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 evaluate the application effect of modified jejunostomy in thoracoscopic Ivor-Lewis esophagectomy. Methods A retrospective analysis of patients who underwent Ivor-Lewis esophagectomy for middle and lower esophageal cancer from 2017 to 2023 in Department of Cardiothoracic Surgery, Anqing Municipal Hospital was performed. The patients from 2017 to 2020 receiving "C+I" in the upper jejunum according to the "C+I" model, with fistula fixed with only two purse-string sutures and the abdominal wall were allocated into a group A. The patients from 2021 to 2023, on the basis of "C+I" suture, with the jejunum and abdominal wall fixed with 3-0 absorbable thread for 1-2 needles at the proximal or distal end of the fistula 10-15 mm, and the upper jejunum and abdominal wall fixed into "curtain" were allocated into a group B. The operation time, jejunostomy time, postoperative pathological stage, and enteral nutrition-related complications such as the incidence of incomplete intestinal obstruction, closed loop intestinal obstruction and intestinal volvulus requiring secondary surgery, skin redness and swelling of intestinal fluid leakage, stoma tube blockage, and accidental extubation were compared between the two groups. Results A total of 243 patients were enrolled in this study. The group A consisted of 118 patients (72 males, 46 females) with a mean age of (64.58±6.30) years. The group B consisted of 125 patients (76 males, 49 females) with a mean age of (65.11±6.81) years. All patients successfully underwent thoracoscopic Ivor-Lewis esophagectomy without perioperative mortality. There were no statistical differences between the two groups in operative time, jejunostomy creation time, or the rate of feeding tube occlusion (P>0.05). However, statistical differences were observed in the incidence of incomplete intestinal obstruction (P=0.035) and closed-loop intestinal obstruction requiring reoperation (P=0.017). The incidence of complications at the stoma site, such as intestinal fluid leakage and redness/swelling, was significantly higher in the group A (n=36) than that in the group B (n=7) (P<0.001). Conclusion The modified jejunostomy can significantly reduce the incomplete intestinal obstruction, closed loop intestinal obstruction and secondary operation rate after "C+I" jejunostomy, and significantly improve the leakage of intestinal fluid at the stoma and the injury of surrounding skin and soft tissue. Improvements in certain technologies reduce operational difficulties.

Artificial intelligence (AI) has made preliminary advances in the management of postoperative follow up for lung cancer; however, a systematic review of its application value across the entire follow-up continuum remains lacking. Taking the four core dimensions of postoperative follow-up management as its framework, including surveillance candidate selection, follow-up interval optimization, follow-up protocol design, and follow-up modality selection, this review examines the progress of AI in patient risk stratification, surveillance frequency optimization, content design, and supportive platform development. The review further delineates the current challenges and future directions for AI in this domain, and ultimately seeks to promote the standardized and scaled application of AI in postoperative follow-up management for lung cancer, with the goal of establishing a "care beyond hospitalization" life-cycle management framework that improves the long-term quality of survival for patients undergoing lung cancer surgery.

Objective Using cockroach surveillance data in Nanjing from 2017 to 2024, we have descriptively analyzed population characteristics and changes in insecticide resistance among Blattella germanica, and have established a seasonal Autoregressive Integrated Moving Average (ARIMA) model to predict monthly population densities in Nanjing spanning the year 2025. Methods B. germanica density and infestation rate were monitored using the sticky trap method, and insecticide resistance was assessed using the residual contact method. Our ARIMA model was applied to fit and estimate cockroach density fluctuations over time. Results From 2017 to 2024, B. germanica accounted for 94.90% of all cockroach specimens captured in Nanjing, with an average density of 0.37 cockroaches per trap and an average infestation rate of 5.56%. Significant differences in density and infestation rate were observed among different habitats (P＜0.001). Significant downward annual trends in both density and infestation rate were found (P＜0.05). ARIMA was found to be the optimal model for fitting the density data from 2017 to 2024 (0, 1, 1) × (0, 1, 1)1 2. Conclusions From 2017 to 2024, B. germanica was overwhelmingly the dominant cockroach species in Nanjing, with both its density and infestation rate declining annually. A positive correlation was observed between the amount and proportion of insecticide use and the development of insecticide resistance (P＜0.05). The established model demonstrated good performance in predicting monthly B. germanica densities in Nanjing throughout 2025, providing a valuable reference for future surveillance and control efforts.

Surgical treatment is one of the key approaches for non-small cell lung cancer (NSCLC). Regular postoperative follow-up is crucial for early detection and timely management of tumor recurrence, metastasis, or second primary tumors. A scientifically sound and reasonable follow-up strategy not only extends patient survival but also significantly improves quality of life, thereby enhancing overall prognosis. This consensus aims to build upon the previous version by incorporating the latest clinical research advancements and refining postoperative follow-up protocols for early-stage NSCLC patients based on different treatment modalities. It provides a scientific and practical reference for clinicians involved in the postoperative follow-up management of NSCLC. By optimizing follow-up strategies, this consensus seeks to promote the standardization and normalization of lung cancer diagnosis and treatment in China, helping more patients receive high-quality care and long-term management. Additionally, the release of this consensus is expected to provide insights for related research and clinical practice both domestically and internationally, driving continuous development and innovation in the field of postoperative management for NSCLC.

Objective To evaluate the efficacy and safety of enteric-coated metformin hydrochloride capsules(Junlida?)in patients with T2DM and poor glycemic control under lifestyle interventions.Methods In this study,419 patients with T2DM were recruited from 15 research centers from July 2020 to March 2022,and randomly divided into observation(Obs)group(n=209)and control group(Con,n=210)using a multicenter,randomized,double-blind,non-inferiority trial design.Patients in the Obs group were treated with enteric-coated Metformin hydrochloride capsules(Junlida?),and patients in the Con group were treated with Metformin hydrochloride tablets(Glucophage?).The optimal effective dose of 2 g/d was achieved within 4 weeks,and the reasonable dose was maintained until the end of treatment.The treatment period was 24 weeks.HbA1c and its compliance rate,FPG,and body weight were compared between the two groups in full analysis set(FAS)and protocol set(PPS).Safety and adverse events(AE)were evaluated in safety set(SS).Results A total of 414 participants were randomized(207 cases in Obs group and 207 cases in Con group).414 cases in FAS population(207 cases in Obs group and 207 cases in Con group),and 328 cases in PPS population(164 cases in Obs group and 164 cases in Con group),and 414 cases in SS population(207 cases in Obs group and 207 cases in Con group).After treatment,HbA1c,FPG and body weight were lower in both groups(P<0.05)in FAS and PPS.HbA1c compliance rate was not significantly different between the two groups in FAS and PPS(P>0.05).The results of non-inferiority test showed that the lower limit was>-0.4%in both FAS(-0.154,95%CI-0.384～0.069)and PPS(-0.139,95%CI-0.390～0.112),and the Obs group reached non-inferiority end point.The achievement rate,compliance rate,safety index and incidence of AE were not significantly different between the two groups(P>0.05).Conclusions Junlida? demonstrated non-inferiority to Glucophage? in glycemic control and can be safely and effectively used in patients with diabetes.

This study explored the effects and underlying mechanism of Raf kinase inhibitory protein(RKIP)on apoptosis in mast cells sensitized by Echinococcus granulosus cyst fluid.Bone marrow-derived mast cells(BMMCs)were isolated and cultured from RKIP knockout(KO)and wild-type(WT)C57BL/6 mice.Cells were divided into control and sensitized groups.The sensitized group was incubated for 24 h in RPMI1640 medium containing 10%serum from mice infected with E.granulosus,then activated for 3 h or 6 h with E.granulosus cyst fluid.The control group was incubated for 24 h in RPMI1640 medium,and then received an equal vol-ume of PBS.Cells and supernatants were collected for analysis.Flow cytometry was used to detect the expression of CD117 and FcεRⅠα on BMMCs.The levels of β-hexosaminidase,IL-4,and TNF-α in the supernatant were quantified with ELISA.Western blot analy-sis was used to assess expression changes in RKIP,apoptosis-related proteins,and pathway proteins in BMMC before and after sensi-tization.Flow cytometry analysis revealed that after 4 weeks of induction,the CD117 and FcεRⅠα double-positivity rates on both WT and KO BMMC exceeded 90%.ELISA indicated that the E.granulosus cyst fluid resulted in significantly greater β-hexosaminidase re-lease(F=16.88,P<0.05),and levels of IL-4(F=16.51,P<0.05)and TNF-α(F=9.78,P<0.05)in the KO sensitized group than the WT sensitized group.With respect to the WT control group,the WT sensitized group showed significantly down-regulated pro-tein expression levels of RKIP(F=8.20,P<0.05)and Bcl-2(F=101.40,P<0.01)after 3 h,but significantly up-regulated levels of p-PI3K(F=8.04,P<0.05),p-Akt(F=32.52,P<0.01),p-P65(F=13.29,P<0.05),and cleaved-caspase-3(F=46.34,P<0.01).With respect to the WT sensitized group,the KO sensitized group showed significantly up-regulated protein expression of p-PI3K(F=8.45,P<0.05),p-Akt(F=8.58,P<0.05),p-P65(F=11.02,P<0.05),and Bcl-2(F=84.50,P<0.001)after 3 h,but significantly down-regulated expression of cleaved-caspase-3(F=15.66,P<0.05).In conclusion,RKIP may inhibit the PI3K/Akt/NF-κB pathway,thereby inducing apoptosis in mast cells sensitized by E.granulosus cyst fluid.This process may help ease aller-gic reactions caused by mast cells in echinococcosis,thus offering a promising new approach for preventing and treating such reactions.

Objective To quantitatively compare the dosimetric differences among 4 volumetric modulated arc therapy(VMAT)plans by analyzing the number of arcs and collimator angle settings,aiming to establish a standardized planning template for hippocampal-sparing prophylactic cranial irradiation(HS-PCI)in clinic and improve both planning quality and clinical efficiency.Methods Twenty HS-PCI patients were enrolled,with 4 VMAT plans(V2c,V2p,V3,and V4)for each patient.The differences in target dose,organs-at-risk dose,and monitor units were compared.Results V4 plan had the highest PTV D98%and V95%,and the differences of PTV D98%in V2c vs V2p,V2c vs V4,and PTV V95%in V2c vs V4 were statistically significant(P<0.05).Meanwhile,V4 plan had the lowest PTV Dmax and Dmin doses.Specifically,statistically significant differences were observed in PTV Dmax in V4 vs V2c,V4 vs V2p,V4 vs V3,as well as PTV Dmin in V2c vs V2p,V2c vs V3,V2c vs V4,V2p vs V4(P<0.05).The PTV Dmean was the highest in V2p plan,with statistically significant differences observed in V2c vs V2p,V2c vs V4,V2p vs V3,and V3 vs V4(P<0.05).The highest PTV D2%dose was observed in V2p plan,and the differences in V2c vs V2p,V2c vs V4,V2p vs V3,V3 vs V4 were statistically significant(P<0.05).The homogeneity index and conformity index were close in 4 plans(P=0.946,P=0.380).V4 plan had the lowest Dmax,Dmean,and Dmin of the hippocampus,with significant differences in hippocampal Dmax in V4 vs V2c,V4 vs V2p,hippocampal Dmean in V4 vs V2c,V4 vs V2p,V3 vs V2c,and hippocampal Dmin in V2c vs V2p/V3/V4,and V4 vs V2p(P<0.05).V3 plan had the lowest Dmax for bilateral lenses,and V4 plan showed the lowest Dmax for lenses with a 3 mm expansion,with significant differences between V2c and V2p/V3/V4(P<0.05).V4 plan had the lowest dose for the right optic nerve,with significant differences in V4 vs V2p,and V4 vs V3(P<0.05).No significant differences were observed for the left optic nerve and optic chiasm.The monitor units in V2p plan was the lowest.Conclusion When differences in organs-at-risk doses and plan quality parameters are insignificant,V2p plan is recommended as it can ensure treatment quality while reducing delivery time.

Computational analysis can accurately detect drug-gene interactions(DGIs)cost-effectively.However,transductive learning models are the hotspot to reveal the promising performance for unknown DGIs(both drugs and genes are present in the training model),without special attention to the unseen DGIs(both drugs and genes are absent in the training model).In view of this,this study,for the first time,proposed an inductive learning-based model for the precise identification of unseen DGIs.In our study,by integrating disease nodes to avoid data sparsity,a multi-relational drug-disease-gene(DDG)graph was constructed to achieve effective fusion of data on DDG intro-relationships and inter-actions.Following the extraction of graph features by utilizing graph embedding algorithms,our next step was the retrieval of the attributes of individual gene and drug nodes.In this way,a hybrid feature charac-terization was represented by integrating graph features and node attributes.Machine learning(ML)models were built,enabling the fulfillment of transductive predictions of unknown DGIs.To realize inductive learning,this study generated an innovative idea of transforming known node vectors derived from the DDG graph into representations of unseen nodes using node similarities as weights,enabling inductive predictions for the unseen DGIs.Consequently,the final model was superior to existing models,with significant improvement in predicting both external unknown and unseen DGIs.The practical feasibility of our model was further confirmed through case study and molecular docking.In summary,this study establishes an efficient data-driven approach through the proposed modeling,suggesting its value as a promising tool for accelerating drug discovery and repurposing.

Aim To explore the mechanism of ligustil-ide(LIG)improving demyelination by inhibiting in-flammatory response in mice with distal middle cerebral artery occlusion(dMCAO)through AIM2/caspase-1 signal pathway.Methods Thirty C57BL/6N male mice were randomly divided into three groups:sham operation group(Sham group,n=10),model group(dMCAO group,n=10)and treatment group(LIG group,n=10).The dMCAO mouse model was estab-lished by electrocoagulation in dMCAO group and LIG group.The mice were scored by Longa after waking up,and the changes of cerebral blood flow were moni-tored by laser speckle blood flow imaging system after dMCAO.One hour after modeling,LIG(30 mg·kg-1·d-1)was injected intraperitoneally in LIG group,and the same amount of normal saline was injected in sham group and dMCAO group for one week until the end of the experiment.The mice in each group were stained with TTC,and the brain injury was observed pathologically.Fatigue turning bar test and open field test were used to evaluate the motor function and anxie-ty degree of mice,and then the brain tissues of mice were taken for black gold staining to compare the chan-ges of myelin sheath in each group.Immunofluores-cence staining was used to detect the average fluores-cence intensity of MBP,IBA1 and GFAP in CC,CPU and CX regions of mouse brains.ELISAwas used to de-tect the contents of TNF-α,IL-6,IL-1 β,IL-17A and BDNF in brain tissue proteins of mice.Western blot-ting was used to detect the protein expressions of AIM2,caspase-1 and ASC-in each group.Results Compared with the dMCAO group,the infarct area was reduced,the behavior was significantly improved and the demyelination was reduced in the LIG group.The expression of MBP protein in CC,CPU and CX regions increased(P＜0.05),the expression of IBA1 in CX decreased(P＜0.01),and the expression of GFAP in-creased in CC,CPU and CX regions(P＜0.01).The results of ELISA showed that the levels ofTNF-α(P＜0.01),IL-6(P＜0.01),IL-1β(P＜0.05)and IL-17A(P＜0.01)significantly decreased,while the ex-pression of BDNF increased(P＜0.05).The protein expression levels of AIM2,caspase-1 and ASC in mouse brain decreased after treatment(P＜0.01).Conclusion LIG has a protective effect on demyelina-tion in dMCAO mice,which may be related to the inhi-bition of AIM2/caspase-1 signaling pathway and in-flammation and to the promotion of BDNF secretion.