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 the efficacy and safety of neoadjuvant immunotherapy combined with chemotherapy in patients with locally advanced resectable non-small cell lung cancer (NSCLC). Methods The clinical data of patients with stage ⅡA-ⅢB NSCLC who underwent surgical treatment after receiving neoadjuvant immunotherapy combined with chemotherapy or chemotherapy alone at the First People’s Hospital of Jining between April 2021 and January 2024 were retrospectively analyzed. According to the preoperative neoadjuvant regimens, the patients were divided into a combined group and a chemotherapy group, and the clinical data of the two groups were compared. Results A total of 66 patients were included, including 61 males and 5 females. There were 53 patients in the combined group with a mean age of (63.40±6.80) years, and 13 patients in the chemotherapy group with a mean age of (58.62±8.30) years. There was a statistical difference in age between the two groups (P＜0.001), while no statistical difference was observed in other baseline data (P>0.05). The major pathological response rates in the combined group and the chemotherapy group were 54.7% and 23.1%, respectively (P=0.041), and the pathological complete response rates were 39.6% and 0.0%, respectively (P=0.006). The operative time in the combined group was shorter (P=0.039). There were no statistical differences between the two groups in intraoperative blood loss, duration of postoperative tube carrying, incidence of postoperative complications, overall survival, or event-free survival (P>0.05). Conclusion Surgical treatment following neoadjuvant immunotherapy combined with chemotherapy is safe and feasible, and its long-term efficacy requires further follow-up for confirmation.

Objective To observe the efficacy and safety of neoadjuvant sintilimab combined with chemotherapy in the treatment of patients with locally advanced resectable esophageal squamous cell carcinoma (ESCC). Methods Clinical data were collected from patients with locally advanced resectable ESCC who received neoadjuvant immunotherapy combined with chemotherapy followed by surgical treatment at the Department of Thoracic Surgery of Jining No.1 People's Hospital from April 2020 to April 2022. The endpoints included major pathological response (MPR), pathological complete response (pCR), R0 resection rate, safety, and postoperative survival. Results A total of 43 patients with ESCC who received at least one cycle of neoadjuvant immunotherapy before surgery were included. Among them, there were 31 males and 12 females with a median age of 65 years (interquartile range: 58-69). All patients successfully completed the surgery without any surgical delays. The pCR rate was 14.0% (6/43), the MPR rate was 58.1% (25/43), and the R0 resection rate was 97.7% (42/43). Patients exhibited reliable safety during neoadjuvant therapy and postoperatively. The 2-year overall survival and disease-free survival rates were 90.7% and 81.4%, respectively. Kaplan-Meier survival analysis and log-rank test revealed lower recurrence rates and better survival in the MPR patients compared to the non-MPR patients. Conclusion The combination of neoadjuvant sintilimab and chemotherapy in the treatment of patients with locally advanced resectable ESCC has demonstrated significant clinical efficacy, while also being safe and reliable.

Objective:To explore the application effect of high-fidelity intelligent simulator combined with scenario simulation for emergency response training in the Department of Radiology, and to improve the emergency preparedness of medical, nursing, and technical staff in managing contrast agent adverse reactions.Methods:From January to July 2024, 132 medical, nursing, and technical staff from the Department of Radiology of a tertiary hospital in Chengdu City, China were selected as the training subjects. The high-fidelity intelligent simulator combined with scenario simulation teaching mode was used to conduct emergency response training for the participants. The differences in theoretical knowledge and post competence regarding contrast agent adverse reactions among the staff were compared before and after the training. A self-made questionnaire was used to investigate their needs and satisfaction of the emergency response training. SPSS 26.0 was used for data analysis. The differences in theoretical knowledge and post competence scores before and after training were compared using the paired samples t test. Results:After the training, the average score of theoretical knowledge examination increased from (84.32±10.19) points to (90.34±7.87) points, and the difference was statistically significant ( P<0.001). After the training, the scores of knowledge reserve, operational skills, situational decision-making ability, professional literacy, comprehensive literacy, and overall post competency were all significantly higher than those before the training ( P<0.05). The satisfaction score of emergency response training was (4.17±0.25) points. Conclusions:High-fidelity intelligent simulator combined with scenario simulation training improved the emergency preparedness and teamwork of radiology staff in clinical emergencies. The training received high recognition and satisfaction from the participants, which is of great significance for clinical emergency response and patient safety.

Objective:In response to the subjectivity and poor real-time performance in methods for evaluating the quality of medical theory teaching, this study aims to develop an objective and real-time evaluation method for medical theory teaching quality.Methods:Classroom behavior data from both teachers and students in the course "medical image processing" were collected. An approach combining chain-like agent genetic algorithm with support vector regression machines was employed to analyze the collected classroom behavior data, and a classroom behavior-based evaluation model for medical theory teaching quality was established.Results:The predicted value generated by the model showed minimal error compared to students' actual answer accuracy, with an average absolute error of 4.84%. Additionally, the model demonstrated low time computation, with an average modeling time of 8.63 seconds and an average prediction time of 21.00 milliseconds.Conclusions:The constructed teaching quality assessment model shows high fitting precision and low time consumption.

Objective:To explore the construction of an evaluation model for aortic root anatomy and calcium burden in patients with bicuspid aortic valve (BAV) stenosis before transcatheter aortic valve replacement (TAVR) based on deep learning (DL) algorithms.Methods:A retrospective collection of 362 BAV stenosis patients who underwent TAVR from September 2023 to May 2024 was performed. All patients underwent cardiac CT angiography. The patients were divided into training group ( n=104), internal validation group ( n=206), and external validation group ( n=52). A DL model was trained on the training dataset to assess aortic root anatomy and calcification burden. The evaluation included the segmentation accuracy of the algorithm, the measurement performance of key anatomical structures (i.e., valve leaflets and type-1 and type-2 fusion raphe), and calcification burden, as well as the measurement efficiency. Overall segmentation performance was assessed using the average Dice coefficient (ADC). The fine-scale segmentation quality was validated by the 95th-percentile Hausdorff distance (HD-95) and the average symmetric surface distance (ASSD). The consistency of the measurement results was assessed using the Pearson correlation coefficient and the intraclass correlation coefficient ( ICC) with a two-way mixed model for absolute agreement. In addition, the total time and total mouse movement distance required for manual assessment versus the DL model on the validation datasets were recorded and compared. Results:The algorithm demonstrated excellent segmentation performance on aortic root anatomical targets, achieving outstanding consistency within both internal and external validation datasets (0.955

In order to establish a competitive chemiluminescent enzyme-linked immunoassay for rapid and quantitative detection of Senecavirus A antibodies,the polystyrene plate was coated with inactivated Senecavirus A antigen,and the monoclonal antibodies against Senecavirus A VP2 and VP3 proteins labeled by horseradish peroxidase(HRP)were used as the competitive enzymic anti-bodies of the antibodies in the serum samples.The standard curve of the calibrator prepared by di-lution of positive serum was drawn to achieve quantitative detection.The successfully established SVA competitive CLEIA reported the result within 45 minutes.The maximum dilution of 1∶2 048 for calibrator serum was still detectable with no cross-reaction with the standard positive serum of other five kinds of virus antigens such as foot-and-mouth disease.The coefficient of variation within batches was less than 10％,and the coefficient of variation between batches was less than 15％,which showed good repeatability and stability.The positive and negative coincidence rates were 95.30％and 97.57％,respectively,and the total coincidence rate was 96.88％,showing high consistency.The SVA competitive CLEIA assay established in this study can be used for the rapid quantitative detection of Senecavirus A antibodies,filling the gap in the domestic rapid quantitative detection of SVA antibodies.

Objective To investigate the current nursing practice of nurses specializing in nutritional support in ICUs and analyze their influencing factors in order to improve the training program and promote the development of standardized and precise nursing practice.Methods Convenience sampling method was used to select nutritional support nurses in ICUs in 29 provinces(autonomous regions and municipalities)from October 2023 to March 2025,and the self-developed questionnaire on nursing practice behaviors of nutritional support nurses in ICUs was used to conduct the survey.SPSS 21.0 software was used for descriptive analysis and multiple linear regression analysis.Results A total of 774 questionnaires were distributed,and 766 valid questionnaires were collected,with a recovery rate of 98.97％,and the score of the questionnaire on nursing practice behaviors of nurses specializing in nutritional support in ICU was(90.41±1 1.82).The results of multiple linear regression analysis showed that gender,presence of a nutritional support nursing team in the hospital,a standardized process of nutritional support nursing in the department,clear positional responsibilities of the nutritional support nursing team members,and inclusion of the nutritional support status of the patients in the quality management of the department were the factors influencing the nursing practice behavior scores of the nurses specializing in nutritional support in ICUs(P＜0.05).Conclusion Nurses in the ICUs have a high level of nursing practice behavior,but there is a need for further standardization in parenteral nutrition infusion and monitoring of complications.ICU nursing managers should formulate improvement strategies to address the weaknesses of clinical practice,strengthen nutritional support training,and improve the quality management program,and further improve the practical ability of nurses specializing in nutritional support.

Objective To observe the predictability of the corneal stromal reduction with smart pulse technology-as-sisted transperitoneal photorefractive keratomileusis(SPT-TPRK)and femtosecond laser-assisted in situ keratomileusis(FS-LASIK).Methods Patients undergoing laser surgery in the Department of Ophthalmology of the First Affiliated Hos-pital of Xinxiang Medical College from February to September 2023 were selected and divided by surgical modalities into an SPT-TPRK group(21 cases,37 eyes)and an FS-LASIK group(18 cases,32 eyes).The uncorrected visual acuity(UCVA),intraocular pressure,corneal thickness,and corneal epithelial thickness were measured before surgery,1 week,1 month and 3 months after surgery.The cutting deviation was calculated,and the change of corneal stromal thickness was ob-served.The correlation between the predicted corneal stromal reduction and the cutting deviation was analyzed.Results There were significant differences in UCVA among different time points in both SPT-TPRK and FS-LASIK groups(all P＜0.001).The UCVA of patients in the FS-LASIK group was significantly higher than that in the SPT-TPRK group 1 week after surgery(P＜0.001).The difference in UCVA was not statistically significant between the two groups 1 month and 3 months after surgery(all P＞0.05).There were significant differences in intraocular pressure among different time points in both SPT-TPRK and FS-LASIK groups(all P＜0.001).The FS-LASIK group had a lower intraocular pressure than the SPT-TPRK group 1 week after surgery(P＜0.05),but the difference in intraocular pressure was not statistically significant between the two groups 1 month and 3 months after surgery(all P＞0.05).There was significant difference between predicted cor-neal stromal reductions and actual corneal stromal reductions measured at different time points postoperatively in both SPT-TPRK and FS-LASIK groups(all P＜0.001).The actual corneal stromal reductions were higher than the predicted ones in the SPT-TPRK group at all postoperative time points(all P＜0.05).In the FS-LASIK group,the actual corneal stromal re-ductions were higher than the predicted ones 1 week and 1 month after surgery(all P＜0.05),but the actual and predicted corneal stromal reductions were not significantly different 3 months after surgery(P＞0.05).The cutting deviations were not significantly different between SPT-TPRK and FS-LASIK groups 1 month after surgery(P＞0.05),while the cutting de-viations were significantly different between the two groups 1 week and 3 months after surgery(all P＜0.05).There were significant differences in the change of the stromal thickness among different time points in both SPT-TPRK and FS-LASIK groups(all P＜0.05).There was no significant difference in the change of the stromal thickness among different time points in the SPT-TPRK group(all P＞0.05).The stromal thickness showed greater changes 1 month after surgery than that 1 week after surgery in the FS-LASIK group(P＜0.05).There were no significant differences in the change of the stromal thickness between 1 month and 3 months after surgery in the FS-LASIK group(P＞0.05).Correlation analysis showed a positive correlation between the predicted corneal stromal reduction and the cutting deviation in the SPT-TPRK group 1 week after surgery(P＜0.05),but they had no correlation 1 month and 3 months after surgery(all P＞0.05).There was no correlation between the predicted corneal stromal reduction and the cutting deviation in the FS-LASIK group at all post-operative time points(all P＞0.05).Conclusion Patients who receive SPT-TPRK or FS-LASIK can both achieve good visual acuity and a reduction in intraocular pressure.FS-LASIK has better predictability in refractive error correction than SPT-TPRK.

Objective To explore the injury process of retinal ganglion cells(RGCs)after glucocorticoid(GC)-in-duced ocular hypertension(OHT),as well as the protective effect and mechanism of estradiol(E2)in RGC injury in rats with OHT.Methods Atotalof36(36 eyes)12-week-old male Sprague-Dawley(SD)rats were randomly divided into the blank control group,the GC-OHT group,and the OHT-E2 group,with 12 rats in each group.Rats in the GC-OHT group and the OHT-E2 group were subconjunctivally injected with GC,while those in the blank control group were subconjuncti-vally injected with an equal volume of normal saline.Two weeks after modeling,in addition to being injected with GC,rats in the OHT-E2 group were also provided with E2 eye drops.Before modeling and 1,2,3,and 4 weeks after modeling,the intraocular pressure of rats in each group was measured.The visual acuity changes of rats in each group were detected by pattern electroretinogram(P-ERG)and flash visual evoked potential(F-VEP)4 weeks after modeling.After the eyeballs were removed,the distribution and number of RGCs in rats of each group were observed by immunofluorescence staining.Immunohistochemistry,Western blot,and real-time fluorescence-based quantitative polymerase chain reaction were used to detect the relative protein and mRNA expression levels of NOD-like receptor protein 3(NLRP3),cysteine aspartate prote-ase-1(Caspase-1),and gasdermin-D(GSDMD)in rats in each group.Results There was no statistically significant difference in the intraocular pressure of rats in each group before modeling(P＞0.05).Compared with the blank control group,the intraocular pressure of rats in the GC-OHT group increased 1,2,3,and 4 weeks after modeling,and the differ-ences were all statistically significant(all P＜0.01).Compared with the GC-OHT group,the intraocular pressure of rats in the OHT-E2 group decreased 3 and 4 weeks after modeling,and the differences were all statistically significant(all P＜0.01).The P-ERG and F-VEP results showed that compared with the blank control group,the amplitudes of P50 and P1 waves of rats in the GC-OHT group decreased,and the differences were both statistically significant(both P＜0.05).Com-pared with the GC-OHT group,the amplitudes of P50 and Pl waves of rats in the OHT-E2 group increased,and the differ-ences were both statistically significant(both P＜0.05).The immunofluorescence staining results showed that compared with the blank control group,the number of RGCs of rats in the GC-OHT group decreased,and the difference was statisti-cally significant(P＜0.001).Compared with the GC-OHT group,the number of RGCs of rats in the OHT-E2 group in-creased,and the difference was statistically significant(P＜0.001).The results of immunohistochemistry,Western blot,and real-time fluorescence-based quantitative polymerase chain reaction showed that compared with the blank control group,the relative protein and mRNA expression levels of NLRP3,Caspase-1,and GSDMD in the retina of rats in the GC-OHT group all increased,and the differences were all statistically significant(all P＜0.05).Compared with the GC-OHT group,the relative protein and mRNA expression levels of NLRP3,Caspase-1,and GSDMD in the retina of rats in the OHT-E2 group all decreased,and the differences were all statistically significant(all P＜0.01).Conclusion GC-induced OHT can cause pyroptosis of RGCs,and E2 may alleviate the injury of RGCs in rats with OHT by inhibiting the pyroptosis-related NLRP3/Caspase-1/GSDMD signaling pathway.