With the continuous deepening of the concept of precision diagnosis and treatment for lung cancer, how to achieve higher efficiency and accuracy in the screening, diagnosis, and treatment pathways in clinical practice has become an important issue that urgently needs to be overcome. The current clinical difficulty lies in the fact that despite continuous advancements in imaging and molecular diagnostic technologies, there are still limitations in manual efficiency and subjective experience when it comes to massive data analysis and multi-scale feature extraction. Artificial intelligence (AI), especially algorithm systems based on deep learning, is an innovative technology capable of deeply empowering medical big data. This method utilizes algorithms such as convolutional neural networks, combined with radiomics, pathomics, and multi-modal data fusion analysis, demonstrating immense potential in early precise detection and benign-malignant differentiation of pulmonary nodules, digital pathological subtype recognition and non-invasive prediction of driver genes, precise 3D surgical planning and automatic delineation of radiotherapy target volumes, as well as dynamic risk warning during follow-up. This innovative technology provides a brand-new solution for realizing intelligent and individualized lung cancer diagnosis and treatment models. This consensus, based on the latest evidence from evidence-based medicine and combined with the development trends in the AI field and real-world clinical needs, was ultimately formed by gathering the consensus opinions of multidisciplinary experts in radiology, pathology, thoracic surgery, and other fields. The main content covers the application specifications of AI in the three core scenarios of lung cancer screening, diagnosis, and treatment, the technical standards for data collection and algorithm validation, as well as the ethical and regulatory challenges faced at the current stage. It aims to clarify the applicable boundaries of AI as a clinical auxiliary decision support tool, providing scientific guidance and standardized exploration directions for peers currently engaged in or planning to carry out AI-assisted clinical diagnosis, treatment, and translation of lung cancer.

Objective To explore factors associated with early postoperative hormonal remission in patients with prolactinoma and to develop prediction models based on clinical and radiological features. Methods Data from 107 patients with prolactinoma who underwent transsphenoidal surgery at The First People’s Hospital of Huai’an, Nanjing Medical University between January 2020 and December 2024 was collected, included general clinical characteristics, preoperative laboratory indicators, and imaging features. Based on whether early postoperative prolactin (PRL) levels normalized, patients were divided into a remission group (n=76) and a non-remission group (n=31). Univariate logistic regression was used for preliminary evaluation of candidate variables, followed by LASSO regression for feature selection. Multiple machine learning models were constructed, including logistic regression, random forest, support vector machine, K-nearest neighbors, naive Bayes, decision tree, neural network, and gradient boosting decision tree (GBDT). All models were trained and evaluated using ten-fold cross-validation, with comprehensive assessment of model performance based on the area under the ROC curve (AUC), accuracy, sensitivity, specificity, precision, and F1 score. Results The maximum diameter of tumors in the non remission group was larger than that in the remission group (P=0.019), and the incidence of tumor stroke and preoperative PRL levels were significantly higher than those in the remission group (P＜0.001). Univariate analysis showed that sex, maximum tumor diameter, tumor stroke, and preoperative PRL levels were influencing factors for early postoperative hormone response in patients with prolactinoma (P＜0.05). The comparison results of machine learning models show that the neural network model performs the best (AUC=0.921) and has good clinical application value, followed by the GBDT model (AUC=0.893) and the support vector machine model (AUC=0.884). Other models also show certain predictive ability. Conclusions Sex, preoperative PRL levels, maximum tumor diameter, Hounsfield unit value, and tumor stroke are important factors affecting early hormone response after prolactinoma surgery. The machine learning model constructed based on the above variables has good predictive performance, and performs the best and has good clinical application value.

ObjectiveThis paper aims to conduct a secondary analysis of a randomized controlled trial on the treatment of myelodysplastic syndrome （MDS） with deficiency of both the spleen and kidney and blockage of toxin and blood stasis with an arsenic-containing traditional Chinese medicine compound， by applying the mixed model for repeated measure （MMRM） and the method of stratified composite outcome with win ratio. The analysis includes the assessment of hematological efficacy and the composite outcome evaluation of adverse reactions， so as to more comprehensively assess the therapy of this regimen. MethodsThe MMRM and win ratio methods were used to evaluate the efficacy of a prospective，multi-center，double-blind，randomized controlled study. The blood routine （hemoglobin concentration，neutrophil count， and platelet count） and biochemical indexes （aspartate aminotransferase，alanine aminotransferase，serum creatinine，and serum ferritin） of the patients were detected at the time of enrollment and at the end of each course of treatment in the laboratory department of Xiyuan Hospital. The patients' syndromes at the time of enrollment and after treatment were recorded and scored according to the therapy standard of traditional Chinese medicine for diseases and syndromes. MMRM was used to analyze the blood routine indexes of the experimental group and the control group. This method has the advantages of high data reliability and dynamic efficacy under intervention and time. The win ratio method was used to evaluate the composite outcome of traditional Chinese medicine syndrome scores and biochemical indexes according to the priority and to verify the clinical safety of arsenic-containing traditional Chinese medicine compound. ResultsThe results of MMRM analysis showed that the hemoglobin concentration of patients in the group with arsenic-containing traditional Chinese medicine compound increased significantly compared with that before treatment in the group，while that in the placebo group decreased significantly （P<0.01）. When compared with that after treatment in the placebo group，the hemoglobin concentration of patients in the group with arsenic-containing traditional Chinese medicine compound increased significantly，and the mean difference of least squares （LS） was statistically significant （P<0.01）. When compared with those before treatment in the group，there were no statistically significant differences in the neutrophil count and platelet count in both groups. After treatment，there were no statistically significant differences in the neutrophil count， platelet count， and the mean difference of LS between the two groups. The analysis results of win ratio showed that the group with arsenic-containing traditional Chinese medicine compound had a significant advantage in the comparison of composite outcomes，with a win ratio （95% CI） of 2.01 （1.24-3.27） （P<0.01），and that the possibility of "winning" in terms of safety was 2.01 times that of the placebo group. The safety advantage of the group with arsenic-containing traditional Chinese medicine compound mainly came from the traditional Chinese medicine syndrome scores，renal function indexes， and iron reserve capacity indexes，and the number of winning times was less than that of losing times in the comparison of liver function outcomes. ConclusionThe MMRM analysis proves that the arsenic-containing traditional Chinese medicine compound can significantly improve the hemoglobin concentration of patients with myelodysplastic syndrome with refractory cytopenia and multilineage dysplasia （MDS-RCMD） of the type of deficiency of both the spleen and kidney and blockage of toxin and blood stasis. This conclusion is not interfered with by time trends and individual relationships and methodologically improves the credibility of the therapy of the arsenic-containing traditional Chinese medicine compound in treating MDS. Four outcomes are evaluated by the win ratio method，namely traditional Chinese medicine syndromes，liver function，renal function， and iron reserve capacity，proving that the arsenic-containing traditional Chinese medicine compound has the comprehensive advantages of improving the survival quality of the patients and reducing adverse reactions. The win ratio outcome provides clear comparative indexes for the evaluation of adverse reactions，making it easier for regulatory authorities，medical staff， and patients to understand the safety of the arsenic-containing traditional Chinese medicine compound in clinical application.

BackgroundThe middle school stage represents a crucial period for the development of borderline personality features. Negative parenting styles and emotional regulation strategies are associated with the formation of borderline personality features. However， the moderating role of emotional regulation strategies between negative parenting styles and borderline personality features among middle school students remains unclear. ObjectiveTo explore the moderating influence of emotional regulation strategies in the relationship between negative parenting styles and borderline personality features among middle school students， and to provide references for the intervention of borderline personality features. MethodsIn October 2023， a total of 5 965 middle school students from three middle schools in Nanning， Guangxi Zhuang Autonomous Region were selected by cluster sampling， and assessed by the Borderline Personality Features Scale for Children （BPFS-C）， the Egna Minnen Barndoms Uppfostran （EMBU）， and the Emotion Regulation Questionnaire-Chinese Revised Version （ERQ-CRV）. Pearson correlation analysis was used to test the correlation between the scores of each scale， and the model 1 of the Process macro program was used to conduct the moderating effect test. ResultsA total of 5 572 middle school students （93.41%） completed this study， and 1 388 of them （24.91%） were identified as having high borderline personality features. The BPFS-C score of middle school students was positively correlated with the score of the negative parenting style dimension of EMBU （r=0.367， P<0.01）， negatively correlated with the score of the cognitive reappraisal dimension of ERQ-CRV （r=-0.168， P<0.01）， and positively correlated with the score of the expression inhibition dimension of ERQ-CRV （r=0.344， P<0.01）. Cognitive reappraisal played a negative moderating effect between negative parenting styles and borderline personality features （β=-0.072， 95% CI： -0.104–-0.041， P<0.01）， while expressive suppression played a positive moderating effect （β=0.076， 95% CI： 0.055–0.097， P<0.01）. ConclusionCognitive reappraisal strategy may help mitigate the negative influence of negative parenting styles on middle school students' borderline personality features， while expressive suppression may exacerbate the harm of negative parenting styles to the borderline personality features of middle school students.

ObjectiveTo evaluate the comprehensive intervention effects of Huangqin Qingre Chubi Capsule （黄芩清热除痹胶囊， HQC） on self-perception of patients （SPP） and immune inflammation in patients with rheumatoid arthritis （RA）， and to explore its potential mechanisms. MethodsClinical data of 452 RA patients were retrospectively collected. Patients were divided into a control group （274 cases）， treated with conventional western medicine， and an observation group （178 cases）， treated with HQC for at least 2 weeks in addition to conventional western medicine. The treatment duration was 2 weeks for both groups. Propensity score matching （PSM） was performed at a ratio of 1∶1 to match patients between groups. SPP including the Chinese version of the short form-36 health survey （SF-36）， self-rating anxiety scale （SAS）， self-rating depression scale （SDS）， visual analog scale （VAS）， and Chinese patient-reported index for rheumatoid arthritis （CPRI-RA）， as well as immune inflammatory indicators， including erythrocyte sedimentation rate （ESR）， high-sensitivity C-reactive protein （hs-CRP）， rheumatoid factor （RF）， anti-cyclic citrullinated peptide antibody （anti-CCP）， interleukin-6 （IL-6）， immunoglobulin A （IgA）， immunoglobulin G （IgG）， immunoglobulin M （IgM）， complement C3， and complement C4， were collected before and after treatment. Spearman correlation analysis was used to assess the relationships between SPP and immune inflammatory indicators. Logistic regression， association rule analysis， and mediation analysis were performed to evaluate the effects and potential pathways of HQC on SPP and immune inflammatory indicators. Network pharmacology was applied to identify the active components and core targets of HQC in the treatment of RA， followed by molecular docking verification. In cell experiments， cells were divided into normal group， model group， 20% medicated serum group， and 80 nmol/L control group. Human synovial fibroblasts （FLS） were cultured with complete medium in the normal group， while human rheumatoid arthritis fibroblast-like synoviocytes （RA-FLS） were cultured in the model group. In the 20% medicated serum group， RA-FLS were cultured with medium containing 20% HQC-medicated serum， and in the 80 nmol/L control group， RA-FLS were cultured with complete medium containing 80 nmol/L methotrexate suspension. After 48 h of culture， cell viability was detected by cell counting kit-8 （CCK-8） assay. Levels of interleukin-1β （IL-1β）， interleukin-6 （IL-6）， interleukin-8 （IL-8）， and interleukin-10 （IL-10） in the cell supernatant were measured by enzyme-linked immunosorbent assay （ELISA）. Protein levels of matrix metalloproteinase 9 （MMP9）， transcription factor AP-1 subunit （JUN）， vascular endothelial growth factor A （VEGFA）， and C-X-C motif chemokine ligand 8 （CXCL8） were detected by Western Blot， and cell migration ability was evaluated using Transwell assay. ResultsAfter PSM， 178 cases were included in each group. After treatment， SF-36 scores increased， while scores of SAS， SDS， VAS and CPRI-RA， levels of ESR， hs-CRP， IL-6， complement C3， and complement C4 levels decreased in both groups； IgG and IgM levels were also reduced in the observation group （P＜0.05）. Physical functioning （correlation coefficient -0.19， P＜0.05） and social functioning （correlation coefficient -0.18， P＜0.05） of SF-36 were negatively correlated with hs-CRP， while VAS score was positively correlated with hs-CRP （correlation coefficient 0.19， P＜0.05）. HQC showed high associations with improvements in multiple indicators of SPP and immune inflammatory， and acted as a protective factor for the improvement of several SPP； hs-CRP and ESR played partial mediating roles in the improvement of SPP induced by HQC （P＜0.05）. Network pharmacology analysis identified baicalein， quercetin， α1-sitosterol， β-sitosterol， stigmasterol， baicalin， and crocetin as the core active components， and JUN， IL-6， VEGFA， MMP9， IL-1β， and CXCL8 as the core targets. Molecular docking results showed strong binding affinities of quercetin with VEGFA， JUN， MMP9， IL-6， and IL-1β， of baicalin with VEGFA and MMP9， and of wogonin with CXCL8. Cell experiments demonstrated that HQC and methotrexate inhibited RA-FLS viability and migration， reduced levels of IL-1β， IL-6， and IL-8， decreased protein levels of MMP9， JUN， VEGFA， and CXCL8， and increased IL-10 levels （P＜0.05）. ConclusionHQC can improve SPP in RA by regulating immune inflammatory responses. Its mechanism may be related to multi-pathway and multi-target inhibition of synovial cell inflammation and migration.

ObjectiveTo investigate the distribution characteristics and correlation of paired oral and esophageal microbiota in patients with esophageal squamous cell carcinoma （ESCC）. MethodsA total of 46 pathologically confirmed ESCC patients were enrolled， and oral swabs and cancerous tissue samples were collected. The microbial composition was analyzed using 16S rRNA gene sequencing， and bioinformatics methods were employed to compare the microbiota diversity， compositional differences， and correlations between the two sites. ResultsThe Alpha diversity of the oral microbiota in ESCC patients was significantly higher than that of their esophageal microbiota， though the overall community structure was similar between the two sites. LEfSe analysis revealed that Spirochaetes， Prevotella， Catonella， Enterococcus， Fusobacterium periodonticum， Veillonella parvula， Capnocytophaga sputigena， and Neisseria subflava were significantly enriched in ESCC tumor tissues. In contrast， Actinobacteria， Proteobacteria， Streptococcus， Neisseria， Haemophilus， Streptococcus mitis， Haemophilus parainfluenzae， Porphyromonas gingivalis， Haemophilus haemolyticus， and Prevotella tannerae were significantly enriched in the oral cavity. Correlation analysis demonstrated significant associations between the two sites at taxonomic levels such as Spirochaetes， Treponema， Granulicatella elegans， Neisseria macacae， Treponema amylovorum， Fusobacterium periodonticum， and Neisseria meningitidis （P<0.05）. ConclusionThe oral and esophageal microbiota in ESCC patients exhibit both distinct differences and similarities. Oral microbiota may influence the esophageal microenvironment through migration or local immune modulation.

On June 27， 2026， the Asian Pacific Association for the Study of the Liver （APASL） released updated management guidelines for chronic HBV infection， which systematically elaborates on screening， vaccination， antiviral treatment， and hepatocellular carcinoma surveillance and other aspects in 13 key areas， and provides comprehensive recommendations. This article summarizes and makes an excerpt of the key recommendations from the updated guidelines.

Over the past three decades， China has made significant progress in the prevention and control of viral hepatitis， and the incidence rates of new-onset pediatric hepatitis B virus infections and acute viral hepatitis in the population have reduced to a relatively low level； however， there is still a heavy disease burden of chronic viral hepatitis in China， which severely affects the health status of the population. This study systematically summarizes the achievements of viral hepatitis prevention and control in China， analyzes existing problems and challenges， and proposes comprehensive prevention and control strategies and measures to eliminate viral hepatitis as a public health threat based on the national conditions of China， in order to provide a reference for related departments in China on how to achieve the action targets for eliminating viral hepatitis as a public health threat by 2030.

Objective To explore the efficacy of vacuum-assisted minimally invasive gyrotomy for benign lesions in the lower quadrant of the breast.Methods From August 2022 to August 2023,90 patients with benign lesions in the lower quadrant of the breast were treated.According to the different surgical methods,they were divided into two groups:the traditional group included 45 cases,which underwent surgery through the trans-areolar incision;the minimally invasive group included 45 cases,which underwent surgery through the trans-mammary fold incision with vacuum-assisted minimally invasive technique.The surgical-related indicators,inflammatory response indicators,patient satisfaction,and safety were compared between the two groups.Results The operation time[(20.45±6.18)min],intraoperative bleeding[(7.78±2.23)ml],hospital stay[(4.37±1.05)d],scar length[(2.32±0.42)cm]and healing time[(3.46±1.08)d]in the minimally invasive group were significantly better than those in the traditional group[(34.52±9.46)min,(23.16±6.44)ml,(8.72±2.73)d,(19.14±4.18)cm and(7.37±2.16)d](P＜0.05).The levels of IL-6[(12.14±2.86)ng/L],IL-10[(14.33±3.74)pg/ml],CRP[(13.85±3.11)mg/L],Cor[(131.27±6.43)nmol/L]and NE[(82.55±8.44)in the minimally invasive group at 3 days after surgery ng/ml were increased and VEGF was decreased[(59.72±7.44)mg/L]than the traditional group[(17.23±3.38)ng/L,(19.62±4.88)pg/ml,(28.36±4.67)mg/L,(196.52±8.84)nmol/L,(117.62±7.14)ng/ml and(88.46±7.89)mg/L](P＜0.05).The satisfaction of patients in minimally invasive group(97.78％,44/45)was significantly higher than that in traditional group(82.22％,37/45)(P＜0.05).The incidence of adverse events in minimally invasive group(4.44％,2/45)was significantly lower than that in traditional group(22.22％,10/45)(P＜0.05).Conclusion Vacuum-assisted minimally invasive rotatory excision can optimize surgical indicators,improve serological indicators,enhance patient satisfaction and treatment safety compared to traditional areola incision surgery.

Objective To establish an effective model for distinguishing glandular prodromal lesions(PGL)mixed with ground-glass nodules(mGGN)from minimally invasive adenocarcinoma(MIA)on CT based on artificial intelligence.Methods A retrospective analysis was conducted on the clinical and CT image data of 180 patients with lung adenocarcinoma confirmed by surgical pathology and with CT manifestations of mGGN in the First Affiliated Hospital of Wenzhou Medical University from January 2017 to June 2023,inclu-ding 66 patients with PGL and 114 patients with MIA.Patients were divided into the training set(n=144)and the test set(n=36)in an 8∶2 ratio using a completely random method.The quantitative parameters and radiomics features of the lesions in CT images were automatically extracted using artificial intelligence soft-ware(United Imaging Research Platform uRP).By incorporating the most obvious correlation features of omics through dimensionality reduction,five machine learning classifiers were established,including logistic regression(LR),support vector machine(SVM),Random forest(RF),Gaussian process(GP),and Decision Tree(DT).The classifier with the training set highest area under the curve(AUC)was selected as the best radiomics model,and output the result as radiomics score(Rad-score).The clinical information,CT morpho-logical characteristics and quantitative data of the two groups were included in the multivariate logistic regres-sion analysis to screen the independent influencing factors for effectively differentiating PGL and MIA,and a clinical model was established.Finally,a comprehensive prediction model was constructed based on Rad-score and clinical risk factors.The diagnostic performance of the three models was evaluated by using the AUC,sen-sitivity,specificity and accuracy of receiver operating characteristic(ROC)curve.Results Eleven radiomics features for distinguishing PGL from MIA were obtained through LASSO dimensionality reduction.Among the five machine learning classifiers,GP has the best diagnostic performance,with AUC of 0.865 in the train-ing set and 0.762 in the test set,respectively.Univariate and multivariate logistic regression analyses were used for clinical feature screening.The clinical model was constructed by using the average CT value,average long and short diameter,and solid partial long diameter of mGGN,and the AUCs of the training set and the test set were 0.870 and 0.794,respectively.The comprehensive prediction model demonstrated superior diag-nostic performance,with AUC,sensitivity,specificity,and accuracy in the training set being 0.948,81.1%,91.2%and 87.5%respectively,while 0.883,76.9%,91.3%and 86.1%respectively in the test set.Conclu-sion The comprehensive prediction model established based on the quantitative and omics feature analysis of pulmonary nodules by artificial intelligence can well distinguish mGGN mixed with PGL from MIA on CT,and can be used to guide clinical treatment decisions.