related to the activation of the AMPK/NF-κB/HIF-1α pathway.

ObjectiveTo clarify the anti-inflammatory and lung-protective effects of Yantiao prescription on lipopolysaccharide （LPS）-induced acute lung injury （ALI）， and to explore the impact of Yantiao prescription on the metabolic pathways of arachidonic acid （AA） in vivo. MethodsThirty male C57BL/6J mice were randomly divided into the following groups based on body weight： normal group， model group， dexamethasone group （2 mg·kg^-1）， low-dose Yantiao prescription group （18 g·kg^-1）， and high-dose Yantiao prescription group （36 g·kg^-1）， with 6 mice in each group. The ALI mouse model was established by intraperitoneal injection of LPS. The treatment groups received oral gavage once a day for 7 consecutive days， and serum and lung tissue were collected at the end of the experiment. The content of pro-inflammatory cytokines tumor necrosis factor-α （TNF-α）， interleukin-1β （IL-1β）， and interleukin-6 （IL-6） in serum was detected by enzyme-linked immunosorbent assay （ELISA）. Hematoxylin-eosin （HE） staining was used to assess lung tissue pathology. The wet/dry weight ratio （W/D） and myeloperoxidase （MPO） activity in lung tissue were measured. The content of AA metabolites in serum and lung tissue was measured by liquid chromatography triple quadrupole-mass spectrometry （LC-MS/MS）. ResultsCompared with the conditions in the normal group， the content of serum pro-inflammatory cytokines TNF-α， IL-1β， and IL-6 in the model group was significantly increased （P<0.01）. The alveolar structure in mice was severely damaged， with markedly thickened alveolar walls and extensive inflammatory cell infiltration. The W/D ratio and MPO activity in lung tissue were significantly increased （P<0.01）. The content of AA metabolites， including prostaglandin D₂ （PGD₂）， prostaglandin E₂ （PGE₂）， 11（S）-hydroxy-eicosatetraenoic acid ［11（S）-HETE］， and 5-hydroxy-eicosatetraenoic acid （5-HETE） in serum and lung tissue was significantly increased （P<0.05）， while the content of 11，12-epoxyeicosatrienoic acid （11，12-EET） and 14，15-epoxyeicosatrienoic acid （14，15-EET） in serum was significantly decreased （P<0.01）. Compared with the results in the model group， the content of serum pro-inflammatory cytokines TNF-α， IL-1β， and IL-6 in the dexamethasone group， low-dose Yantiao prescription group， and high-dose Yantiao prescription group was significantly reduced （P<0.05）. Mild thickening of alveolar walls， scattered inflammatory cell infiltration， and relatively intact tissue structure with improved alveolar architecture were observed. The W/D ratio and MPO activity in lung tissue were significantly reduced （P<0.01）. The content of AA metabolites PGD₂， PGE₂， 11（S）-HETE， and 5-HETE in serum from the dexamethasone group was significantly decreased （P<0.05）， while the content of 14，15-EET in serum significantly increased （P<0.01）， and the content of 5-HETE in lung tissue significantly decreased （P<0.01）. In the low-dose and high-dose Yantiao prescription groups， the content of AA metabolites PGD₂， PGE₂， 11（S）-HETE， and 5-HETE in serum and lung tissue was significantly decreased （P<0.05）， while the content of 11，12-EET in both serum and lung tissue was significantly increased （P<0.05）. ConclusionYantiao prescription has significant protective effects against LPS-induced ALI， which are related to its regulation of AA metabolic pathways in vivo.