OBJECTIVE To construct a preoperative medication reconciliation model assisted by a localized large language model （LLM） for gastric cancer and evaluate its clinical efficacy. METHODS A total of 249 gastric cancer patients with a history of continuous medication before admission in the Gastric Surgery Department of Jiangsu Cancer Hospital were retrospectively enrolled. Patients were divided into training set （154 cases） and validation set （95 cases） based on the order of time. Based on guidelines， drug package inserts， and other evidence， a standardized medication reconcili ation process and a structured knowledge base were constructed. DeepSeek-V3 LLM was deployed privately in the hospital， combined with retrieval-augmented generation technology， to achieve automated integration of medication information， risk screening， and generation of personalized recommendations. The quality of LLM-generated recommendations was evaluated using automatic metrics （BERT Score and ROUGE-1， 2， L） and manual scoring [seven-dimensional index （7DI） ] . Spearman correlation analysis was performed to explore the correlation between automatic scores and manual scores. Cronbach’s α coefficient was used to test the internal consistency of manual scoring results. The time consumed by manual and LLM-assisted medication reconciliation was compared across tasks of different difficulty levels （simple， moderate， and high）. RESULTS A structured knowledge base covering 8 major drug categories was finally established， covering common and high-risk preoperative medication scenarios and providing structured retrieval support for the LLM. For automatic evaluation， the precision， recall， and F1-score of BERT Score were 0.783±0.033， 0.811±0.038， and 0.796±0.028， respectively. The F1-scores of ROUGE-1， ROUGE-2 and ROUGE-L were 0.566±0.067， 0.338±0.076 and 0.468±0.082， respectively. The 7DI scores from three manual raters ranged from 32.06 to 33.45. The F1-score of automatic scoring was significantly positively correlated with the 7DI score of manual scoring （maximum coefficient of determination＝0.611， P ＜0.001）， and the internal consistency of manual scoring was good （Cronbach’s α ＝ 0.876）. In terms of efficiency， LLM-assisted medication reconciliation reduced time consumption by more than 90% compared with manual reconciliation in the simple， moderate， and high-difficulty groups （ P ＜0.001）. CONCLUSIONS The medication reconciliation model constructed based on a localized LLM and structured knowledge base shows high accuracy， consistency， and clinical applicability in complex preoperative medication scenarios for gastric cancer. It can improve the efficiency of medication reconciliation and reduce potential medication risks.

Natural product-based drug combinations (NPDCs) present distinctive advantages in treating complex diseases. While high-throughput screening (HTS) and conventional computational methods have partially accelerated synergistic drug combination discovery, their applications remain constrained by experimental data fragmentation, high costs, and extensive combinatorial space. Recent developments in artificial intelligence (AI), encompassing traditional machine learning and deep learning algorithms, have been extensively applied in NPDC identification. Through the integration of multi-source heterogeneous data and autonomous feature extraction, prediction accuracy has markedly improved, offering a robust technical approach for novel NPDC discovery. This review comprehensively examines recent advances in AI-driven NPDC prediction, presents relevant data resources and algorithmic frameworks, and evaluates current limitations and future prospects. AI methodologies are anticipated to substantially expedite NPDC discovery and inform experimental validation.
Artificial Intelligence ; Biological Products/chemistry* ; Humans ; Drug Combinations ; Drug Discovery/methods* ; Machine Learning ; Algorithms

Temporomandibular joint osteoarthritis (TMJ-OA) is a common disease often accompanied by pain, seriously affecting physical and mental health of patients. Abnormal innervation at the osteochondral junction has been considered as a predominant origin of arthralgia, while the specific mechanism mediating pain remains unclear. To investigate the underlying mechanism of TMJ-OA pain, an abnormal joint loading model was used to induce TMJ-OA pain. We found that during the development of TMJ-OA, the increased innervation of sympathetic nerve of subchondral bone precedes that of sensory nerves. Furthermore, these two types of nerves are spatially closely associated. Additionally, it was discovered that activation of sympathetic neural signals promotes osteoarthritic pain in mice, whereas blocking these signals effectively alleviates pain. In vitro experiments also confirmed that norepinephrine released by sympathetic neurons promotes the activation and axonal growth of sensory neurons. Moreover, we also discovered that through releasing norepinephrine, regional sympathetic nerves of subchondral bone were found to regulate growth and activation of local sensory nerves synergistically with other pain regulators. This study identified the role of regional sympathetic nerves in mediating pain in TMJ-OA. It sheds light on a new mechanism of abnormal innervation at the osteochondral junction and the regional crosstalk between peripheral nerves, providing a potential target for treating TMJ-OA pain.
Animals ; Osteoarthritis/physiopathology* ; Mice ; Sympathetic Nervous System/physiopathology* ; Temporomandibular Joint Disorders/physiopathology* ; Arthralgia ; Sensory Receptor Cells ; Disease Models, Animal ; Norepinephrine ; Male ; Temporomandibular Joint/physiopathology* ; Pain Measurement

Ferroptosis of chondrocytes is a significant contributor to osteoarthritis (OA), for which there is still a lack of safe and effective therapeutic drugs targeting ferroptosis. Here, we screen for anti-ferroptotic drugs in Food and Drug Administration (FDA)-approved drug library via a high-throughput manner in chondrocytes. We identified a group of FDA-approved anti-ferroptotic drugs, among which vitamin K showed the most powerful protective effect. Further study demonstrated that vitamin K effectively inhibited ferroptosis and alleviated the extracellular matrix (ECM) degradation in chondrocytes. Intra-articular injection of vitamin K inhibited ferroptosis and alleviated OA phenotype in destabilization of the medial meniscus (DMM) mouse model. Mechanistically, transcriptome sequencing and knockdown experiments revealed that the anti-ferroptotic effects of vitamin K depended on growth arrest-specific 6 (Gas6). Furthermore, exogenous expression of Gas6 was found to inhibit ferroptosis through the AXL receptor tyrosine kinase (AXL)/phosphatidylinositol 3-kinase (PI3K)/AKT serine/threonine kinase (AKT) axis. Together, we demonstrate that vitamin K inhibits ferroptosis and alleviates OA progression via enhancing Gas6 expression and its downstream pathway of AXL/PI3K/AKT axis, indicating vitamin K as well as Gas6 to serve as a potential therapeutic target for OA and other ferroptosis-related diseases.

Tumor microenvironment(TME)is the cellular environment for tumor development,growth,and metastasis.Adenosine(ADO)is an immunosuppressive metabolic product that is continuously upregulated in TME,with various types and wide distribution of receptors.The complex and dynamic interactions between ADO and tumor cells constantly influence tumor progression.ADO can di-rectly or indirectly promote tumor development and progression by promoting tumor generation and metastasis,mediating the immune escape of tumor,and modulating tumor-infiltrating immune cells.Based on the characteristics of ADOs in TME,this article reviews the latest advances in the dynamic alterations of ADO in TME,in order to provide insights into tumor treatment targeting the ADO pathway.

Ferroptosis of chondrocytes is a significant contributor to osteoarthritis(OA),for which there is still a lack of safe and effective therapeutic drugs targeting ferroptosis.Here,we screen for anti-ferroptotic drugs in Food and Drug Administration(FDA)-approved drug library via a high-throughput manner in chondrocytes.We identified a group of FDA-approved anti-ferroptotic drugs,among which vitamin K showed the most powerful protective effect.Further study demonstrated that vitamin K effectively inhibited ferroptosis and alleviated the extracellular matrix(ECM)degradation in chondrocytes.Intra-articular injection of vitamin K inhibited ferroptosis and alleviated OA phenotype in destabilization of the medial meniscus(DMM)mouse model.Mechanistically,transcriptome sequencing and knockdown experiments revealed that the anti-ferroptotic effects of vitamin K depended on growth arrest-specific 6(Gas6).Furthermore,exogenous expression of Gas6 was found to inhibit ferroptosis through the AXL receptor tyrosine kinase(AXL)/phosphatidylinositol 3-kinase(PI3K)/AKT serine/threonine kinase(AKT)axis.Together,we demonstrate that vitamin K inhibits ferroptosis and alleviates OA progression via enhancing Gas6 expression and its downstream pathway of AXL/PI3K/AKT axis,indicating vitamin K as well as Gas6 to serve as a potential therapeutic target for OA and other ferroptosis-related diseases.

ObjectiveThis study explores the efficacy and pharmacological mechanism of Wujiwan in rats with inflammatory bowel disease （IBD） from the perspectives of the peroxisome proliferator-activated receptor γ （PPARγ） signaling pathway and T-cell immunity， providing reference for the treatment of IBD with traditional Chinese medicine. MethodThe study involved administering 2，4，6-trinitrobenzenesulfonic acid （TNBS） enemas to 35 rats to induce acute IBD. After 24 hours， the animals were divided into the following groups： normal group， model group， Wujiwan treatment group， and positive drug control group. Each group received gastric gavage for 8 consecutive days before the rats were dissected to compare the disease activity index （DAI） of the rat colon tissue， the colon mucosal damage index （CMDI）， and the spleen index. Enzyme-linked immunosorbent assay （ELISA） was used to measure the levels of interleukin-1β （IL-1β）， interleukin-10 （IL-10）， and tumor necrosis factor-α （TNF-α） in the serum. Quantitative real-time polymerase chain reaction （Real-time PCR） was used to determine the mRNA expression levels of T-bet （T-box expressed in T cells） and Gata3 （Gata-binding protein-3） in the colon tissue. Western blot analysis was conducted to detect the protein expression levels of PPARγ， T-bet， and nuclear factor-κB p65 （NF-κB p65） in the rat colon. ResultThe rat model of IBD was successfully established. Compared with the model group， the Wujiwan treatment group showed reduced DAI， CMDI， and spleen index， decreased content of TNF-α in the serum（P<0.01）， significantly increased content of IL-10（P<0.01）， and elevated mRNA content of T-bet and Gata3（P<0.05） in the colon tissue. The expression of PPARγ protein was augmented（P<0.05）， and the expression of T-bet and NF-κB p65 protein was decreased（P<0.05，P<0.01）. ConclusionWujiwan activates or upregulates PPARγ expression in IBD rats to inhibit the generation of pro-inflammatory factors， participates in the inflammatory immune process， and alleviates inflammatory reactions. Its mechanism may involve regulating the NF-κB pathway through PPARγ， enhancing Th2 cell transcription expression， and reducing Th1 cell transcription.

Traditional Chinese medicine （TCM） has a long history of application in China and has consistently played a vital role in treating diseases and saving lives. TCM prescriptions （compounds） constitute the primary form of clinical TCM treatment and significantly differ from western medicine （chemicals） due to the diverse composition and chemical constituents of TCM （compounds）. Nevertheless， the potential multi-component， multi-target， and multi-pathway action characteristics of TCM prescriptions also demonstrate their possible （complementary） therapeutic advantages when compared with single-component chemical drugs. Therefore， driven by the development of modern science and technology and the demands of the modernization and internationalization of TCM， modern theories regarding the complexity of TCM prescription effects have been continuously proposed： Different from the abstract language of traditional prescription theory， the modern TCM prescription theory is more inclined to illustrate the connotation of prescription compatibility concretely and vividly from an experimental and scientific perspective. In this paper， new theories on the complexity of TCM prescriptions proposed in recent years are summarized to provide research references and ideas for the greater role of TCM prescriptions and a better scientific understanding.

ObjectiveTo investigate the influencing factors for rebleeding after endoscopic therapy and the effect of the number of sequential treatment sessions on postoperative rebleeding in patients with liver cirrhosis receiving secondary prevention of gastroesophageal varices （GOV）. MethodsA total of 1 717 patients with liver cirrhosis who received secondary prevention of GOV and attended The 960th Hospital of the PLA Joint Logistice Support Force from January 2017 to December 2021 were enrolled， and according to the presence or absence of bleeding after endoscopic therapy， they were divided into non-bleeding group and rebleeding group. The influencing factors for rebleeding were analyzed， as well as the association between the number of endoscopic treatment sessions and rebleeding. The chi-square test was used for comparison of categorical data between groups； the independent-samples t test or the Mann-Whitney U test was used for comparison of continuous data between the two groups； the Kruskal-Wallis H test was used for comparison bertween multiple groups， and the Wilcoxon test was used for further comparison between two groups. The Cox regression model was used to investigate the influencing factors for rebleeding， and the Kaplan-Meier method was used to plot survival curves， while the Log-rank test was used for comparison between groups. ResultsOf all patients， 286 （16.7%） experienced rebleeding after endoscopic therapy， and 1 431 （83.3%） did not experience bleeding. There were significant differences between the two groups in history of smoking and drinking， etiology of liver cirrhosis， hemoglobin （Hb）， prothrombin time （PT）， prothrombin activity （PTA）， international normalized ratio （INR）， albumin （Alb）， fasting blood glucose， blood urea nitrogen， Child-Pugh class， aspartate aminotransferase-to-platelet ratio index （APRI） score， albumin-bilirubin （ALBI） score， use of non-selective beta-blocker （NSBB） before surgery， treatment modality， type of varices， and maximal varicose vein diameter （all P<0.05）. The univariate Cox regression analysis showed that in the patients with liver cirrhosis who received secondary prevention of GOV， rebleeding was associated with history of smoking and drinking， etiology of liver cirrhosis， use of NSBB before surgery， treatment modality， maximal varicose vein diameter， Hb， platelet count， PT， PTA， INR， Alb， total bilirubin （TBil）， alkaline phosphatase （ALP）， gamma-glutamyl transpeptidase， blood glucose， Child-Pugh class， and ALBI score （all P<0.05）. The multivariate Cox regression analysis showed that Hb （hazard ratio ［HR］=0.989， 95% confidence interval ［CI］： 0.983‍ ‍—‍ ‍0.994， P<0.001）， TBil （HR=1.020， 95%CI： 1.006‍ ‍—‍ ‍1.034， P=0.005）， Alb （HR=0.868， 95%CI： 0.758‍ ‍—‍ ‍0.994， P=0.041）， treatment modality （sclerosing agent： HR=2.158， 95%CI： 1.342‍ ‍—‍ ‍3.470， P=0.002； tissue adhesive： HR=2.709， 95%CI： 1.343‍ ‍—‍ ‍5.462， P=0.005； ligation+sclerosing agent： HR=3.181， 95%CI： 1.522‍ ‍—‍ ‍6.645， P=0.002； sclerosing agent+tissue adhesive： HR=1.851， 95%CI： 1.100‍ ‍—‍ ‍3.113， P=0.020）， ALP （HR=1.003， 95%CI： 1.001‍ ‍—‍ ‍1.004， P=0.002）， and maximal varicose vein diameter （HR=1.346， 95%CI： 1.119‍ ‍—‍ ‍1.618， P=0.002） were independent influencing factors for rebleeding after endoscopic therapy. Comparison of rebleeding rate after different numbers of sequential treatment sessions showed that the patients treated for three sessions had a significantly lower rebleeding rate than those treated for one or two sessions （χ²=8.643 and 5.277， P=0.003 and 0.022）. The survival analysis showed that with the increase in the number of treatment sessions， there was a significantly longer interval between rebleeding （P=0.006） and a significantly lower mortality rate （P<0.001）. ConclusionThe levels of TBil， ALP， Hb， and Alb on admission， endoscopic treatment modality， and maximal varicose vein diameter were the main predictive factors for rebleeding after endoscopic therapy for GOV in liver cirrhosis， and such predictive factors should be closely monitored in clinical practice. Regular endoscopic therapy can reduce the rebleeding and mortality rates of patients with liver cirrhosis and GOV and prolonmg the interval between rebleeding.