In the context of the rapid development of 5G technology， the development of artificial intelligence （AI） in traditional Chinese medicine （TCM） faces new opportunities and challenges. Focusing on how to uphold tradition while innovating in the development of AI in TCM， starting from the current development status of AI in Chinese medicine， including the integration of four diagnostic methods， syndrome differentiation and treatment， auxiliary diagnosis and treatment， research and development of Chinese herbal medicine， prevention and treatment of diseases， knowledge inheritance， and other aspects， this paper discussed the support of policies and technical advancements， as well as development opportunities such as increased demand for health. Regarding machine ethics， data ethics， regulatory review， and other aspects， it also proposed some suggestions that the training algorithm should be improved to assist medical work； data ownership should be clarified to ensure data security； and an AI ethics committee should be set up to improve the review system， aiming to maximize the advantages of smart healthcare and accelerate the modernization of TCM for the benefit of patients and the service of human health.

BACKGROUND:In recent years,deep learning technologies have been increasingly applied in the field of oral medicine,enhancing the efficiency and accuracy of oral imaging analysis and promoting the rapid development of intelligent oral medicine. OBJECTIVE:To elaborate the current research status,advantages,and limitations of deep learning based on oral imaging in the diagnosis and treatment decision-making of oral diseases,as well as future prospects,exploring new directions for the transformation of oral medicine under the backdrop of deep learning technology. METHODS:PubMed was searched for literature related to deep learning in oral medical imaging published from January 2017 to January 2024 with the search terms"deep learning,artificial intelligence,stomatology,oral medical imaging."According to the inclusion criteria,80 papers were finally included for review. RESULTS AND CONCLUSION:(1)Classic deep learning models include artificial neural networks,convolutional neural networks,recurrent neural networks,and generative adversarial networks.Scholars have used these models in competitive or cooperative forms to achieve more efficient interpretation of oral medical images.(2)In the field of oral medicine,the diagnosis of diseases and the formulation of treatment plans largely depend on the interpretation of medical imaging data.Deep learning technology,with its strong image processing capabilities,aids in the diagnosis of diseases such as dental caries,periapical periodontitis,vertical root fractures,periodontal disease,and jaw cysts,as well as preoperative assessments for procedures such as third molar extraction and cervical lymph node dissection,helping clinicians improve the accuracy and efficiency of decision-making.(3)Although deep learning is promising as an important auxiliary tool for the diagnosis and treatment of oral diseases,it still has certain limitations in model technology,safety ethics,and legal regulation.Future research should focus on demonstrating the scalability,robustness,and clinical practicality of deep learning,and finding the best way to integrate automated deep learning decision support systems into routine clinical workflows.

AIM: To design and construct recombinant epitope nucleotides vaccine of glycoprotein B(gB)and glycoprotein D(gD)of herpes simplex virus type 1(HSV-1), and to investigate its immunoprotective effects and tissue expression in animal models.METHODS: The HSV-1 gB and gD epitope genes were selected and tandem assembled to construct the recombinant protein-coding gene X, which was transducted into the prokaryotic expression vector pET28(a). The recombinant protein was synthesized and utilized to generate monoclonal antibodies, which were subsequently used to immunize New Zealand white rabbits. The immunogenicity of the purified protein and the presence of polyclonal antibodies in the serum were tested through separating serum from cardiac blood, and the serum antibody titers were determined. The pcDNA3.1-X was successfully constructed as a eukaryotic expression vector and immunized the female BALB/c mice aged 4 to 6 wk via intramuscular injection. Serum antibodies and immune-related cytokines were quantified using enzyme-linked immunosorbent assay(ELISA). The expression of the X protein in the ocular, trigeminal ganglion, and brain tissues of the mice was assessed.RESULTS: The target polyclonal antibody was identified with a serum antibody titer of 1:3200 in the rabbit serum after immunized by recombinant protein X. Upon immunizing mice with the eukaryotic recombinant plasmid pcDNA3.1-X, the concentration of HSV-1 serum IgM antibodies of the experimental group was 12.13±0.85 ng/L, which was significantly higher than that of the vector control group(0.49±0.44 ng/L; t=21.07, P<0.001). The concentrations of cytokines interleukin IL-2, IL-4, IL-10, and IFN-γ in the experimental group were 11.63±0.60, 22.65±1.47, 85.75±14.12, and 114.90±6.39 ng/L, respectively, all of which were significantly higher than those in the vector control group and the blank control group(all P<0.05). Immunohistochemical staining revealed the presence of target protein X in the eyeball, trigeminal ganglion, and brain tissue.CONCLUSION: The HSV-1 gB and gD tandem epitope nucleotides vaccine pcDNA3.1-X was successfully constructed, which activates a remarkable immune response and is stably expressed in the eyeball, trigeminal ganglion, and brain tissue. This study provides a foundation for further research of an HSV-1 recombinant antigen epitope tandem vaccine.

BackgroundNon-suicidal self-injury （NSSI） behavior among adolescents has become a global public health concern. Anxiety and depression are considered key factors influencing NSSI behavior， while social support may play a protective role in alleviating emotional and behavioral issues. However， existing research has primarily focused on the direct impact of individual factors on NSSI behavior， with insufficient exploration of the combined effects of anxiety， depression and social support. ObjectiveTo investigate the direct effect of anxiety on NSSI， the mediating role of depression and the moderating role of social support in relationship between anxiety and NSSI behavior， thus to provide references for the prevention and intervention of NSSI behavior among adolescents. MethodsIn February 2022， a total of 40 820 students in grades 7 to 12 across 10 middle schools in a district of Chengdu were selected as participants， and they were assessed using Generalized Anxiety Disorder Scale-7 item （GAD-7）， Patient's Health Questionnaire Depression Scale-9 item （PHQ-9）， Social Support Scale for Urban Students （SSSUS） and Adolescent Self-Harm Scale （ASHS）. Pearson correlation analysis was conducted to examine the correlations between scale scores among adolescents with NSSI behaviors. Mediation and moderation analyses were performed using Process 3.5 in SPSS， and the significance was tested with bootstrapping. The interaction was visualized by using simple slope analysis. ResultsAmong 34 534 （84.60%） valid respondents， 542 adolescents （1.57%） reported engaging in NSSI behavior. Significant differences in gender， GAD-7 scores， PHQ-9 scores， and SSSUS scores were observed between NSSI behavior group and non-NSSI group （χ²/t=62.889， 71.120， 94.365， -41.464， P<0.01）.Adolesents with NSSI showed positive correlations between GAD-7 scores and both ASHS and PHQ-9 scores （r=0.158， 0.166， P<0.01）. PHQ-9 scores were positively correlated with ASHS scores （r=0.364， P<0.01）， but negatively correlated with SSSUS scores （r=-0.290， P<0.01）. SSSUS scores were negatively correlated with ASHS scores （r=-0.247， P<0.01）. Depression partially mediated the relationship between anxiety and NSSI behavior， with an effect size of 0.544 （95% CI： 0.162~0.944）， accounting for 35.79% of the total effect. Social support moderated the relationship between depression and NSSI bahavior， with an effect value of -0.082 （95% CI： -0.135~-0.029）. ConclusionAnxiety not only directly influences NSSI bahavior among adolescents， also indirectly exacerbates it through depression， while social support mitigates the impact of depression on NSSI behavior. ［Funded by Youth Project of National Natural Science Foundation of China （number， 82401812）； Project of Health Commission of Sichuan Province （number， 24LCYJPT18）］

OBJECTIVES: The Charlson comorbidity index reflects overall comorbidity burden and has been applied in cardiovascular medicine. However, its role in predicting in-hospital mortality in patients with acute myocardial infarction (AMI) complicated by ventricular arrhythmias (VA) remains unclear. This study aims to evaluate the predictive value of the Charlson comorbidity index in this setting and to construct a nomogram model for early risk identification and individualized management to improve outcomes. METHODS: Using the open-access critical care database MIMIC-IV (Medical Information Mart for Intensive Care IV), we identified intensive care unit (ICU) patients diagnosed with AMI complicated by VA. Patients were grouped according to in-hospital survival. The predictive performance of the Charlson comorbidity index and other clinical variables for in-hospital mortality was analyzed. Key predictors were selected using the least absolute shrinkage and selection operator (LASSO) regression, followed by multivariable Logistic regression. A nomogram model was constructed based on the regression results. Model performance was assessed using receiver operating characteristic (ROC) curves and calibration plots. RESULTS: A total of 1 492 patients with AMI and VA were included, of whom 340 died and 1 152 survived during hospitalization. Significant differences were observed between survivors and non-survivors in sex distribution, vital signs, comorbidity burden, organ function, and laboratory parameters (all P<0.05). The area under the curve (AUC) of the Charlson comorbidity index for predicting in-hospital mortality was 0.712 (95% CI 0.681 to 0.742), significantly higher than albumin, international normalized ratio (INR), hemoglobin, body temperature, and platelet count (all P<0.001), but comparable to Sequential Organ Failure Assessment (SOFA) score (P>0.05). LASSO regression identified seven key predictors: the Charlson comorbidity index (quartile groups: T1, <6; T2, ≥6-<7; T3, ≥7-<9; T4, ≥9), ventricular fibrillation, age, systolic blood pressure, respiratory rate, body temperature, and SOFA score. Multivariate Logistic regression showed that compared with T1, mortality risk increased significantly in T2 (OR=1.996, 95% CI 1.135 to 3.486, P=0.016), T3 (OR=3.386, 95% CI 2.192 to 5.302, P<0.001), and T4 (OR=5.679, 95% CI 3.711 to 8.842, P<0.001). Age (OR=1.056, P<0.001), respiratory rate (OR=1.069, P<0.001), SOFA score (OR=1.223, P<0.001), and ventricular fibrillation (OR=2.174, P<0.001) were independent risk factors, while systolic blood pressure (OR=0.984, P<0.001) and body temperature (OR=0.648, P<0.001) were protective factors. The nomogram incorporating these predictors achieved an AUC of 0.849 (95% CI 0.826 to 0.871) with high discrimination and good calibration (mean absolute error=0.014). CONCLUSIONS The Charlson comorbidity index is an independent predictor of in-hospital mortality in AMI patients complicated by VA, with performance comparable to the SOFA score. The nomogram model based on the Charlson comorbidity index and additional clinical variables effectively estimates mortality risk and provides a valuable reference for clinical decision-making.
Humans ; Nomograms ; Hospital Mortality ; Myocardial Infarction/complications* ; Male ; Female ; Comorbidity ; Middle Aged ; Aged ; Arrhythmias, Cardiac/complications* ; ROC Curve ; Intensive Care Units

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

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.

Liraglutide (Lira), a glucagon-like peptide-1 (GLP-1) receptor agonist approved for diabetes and obesity, has shown significant potential in treating metabolic dysfunction-associated steatotic liver disease (MASLD). However, its systematic molecular regulation and mechanisms remain underexplored. In this study, a mouse model of MASLD was developed using a high-fat diet (HFD), followed by Lira administration. Proteomics and glycoproteomics were analyzed using label-free liquid chromatography-tandem mass spectrometry (LC-MS/MS), while potential molecular target analysis was conducted via quantitative real-time polymerase chain reaction (qPCR) and Western blotting. Our results revealed that Lira treatment significantly reduced liver weight and serum markers, including alanine aminotransferase (ALT) and others, with glycosylation changes playing a more significant role than overall protein expression. The glycoproteome identified 255 independent glycosylation sites, emphasizing the impact of Lira on amino acid, carbohydrate metabolism, and ferroptosis. Simultaneously, proteomic analysis highlighted its effects on lipid metabolism and fibrosis pathways. 21 signature molecules, including 7 proteins and 14 N-glycosylation sites (N-glycosites), were identified as potential targets. A Lira hydrogel formulation (Lira@fibrin (Fib) Gel) was developed to extend drug dosing intervals, offering enhanced therapeutic efficacy in managing chronic metabolic diseases. Our study demonstrated the importance of glycosylation regulation in the therapeutic effects of Lira on MASLD, identifying potential molecular targets and advancing its clinical application for MASLD treatment.

BackgroundThe distressingly high prevalence of depressive symptoms among adolescents exerts profound impacts on their physical and psychological development， urgently necessitating effective preventive interventions. Existing studies， however， have predominantly focused on isolated risk factors， neglecting to construct an integrated model that systematically disentangles the intricate relationships linking parenting styles， learning burnout， and childhood trauma to adolescent depressive symptoms. Moreover， the potential protective roles of social support and psychological resilience in this context remain insufficiently elucidated. ObjectiveTo construct a structural equation model encompassing multiple pathways to unravel the comprehensive mechanisms through which negative parenting styles， childhood trauma， learning burnout， psychological resilience， and social support collectively influence adolescent depressive symptoms， thereby providing evidence-based intervention strategies. MethodsA stratified sampling technique was utilized to recruit 5 865 students from 12 middle schools in Chengdu City， Sichuan Province from March to May 2022. Participants were assessed using the following validated instruments： the Short-form Egna Minnen av Barndoms Uppfostran （s-EMBU）， the Childhood Trauma Questionnaire-Short Form （CTQ-SF）， the Adolescent Student Burnout Inventory， the Patients' Health Questionnaire Depression Scale-9 item （PHQ-9）， the Social Support Rating Scale （SSRS），and the Connor-Davidson Resilience Scale （CD-RISC）. A partial least squares structural equation modeling （PLS-SEM） approach was employed to construct a predictive framework examining the complex network of pathways through which negative parenting styles， childhood trauma， learning burnout， psychological resilience，and social support collectively influence depressive symptoms in adolescents. ResultsThe PHQ-9 scores demonstrated significant positive correlations with the scores on s-EMBU overprotection subscale （r=0.272， P<0.01）， s-EMBU rejection subscale （r=0.368， P<0.01）， CTQ-SF （r=0.288， P<0.01） and Adolescent Student Burnout Inventory （r=0.587， P<0.01）. Conversely， significant negative correlations were observed between PHQ-9 scores and both SSRS （r=-0.532， P<0.01） and CD-RISC scores （r=-0.418， P<0.01）. Negative parenting styles （β=0.113， 95% CI： 0.087-0.138） and learning burnout （β=0.339， 95% CI： 0.315-0.364） emerged as significant positive predictors of depressive symptoms， with childhood trauma mediating the relationship between negative parenting styles and depressive symptoms （effect size=0.018， 95% CI： 0.013-0.024）. Social support servesed as a mediating pathway between negative parenting styles and depressive symptoms （β=0.080， 95% CI： 0.069-0.092）， as well as between negative parenting styles and childhood trauma （β=0.041， 95% CI： 0.032-0.050）. It also functioned as an intermediary pathway linking learning burnout to depressive symptoms （β=0.092， 95% CI： 0.081-0.104） and connecting learning burnout with childhood trauma （β=0.048， 95% CI： 0.037-0.058）. Additionally， psychological resilience serveed as a mediating pathway between negative parenting styles and depressive symptoms （β=0.004， 95% CI： 0.002-0.007）， between learning burnout and depressive symptoms （β=0.037， 95% CI： 0.023-0.052）， and between childhood trauma and depressive symptoms （β=0.003， 95% CI： 0.001-0.006）. ConclusionLearning burnout exerts a direct effect on adolescent depressive symptoms. Negative parenting styles influence depressive symptoms both directly and indirectly through childhood trauma. Furthermore， social support and psychological resilience serve as mediator linking negative parenting styles and learning burnout to depressive symptoms in adolescents. ［Funded by Science and Technology Project of the Health Commission of Sichuan Province （number， 24LCYJPT18）］

Objective:To explore the effects of activating α7 nicotinic acetylcholine receptor(α7nAChR)on cognitive function and polarization of hippocampal microglia in traumatic brain injury (TBI) rats.Methods:Totally 36 male SD rats with 6-8 weeks old were randomly divided into Sham group ( n=12), TBI group ( n=12), TBI+ α7nAChR agonist group ( n=6) and TBI+ α7nAChR antagonist group( n=6). The TBI model was established by the " free fall impact" method. From the 4th to 6th day after modeling, mice in the TBI+ α7nAChR agonist group were intraperitoneally injected with α7nAChR agonist PNU-282987 (3 mg/kg). Rats in TBI+ α7nAChR antagonist group were intraperitoneally injected with α7nAChR antagonist methyllycaconitine citrate (5 mg/kg) first, then 45 minutes later they were injected with α7nAChR agonist PNU-282987 (3 mg/kg). Rats in the TBI group and Sham group were intraperitoneally injected with an equal volume of 0.9% sodium chloride solution. Morris water maze test was used to evaluate the learning and memory function of rats. Immunofluorescence staining was used to observe the ionized calcium binding adapter molecule 1 (Iba-1)(a marker for microglia) and arginase 1 (Arg-1)(a marker for M2 microglia). Western blot was used to detect the protein level of Arg-1 in hippocampal tissue. Statistical analysis was performed using GraphPad Prism 9 software. Independent sample t test was used for comparison between two groups, one-way ANOVA was used for comparison among multiple groups, and Tukey test was used for multiple comparison. Results:The results of the water maze test showed that after 7 days of modeling, there was a statistical difference in the escape latency among the 4 groups of rats ( F=6.134, P<0.05). There was no statistical difference in the escape latency between the TBI group and the TBI+ α7nAChR antagonist group( P>0.05), but the both were higher than that of the Sham group (both P<0.05). The escape latency of the TBI+ α7nAChR agonist group((31.87±9.01)s) was shorter than that of the TBI group((56.75±2.62)s) and the TBI+ α7nAChR antagonist group((60.00±0.00)s) (both P<0.05). The results of immunofluorescence staining showed that there were statistical differences in the fluorescence intensity and cell numbers of Arg-1 + /Iba-1 + among the four groups ( F=17.37, 9.33, both P<0.05). The immune fluorescence intensity (0.27±0.03) and cell numbers (21.67±4.41) of Arg-1 + /Iba-1 + in the TBI+ α7nAChR agonist group were higher than those in the TBI group((0.14±0.03), (11.33±2.60)) and TBI+ α7nAChR antagonist group((0.10±0.03), (7.67±1.20)) (all P<0.05). The results of Western blot showed that there was a statistical difference in the level of Arg-1 protein in hippocampus among the 4 groups ( F=8.323, P=0.001). There was no significant difference in the level of Arg-1 protein between the TBI group and the TBI+ α7nAChR antagonist group( P>0.05), and the level of Arg-1 protein in the TBI+ α7nAChR agonist group(1.06±0.22) was higher than that in the TBI group(0.60±0.13) and TBI+ α7nAChR antagonist group(0.35±0.10) (both P<0.05). Conclusion:Activating α7nAChR can promote the polarization of M2 type microglia in rat hippocampal tissue and improve the learning and memory function of TBI rats.