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 understand the current status of psychological sub health among secondary vocational school students and explore its related factors, so as to provide a scientific basis for improving their mental health. Methods: From September to December 2024, a convenience sampling method was used to conduct a questionnaire survey among 5 141 secondary vocational school students from 16 schools across 8 provinces and municipalities (Fujian, Chongqing, Guangdong, Guangxi, Hubei, Jiangxi, Shanghai, Zhejiang). A self designed questionnaire was used to collect data on students demographic characteristics and lifestyle behaviors. The Multidimensional Sub health Questionnaire of Adolescents was adopted to assess psychological sub health status. Multivariate binary Logistic stepwise regression analysis was performed to explore the related factors of psychological sub health among secondary vocational school students. Results: The detection rate of psychological sub health among secondary vocational school students was 11.0%, with detection rates of emotional problems, conduct problems, and social adaptation difficulty being 12.3 %, 12.5%, and 9.5%, respectively. Logistic regression analysis revealed that boys and students whose fathers had an educational level of primary school or below, and junior high school, had relatively lower risks of developing psychological sub health or emotional problems, conduct problems, and social adaptation difficulty ( OR =0.55-0.64, all P <0.05). Conversely, students with urban household registration, those with left behind experience, those with poor self rated family economic status, those from other family structures, those classified as overweight and obesity, and those with sleep disorders, frequent consumption of sugar sweetened beverages, frequent consumption of takeout/delivery food, smoking, alcohol consumption, and low to moderate physical activity levels exhibited significantly higher risks across psychological sub health or emotional problems,conduct problems, and social adaptation difficulty ( OR =1.25-4.79, all P <0.05). Conclusions The psychological sub health condition of secondary vocational school students should not be neglected. Psychological sub health of secondary vocational school students is related to multiple factors such as demographic characteristics and lifestyle behaviors. Multi dimensional intervention measures should be implemented to improve their mental health.

Objective: To investigate the association between brain and muscle Arnt like protein 1( BMAL 1) gene and ambulatory blood pressure (ABP) parameters in college students, and to explore the influence of the interaction between the gene and weight status on the ABP levels, so as to provide reference for early prevention of chronic cardiovascular diseases related to hypertension. Methods: During September 2022 to June 2024, a total of 510 college students were recruited from a university in Changsha, China for on site questionnaire investigation, physical examination, ABP monitoring and genotyping testing. Multiple linear regression method was used to explore the association between the BMAL 1 gene and ABP indicators. An interaction term was included in the general linear model of multiple linear regression to analyze the interactive effects of BMAL 1 gene polymorphisms and weight status on ABP levels. Results: The prevalence of abnormal 24 hour blood pressure, abnormal daytime blood pressure, and abnormal nighttime blood pressure were 3.3%, 3.1%, and 3.9%, respectively. Multiple linear regression analysis showed that the BMAL 1/rs7950226 polymorphism was positively correlated with the 24 hour diastolic blood pressure(DBP) and the daytime DBP level after adjusting for gender, age, and body mass index( β =0.87,0.99, both P <0.05). Also, interaction between BMAL 1/ rs 11022775 and weight status on the nighttime DBP level ( P interaction =0.03) was found. The CC genotype carriers had significantly higher nighttime DBP level ( β =3.52, P <0.05) among overweight/obesity college students, but no differences in nocturnal DBP levels were observed between CC genotype carriers and TT+CT genotype carriers among college students with normal body weight( P > 0.05). Conclusions The rs 7950226 polymorphism is associated with 24 hours DBP and daytime DBP levels. Significant interaction between rs 11022775 with weight status on the nighttime DBP level is found among college students.

Objective: To investigate the heritability of axial length (AL) by comparing the consistency of AL in monozygotic (MZ) and dizygotic (DZ) twins, thereby providing data support for research on the genetic mechanisms and prevention and control practices of myopia in children and adolescents. Methods: A total of 137 twin pairs aged 3 to 16 years who attended the Optometry Center of the First Affiliated Hospital of Anhui Medical University from January 2021 to December 2024 were enrolled, comprising 79 DZ pairs and 58 MZ pairs. Biometry was used to measure children s axial length, and structural equation modeling within the OpenMx package was applied to calculate the heritability of axial length. Results: The overall mean axial length of the twin cohort was (23.7±1.5) mm. The intraclass correlation coefficient (ICC) for axial length in all twins was 0.82 (95% CI =0.76-0.87) ( P < 0.05 ). The ICC for MZ twins was 0.97 (95% CI =0.94-0.98), which was higher than that for DZ twins ( ICC =0.71, 95% CI =0.58-0.80) (both P <0.05). Maximum likelihood estimation using OpenMx revealed that the additive genetic plus unique environmental (AE) model provided the best fit. Specifically, additive genetic factors (A) accounted for 93.63% (95% CI =90.31%-95.69%) of the total variance, while unique environmental factors (E) accounted for 6.37% (95% CI =4.31%-9.69%). Conclusion Axial length in children is predominantly influenced by genetic factors, while unique environmental factors also play a contributory role.

Chemical constituents of n-butanol fraction of ethanol extract from the leaves of Cyclocarya paliurus (Batalin) Iljinskaja were studied. Ten compounds were purified by silica gel, MCI, ODS, Sephadex LH-20 column chromatography and semi-preparative high-performance liquid chromatography. Based on the physicochemical properties and spectroscopic data, these compounds were identified as (4S)-4,8-dihydroxy-α-tetralone-5-[6′-(3′′,5′′-dimethoxy-(E)-p-coumaroyl)]-β-D-glucopyranoside (1), (4S)-4,8-dihydroxy-α-tetralone-5-[6′-(E)-feruloyl]-β-D-glucopyranoside (2), (1S,3R,4S,5R)-4,5-di-O-caffeoyl quinic acid methyl ester (3), (1R,3R,4S,5R)-3,4-di-O-caffeoyl quinic acid methyl ester (4), (3R,5R)-3,4,5-tri-O-caffeoylquinic acid methyl ester (5), (1R,3R,4S,5R)-3-O-caffeoyl-5-O-p-coumaroyl quinic acid methyl ester (6), (1R,3R,4S,5R)-3-O-p-coumaroy-4-O-caffeoyl quinic acid methyl ester (7), (1R,3R,4S,5R)-3-O-caffeoyl-4-O-p-coumaroy quinic acid methyl ester (8), (3R,5R)-3,5-di-O-caffeoyl quinic acid methyl ester (9) and (1S,3R,4R,5R)-4-O-caffeoyl-5-O-feruloyl quinic acid methyl ester (10). Among them, compound 1 was a new compound, and compounds 3–10 were isolated from the genus Cyclocarya for the first time.

Objective Inflammatory myofibroblastic tumor (IMT) is a rare condition. This report summarizes the characteristics of IMT in order to strengthen clinicians' understanding of this disease. Case Presentation A 59-year-old female patient presented with intermittent right flank and abdominal pain with fever for 1 month, and a right renal mass detected 3 weeks ago. The highest body temperature during the course of the illness was 39℃. She received symptomatic antiinfective treatment at another hospital for 2 weeks, and the symptoms were alleviated. Enhanced CT of the lower abdomen strongly suggested a right renal carcinoma, with multiple small lymph nodes in the peritoneal cavity and retroperitoneum. MRI indicated a neoplastic lesion in the right kidney, with suspicion of chromophobe cell carcinoma. Laparoscopic partial right nephrectomy was performed under general anesthesia, and the procedure was successful. Postoperative pathology showed that there was significant localized infiltration of lymphocytes and formation of lymphoid follicles, and the lymph nodes showed chronic inflammation. The final diagnosis was IMT. In the follow-up of 3 months, no tumor recurrence was observed. Conclusion IMT has a high misdiagnosis rate. When imaging findings are atypical for renal cell carcinoma, IMT should be suspected. The preferred treatment is laparoscopic partial nephrectomy.

ObjectiveTo investigate the association of the traditional Chinese medicine （TCM） syndrome types of primary liver cancer （PLC） with clinical features and multimodal quantitative radiological features on computed tomography （CT） and magnetic resonance imaging （MRI）， and to provide a reference for the objectification of TCM syndrome differentiation and precise diagnosis and treatment. MethodsA retrospective analysis was performed for the clinical data of 312 patients who were diagnosed with PLC in The First Affiliated Hospital of Hunan University of Chinese Medicine from March 2020 to June 2025， and according to the TCM syndrome type， they were divided into stagnation of liver Qi group with 40 patients， stagnation of liver Qi and spleen deficiency group with 109 patients， Qi stagnation and blood stasis group with 62 patients， dampness-heat toxin amassment group with 81 patients， and liver-kidney Yin deficiency group with 20 patients. Clinical features and multimodal quantitative radiological features were compared between the patients with different TCM syndrome types. A one-way analysis of variance was used for comparison of normally distributed continuous data between multiple groups， and the least significant difference t-test was used for further comparison between two groups； the Kruskal-Wallis H test was used for comparison of non-normally distributed continuous data between multiple groups， and the Dunn’s multiple test was used for further comparison between two groups； the chi-square test was used for comparison of categorical data between groups， and the Bonferroni method was used for further comparison between two groups. ResultsThere were significant differences between the patients with different TCM syndrome types in China liver cancer staging （CNLC）， Child-Pugh class， alanine aminotransferase， aspartate aminotransferase， albumin， direct bilirubin， total bilirubin， prothrombin time， neutrophil， and albumin-bilirubin score （all P<0.05）. In the stagnation of liver Qi group， the patients with Child-Pugh class A accounted for 75.00%； among the patients with CNLC stage I PLC， the patients with stagnation of liver Qi accounted for 60.00%， and those with Qi stagnation and blood stasis syndrome accounted for 59.68%， while among the patients with CNLC stage IV PLC， the distribution proportion of dampness-heat toxin amassment （27.16%） and liver-kidney Yin deficiency （30.00%） was significantly higher than that of stagnation of liver Qi （2.50%） （all P<0.05）. Radiological examination showed that there were significant differences between the patients with different TCM syndrome types in the number of tumors， ascites， venous tumor thrombus， maximum tumor diameter， intrahepatic metastasis， and lymph node metastasis in the hepatic hilar and retroperitoneal regions （all P<0.05）. Compared with the patients with stagnation of liver Qi， the patients with liver depression and spleen deficiency or liver-kidney Yin deficiency were more likely to develop intrahepatic metastasis； the patients with liver depression and spleen deficiency， dampness-heat toxin amassment， or liver-kidney Yin deficiency were more likely to develop lymph node metastasis in the hepatic hilar and retroperitoneal regions； the patients with liver-kidney Yin deficiency were more likely to experience multiple tumors； the patients with liver depression and spleen deficiency or dampness-heat toxin amassment were more likely to develop ascites （all P<0.05）. Compared with the patients with Qi stagnation and blood stasis syndrome， the patients with liver depression and spleen deficiency had a significantly longer maximum tumor diameter and a significantly higher proportion of patients with venous tumor thrombus （both P<0.05）. Furthermore， among the 184 patients with MRI diffusion-weighted imaging sequences， the patients with dampness-heat toxin amassment or Qi stagnation and blood stasis syndrome had significantly higher ADC values and relative ADC values than those with stagnation of liver Qi （all P<0.05）. ConclusionThere are significant differences in CT/MRI radiological features and clinical features between PLC patients with different TCM syndrome types， among whom the patients with liver depression and spleen deficiency， dampness-heat toxin amassment， and liver-kidney Yin deficiency tend to exhibit progressive radiological features， and those with dampness-heat toxin amassment or Qi stagnation and blood stasis syndrome tend to have higher ADC values. These findings provide an objective basis for TCM syndrome differentiation in PLC.

To summarize the clinical characteristics, antibody spectrum and neuroelectrophysiological features of autoimmune nodopathy(AN), and to explore the phenotypic differences among different antibody-positive subgroups.

Objective To develop and validate a prediction model for in-hospital recurrent intensive care unit (ICU) admission in critically ill patients with ischemic stroke (IS) based on machine learning (ML) algorithms. Methods Clinical data from 2 929 IS patients were included from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. Least absolute shrinkage and selection operator (LASSO) regression was used to identify predictive factors, and the synthetic minority over-sampling technique (SMOTE) was employed to create a derivation cohort comprising 2 583 patients. These patients were randomly divided into a training set (n=2 066) and a test set (n=517) at an 8:2 ratio. Five ML algorithms, including decision tree, random forest, adaptive boosting (AdaBoost), gradient boosting decision tree (GBDT), and support vector machine (SVM), were performed to construct prediction models. Five-fold cross-validation was used to evaluate the performance of the model in the training set. The area under the receiver operating characteristic curve (ROC-AUC) and decision curve analysis (DCA) were used to assess and compare the models in the testing set. The best-performing model was interpreted by shapley additive explanations (SHAP). Results Among the 2 929 patients included, 704 (24.0%) experienced in-hospital recurrent ICU admission. Among the five ML models, the random forest model demonstrated the best predictive performance, with an AUC of 0.839 (95%CI 0.801–0.877). Feature importance analysis identified five most significant features affecting model prediction, including APS Ⅲ score, albumin, age, heart rate, and SOFA score. Conclusions ML-based models can effectively predict the risk of in-hospital recurrent ICU admission in critically ill patients with IS. The random forest model showed superior predictive performance, which may have potential applications in early clinical risk stratification and intervention.