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 construct an age prediction model for adolescents using radiomics from oral panoramic radiographs.Methods Panoramic radiographic images of 441 adolescent patients aged 11.00～13.99 years were imported into the open-source software 3D Slicer for segmentation of regions of interest(ROI).Python was used to extract all features from the ROIs of all patients.The patients were randomly divided into a training set and a test set at a ratio of 7∶3.Machine learning methods were applied to analyze the correlation between radiomics features and age characteristics to build the age prediction model.Results Out of 863 two-dimensional radiomics features,10 were selected.Three machine learning methods—support vector machine,random forest,and logistic regression—were used to train the model on the training set,and the best machine learning model was chosen.The performance of the machine learning models was evaluated using the Area Under Curve(AUC).In the test set,the AUCs for females were 0.795,0.830,and 0.795 for the three methods respectively,while for males,they were 0.830,0.864,and 0.846.Conclusion The radiomics model based on oral panoramic radiographs demonstrates good diagnostic efficacy and can be used for age prediction.

Objective To construct an age prediction model for adolescents using radiomics from oral panoramic radiographs.Methods Panoramic radiographic images of 441 adolescent patients aged 11.00～13.99 years were imported into the open-source software 3D Slicer for segmentation of regions of interest(ROI).Python was used to extract all features from the ROIs of all patients.The patients were randomly divided into a training set and a test set at a ratio of 7∶3.Machine learning methods were applied to analyze the correlation between radiomics features and age characteristics to build the age prediction model.Results Out of 863 two-dimensional radiomics features,10 were selected.Three machine learning methods—support vector machine,random forest,and logistic regression—were used to train the model on the training set,and the best machine learning model was chosen.The performance of the machine learning models was evaluated using the Area Under Curve(AUC).In the test set,the AUCs for females were 0.795,0.830,and 0.795 for the three methods respectively,while for males,they were 0.830,0.864,and 0.846.Conclusion The radiomics model based on oral panoramic radiographs demonstrates good diagnostic efficacy and can be used for age prediction.

Background: s/Aims: Non-invasive models stratifying clinically significant portal hypertension (CSPH) are limited. Herein, we developed a new non-invasive model for predicting CSPH in patients with compensated cirrhosis and investigated whether carvedilol can prevent hepatic decompensation in patients with high-risk CSPH stratified using the new model. Methods: Non-invasive risk factors of CSPH were identified via systematic review and meta-analysis of studies involving patients with hepatic venous pressure gradient (HVPG). A new non-invasive model was validated for various performance aspects in three cohorts, i.e., a multicenter HVPG cohort, a follow-up cohort, and a carvediloltreating cohort. Results: In the meta-analysis with six studies (n=819), liver stiffness measurement and platelet count were identified as independent risk factors for CSPH and were used to develop the new “CSPH risk” model. In the HVPG cohort (n=151), the new model accurately predicted CSPH with cutoff values of 0 and –0.68 for ruling in and out CSPH, respectively. In the follow-up cohort (n=1,102), the cumulative incidences of decompensation events significantly differed using the cutoff values of <–0.68 (low-risk), –0.68 to 0 (medium-risk), and >0 (high-risk). In the carvediloltreated cohort, patients with high-risk CSPH treated with carvedilol (n=81) had lower rates of decompensation events than non-selective beta-blockers untreated patients with high-risk CSPH (n=613 before propensity score matching [PSM], n=162 after PSM). Conclusions Treatment with carvedilol significantly reduces the risk of hepatic decompensation in patients with high-risk CSPH stratified by the new model.

Background: s/Aims: Non-invasive models stratifying clinically significant portal hypertension (CSPH) are limited. Herein, we developed a new non-invasive model for predicting CSPH in patients with compensated cirrhosis and investigated whether carvedilol can prevent hepatic decompensation in patients with high-risk CSPH stratified using the new model. Methods: Non-invasive risk factors of CSPH were identified via systematic review and meta-analysis of studies involving patients with hepatic venous pressure gradient (HVPG). A new non-invasive model was validated for various performance aspects in three cohorts, i.e., a multicenter HVPG cohort, a follow-up cohort, and a carvediloltreating cohort. Results: In the meta-analysis with six studies (n=819), liver stiffness measurement and platelet count were identified as independent risk factors for CSPH and were used to develop the new “CSPH risk” model. In the HVPG cohort (n=151), the new model accurately predicted CSPH with cutoff values of 0 and –0.68 for ruling in and out CSPH, respectively. In the follow-up cohort (n=1,102), the cumulative incidences of decompensation events significantly differed using the cutoff values of <–0.68 (low-risk), –0.68 to 0 (medium-risk), and >0 (high-risk). In the carvediloltreated cohort, patients with high-risk CSPH treated with carvedilol (n=81) had lower rates of decompensation events than non-selective beta-blockers untreated patients with high-risk CSPH (n=613 before propensity score matching [PSM], n=162 after PSM). Conclusions Treatment with carvedilol significantly reduces the risk of hepatic decompensation in patients with high-risk CSPH stratified by the new model.

The concept of "qi deficiency with stagnation" refers to a pathological state characterized by the depletion of primordial qi， impaired qi transformation， and the development of internal stagnation. Under the cyclic chemotherapy regimen in oncology， chemotherapy-induced myelosuppression follows a progressive pathological course from qi deficiency to increasing stagnation. This sequential evolution from mild to severe myelosuppression closely aligns with the dynamic syndrome differentiation and treatment framework of "qi deficiency with stagnation". "Qi deficiency" reflects the gradual depletion of qi， blood， and essence， while "stagnation" refers to the accumulation of phlegm， turbid dampness， and blood stasis. These two components interact reciprocally， forming a vicious cycle where deficiency leads to stagnation， and stagnation further damages the healthy qi. In the early stage of mild myelosuppression， chemotoxicity begins to accumulate in the bone marrow， leading to qi consumption， blood deficiency， yin injury， and the gradual formation of turbid phlegm and damp stagnation. In the advanced stage of severe myelosuppression， the accumulation of toxicity causes qi sinking， exhaustion of essence， and marrow depletion， along with blood stasis obstructing the collaterals. Treatment strategies should be based on syndrome differentiation， with an emphasis on assessing the severity of the condition， balancing deficiency and excess， and achieving both symptomatic relief and root cause resolution.

Background: s/Aims: Non-invasive models stratifying clinically significant portal hypertension (CSPH) are limited. Herein, we developed a new non-invasive model for predicting CSPH in patients with compensated cirrhosis and investigated whether carvedilol can prevent hepatic decompensation in patients with high-risk CSPH stratified using the new model. Methods: Non-invasive risk factors of CSPH were identified via systematic review and meta-analysis of studies involving patients with hepatic venous pressure gradient (HVPG). A new non-invasive model was validated for various performance aspects in three cohorts, i.e., a multicenter HVPG cohort, a follow-up cohort, and a carvediloltreating cohort. Results: In the meta-analysis with six studies (n=819), liver stiffness measurement and platelet count were identified as independent risk factors for CSPH and were used to develop the new “CSPH risk” model. In the HVPG cohort (n=151), the new model accurately predicted CSPH with cutoff values of 0 and –0.68 for ruling in and out CSPH, respectively. In the follow-up cohort (n=1,102), the cumulative incidences of decompensation events significantly differed using the cutoff values of <–0.68 (low-risk), –0.68 to 0 (medium-risk), and >0 (high-risk). In the carvediloltreated cohort, patients with high-risk CSPH treated with carvedilol (n=81) had lower rates of decompensation events than non-selective beta-blockers untreated patients with high-risk CSPH (n=613 before propensity score matching [PSM], n=162 after PSM). Conclusions Treatment with carvedilol significantly reduces the risk of hepatic decompensation in patients with high-risk CSPH stratified by the new model.

Hemophilia A and hemophilia B are hereditary coagulation bleeding disorders. Traditional treatment primarily relies on factor replacement therapy using coagulation factor Ⅷ(FⅧ) or coagulation factor Ⅸ (FⅨ)products. Although conventional therapies can alleviate bleeding symptoms to some extent, they also have certain limitations, such as the need for frequent infusions, the risk of infection, and the potential development of inhibitors in some patients. Currently, treatment strategies for hemophilia are gradually shifting toward non-factor therapies, providing the appearence of novel non-factor drugs. However, these novel therapies not only interfere with traditional coagulation assays but may also fail to comprehensively evaluate their efficacy and safety through conventional coagulation tests. Therefore, there is an urgent need to develop and optimize new laboratory testing methods to ensure accurate assessment of patients′ responses to non-factor therapies and the hemostatic capacity of the drugs themselves. Although some studies have explored the coagulation factor equivalence of non-factor agents, such equivalence cannot fully reflect the actual hemostatic effect in patients after treatment and is therefore unsuitable as a prognostic indicator. Compared with assessing coagulation factor equivalence, total coagulation assays, such as the thrombin generation assay (TGA), can more accurately evaluate efficacy and safety. TGA can take into account multiple factors in the coagulation process, providing a more comprehensive assessment of coagulation function. Furthermore, combining TGA with patient symptoms for comprehensive analysis can enhance its prognostic predictive ability, offering more reliable support for clinical decision-making.

Objective:To analyze the levels of thrombin generation and activated protein C resistance (APC-R) in lupus anticoagulant (LA)-positive patients, and to assess their effectiveness in predicting thrombotic risk in these patients.Methods:Retrospective case-control study. A total of 185 patients with positve LA [91 males, 94 females; age (47.59±19.14) years] in Ruijin Hospital of Shanghai Jiaotong University School of Medicine from November 1st, 2024 to March 31st, 2025 were included. Patients were stratified into thrombotic ( n=91) and non-thrombotic groups ( n=94) based on clinical diagnosis and imaging evidence of thrombosis. The basic characteristics and routine laboratory coagulation levels of LA-positive patients were analyzed. Post-test plasma samples were collected from 43 cases with positive or strongly positive LA, categorized into thrombotic ( n=23) and non-thrombotic ( n=20) groups. Additionally, plasma was collected from 80 healthy controls [40 males and 40 females, age (38.37±15.74) years]. Using simple random sampling method, plasma samples from 10 selected males and 10 selected females were mixed to make 1 group of healthy control, thus accordingly resulted in a total of 4 healthy control groups. Thrombin generation assays (TGA) were then employed to measure prothrombin generation and activated protein C resistance (APC-R) levels in the healthy control, non-thrombotic, and thrombotic groups. One-way analysis of variance was utilized to compare thrombin generation and APC-R levels across these groups. Results:Among the routine laboratory coagulation indexes, the median levels of activated partial thromboplastin time (APTT), fibrin degradation product (FDP) and protein C (PC) in thrombotic group were 30.9 (28.8, 35.5) s, 2.5 (1.3, 2.8) mg/L, and 107.0 (93.0, 127.0)%, respectively, which were significantly higher compared with the non-thrombosis group (all P<0.05). However, between the thrombotic and non-thrombotic group, no statistically significant differences were observed for the levels of prothrombin time (PT), thrombin time (TT), fibrinogen (Fg), or D-dimer (D-D) ( P>0.05). The TGA results showed that the total thrombin generation, the maximal thrombin generation and APC-R levels of patients in the thrombotic group were (1 118.72±387.34) nmol/L·min, (106.01±59.00) nmol/L and (0.33±0.22), respectively, which were significantly higher compared with those in the non-thrombotic group (all P<0.05). Conclusion:Significantly increased thrombin generation and enhanced APC-R were present in the LA-positive patients with thrombosis, indicating the important values of thrombin generation and APC-R in assessing thrombosis risk among this population.

Objective:To compare the accuracy of one-stage clotting assay and chromogenic substrate assay for testing an extended half-life recombinant FⅧ and to explore standardized conversion models between methods.Methods:Observational study. FⅧ activity (FⅧ:C) in plasma samples with theoretical values of 1 000, 800, 600, 500, 400, and 300 IU/L was measured using both one-stage clotting assay (employing Siemens Actin FSL reagent, Werfen SynthASil reagent, Stago PTT-A reagent) and the chromogenic substrate assay from Hyphen Biomed. Differences in FⅧ:C measured by the various methods were compared using the SNK test. Recovery rates were calculated to evaluate the accuracy of each assay. Sample activity was verified using the thrombin generation assay (TGA). Correlations between activities determined by the different assay systems were assessed using linear regression analysis.Results:Observational study. FⅧ activity (FⅧ:C) in diluted plasma samples with theoretical values of 1 000, 800, 600, 500, 400, and 300 IU/L was measured using both one-stage clotting assay (employing Siemens Actin FSL reagent, Werfen SynthASil reagent, Stago PTT-A reagent) and the chromogenic substrate assay from Hyphen Biomed. Differences in FⅧ:C measured by the various methods were compared using the SNK test. Recovery rates were calculated to evaluate the accuracy of each assay. Sample activity was verified using the thrombin generation assay (TGA). Correlations between activities determined by the different assay systems were assessed using linear regression analysis.Conclusion:Some marked one-stage clotting assay system has limitations in the clinical detection of extended half-life recombinant FⅧ. While the chromogenic substrate assay provides more accurate results. The one-stage clotting assay values can undergo cross-assay correction for FⅧ:C using a standardized conversion coefficient, which can further elevate the accuracy of monitoring hemophilia treatment efficacy.