Objective: To develop a dual-branch deep learning framework for accurate multi-label classification of fundus diseases, addressing the key limitations of insufficient complementary feature extraction and inadequate cross-modal feature fusion in existing automated diagnostic methods. Methods: The fundus multi-label classification dataset with 12 disease categories (FMLC-12) dataset was constructed by integrating complementary samples from Ocular Disease Intelligent Recognition (ODIR) and Retinal Fundus Multi-Disease Image Dataset (RFMiD), yielding 6 936 fundus images across 12 retinal pathology categories, and the framework was validated on both FMLC-12 and ODIR. Inspired by the holistic multi-regional assessment principle of the Five Wheels theory in traditional Chinese medicine (TCM) ophthalmology, the dual-branch multi-label network (DBMNet) was developed as a novel framework integrating complementary visual feature extraction with pathological correlation modeling. The architecture employed a TransNeXt backbone within a dual-branch design: one branch processed red-green-blue (RGB) images to capture color-dependent features, such as vascular patterns and lesion morphology, while the other processed grayscale-converted images to enhance subtle textural details and contrast variations. A feature interaction module (FIM) effectively integrated the multi-scale features from both branches. Comprehensive ablation studies were conducted to evaluate the contributions of the dual-branch architecture and the FIM. The performance of DBMNet was compared against four state-of-the-art methods, including EfficientNet Ensemble, transfer learning-based convolutional neural network (CNN), BFENet, and EyeDeep-Net, using mean average precision (mAP), F1-score, and Cohen's kappa coefficient. Results: The dual-branch architecture improved mAP by 15.44 percentage points over the single-branch TransNeXt baseline, increasing from 34.41% to 44.24%, and the addition of FIM further boosted mAP to 49.85%. On FMLC-12, DBMNet achieved an mAP of 49.85%, a Cohen’s kappa coefficient of 62.14%, and an F1-score of 70.21%. Compared with BFENet (mAP: 45.42%, kappa: 46.64%, F1-score: 71.34%), DBMNet outperformed it by 4.43 percentage points in mAP and 15.50 percentage points in kappa, while BFENet achieved a marginally higher F1-score. On ODIR, DBMNet achieved an F1-score of 85.50%, comparable to state-of-the-art methods. Conclusion DBMNet effectively integrates RGB and grayscale visual modalities through a dual-branch architecture, significantly improving multi-label fundus disease classification. The framework not only addresses the issue of insufficient feature fusion in existing methods but also demonstrates outstanding performance in balancing detection across both common and rare diseases, providing a promising and clinically applicable pathway for standardized, intelligent fundus disease classification.

Tracheobronchial adenoid cystic carcinoma （TACC） is a low-grade malignant tumor originating from the airway mucosa. Despite its slow progression，it is characterized by high invasiveness，frequent recurrence，and a strong tendency for metastasis. Preclinical studies have shown that vascular-targeted therapy holds significant potential. However，an effective systemic treatment for TACC has not been established yet. This study explored TACC from the perspective of "Feiji" in traditional Chinese medicine （TCM） as the starting point. It deeply investigated the mechanisms of abnormal collaterals and tumor vascular recruitment and further elaborated on the theoretical connection between abnormal collaterals and tumor vascular recruitment. Firstly，collateral hyperactivity led to disordered and erratic pulmonary collaterals. Their abnormal structures were similar to the disorderly and tortuous nature of tumor （pseudo）angiogenesis. This resulted in imbalances in the functions of circulation，perfusion，and reverse injection of the pulmonary collaterals，and then led to unrestrained collateral dysfunction and the accumulation of pathogenic factors. Secondly，the remodeling of the extracellular matrix （ECM） and epithelial-mesenchymal transition （EMT） in TACC were critical processes in vascular co-option （VCO），representing the micro-level manifestation of the displacement of nutrient and defense. During this process，ECM remodeling made TACC cells more likely to hijack normal blood vessels，creating a complex vascular microenvironment conducive to tumor growth. In terms of treatment，this study proposed a TCM strategy of "regulating collaterals to expel pathogenic factors and nourishing collaterals to strengthen the healthy Qi"，and listed potential TCM. These were intended to regulate the Qi and blood in the collaterals，repair the functions of abnormal collaterals，and intervene in the vascular recruitment process of TACC. Future research should focus on improving the TCM clinical syndrome characteristics of TACC. Through modern molecular biology techniques，it is necessary to deeply analyze the micro-level pattern of vascular recruitment in TACC. This would enrich the understanding of the profound connection between abnormal collaterals and tumor vascular recruitment，providing empirical evidence for TCM-targeted therapies for vascular recruitment in TACC.

Houpo Qiwutang originated from the Synopsis of the Golden Chamber， and it consists of seven medicines： Magnoliae Officinalis Cortex， Rhei Radix et Rhizoma， Aurantii Fructus Immaturus， Cinnamomi Ramulus， Zingiberis Rhizoma Recens， Glycyrrhizae Radix et Rhizoma， and Jujubae Fructus. It is a basic formula for the treatment of abdominal fullness. Through the bibliometric method， the historical history， drug base， preparation and dosage， decoction method， and ancient and modern applications of Houpu Qiwu Tang were analyzed by means of textual research. The research finds that Houpu Qiwu Tang has been passed down through the generations in an orderly manner with fewer changes. The drug base of this formula is basically clear， and the base of Magnoliae Officinalis Cortex， Rhei Radix et Rhizoma， Cinnamomi Ramulus， Zingiberis Rhizoma Recens， and Jujubae Fructus is consistent with the 2020 edition of Chinese Pharmacopoeia. The mainstream base of Aurantii Fructus Immaturus is the dried young fruit of Citrus aurantium of Rutaceae family， and the historical mainstream base of Glycyrrhizae Radix et Rhizoma is the dried root of Glycyrrhiza uralensis of Leguminosae family. The modern dosage of this formula is 110.40 g of Magnoliae Officinalis Cortex， 41.40 g of Rhei Radix et Rhizoma， 69 g of Aurantii Fructus Immaturus， 27.60 g of Cinnamomi Ramulus， 69 g of Zingiberis Rhizoma Recens， 41.40 g of Glycyrrhizae Radix et Rhizoma， and 30 g of Jujubae Fructus. In addition， the decoction method is to add 2 000 mL of water with the above seven flavors of the medicine， boil it to 800 mL， and then take 160 mL in a warm state each time. The amount of the medicine taken for each time is 22.08 g of Magnoliae Officinalis Cortex， 8.28 g of Rhei Radix et Rhizoma， 13.80 g of Aurantii Fructus Immaturus， 5.52 g of Cinnamomi Ramulus， 13.80 g of Zingiberis Rhizoma Recens， 8.28 g of Glycyrrhizae Radix et Rhizoma， and 6 g of Jujubae Fructus. The modern application of this formula involves the digestive system， respiratory system， and urinary system. It is more advantageous in digestive system diseases such as early postoperative inflammatory bowel obstruction， functional dyspepsia， gastric pain， functional abdominal distension， and gastric reflux esophagitis. By comprehensively examining the key information of Houpu Qiwu Tang， this paper aims to provide literature support for the development and clinical application of this formula.

Objective By combining biological detection and imaging evaluation, a clinical prediction model is constructed based on a large cohort to improve the accuracy of distinguishing between benign and malignant pulmonary nodules. Methods A retrospective analysis was conducted on the clinical data of the 32 627 patients with pulmonary nodules who underwent chest CT and testing for 7 types of lung cancer-related serum autoantibodies (7-AABs) at our hospital from January 2020 to April 2024. The univariate and multivariate logistic regression models were performed to screen independent risk factors for benign and malignant pulmonary nodules, based on which a nomogram model was established. The performance of the model was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Results A total of 1 017 patients with pulmonary nodules were included in the study. The training set consisted of 712 patients, including 291 males and 421 females, with a mean age of (58±12) years. The validation set included 305 patients, comprising 129 males and 176 females, with a mean age of (58±13) years. Univariate ROC curve analysis indicated that the combination of CT and 7-AABs testing achieved the highest area under the curve (AUC) value (0.794), surpassing the diagnostic efficacy of CT alone (AUC=0.667) or 7-AABs alone (AUC=0.514). Multivariate logistic regression analysis showed that radiological nodule diameter, nodule nature, and CT combined with 7-AABs detection were independent predictors, which were used to construct a nomogram prediction model. The AUC values for this model were 0.826 and 0.862 in the training and validation sets, respectively, demonstrating excellent performance in DCA. Conclusion The combination of 7-AABs with CT significantly enhances the accuracy of distinguishing between benign and malignant pulmonary nodules. The developed predictive model provides strong support for clinical decision-making and contributes to achieving precise diagnosis and treatment of pulmonary nodules.

Cholelithiasis is a common biliary system disease with a high incidence worldwide. Abnormal lipid metabolism has been shown to play a key role in the mechanism of gallstones. Therefore, recent research literature on the genes, proteins, and molecular substances involved in lipid metabolism during the pathogenesis of gallstones has been conducted. This study aimed to determine the role of lipid metabolism in the pathogenesis of gallstones and provide insights for future studies using previous research in genomics, metabolomics, transcriptomics, and other fields.

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.

Cholelithiasis is a common biliary system disease with a high incidence worldwide. Abnormal lipid metabolism has been shown to play a key role in the mechanism of gallstones. Therefore, recent research literature on the genes, proteins, and molecular substances involved in lipid metabolism during the pathogenesis of gallstones has been conducted. This study aimed to determine the role of lipid metabolism in the pathogenesis of gallstones and provide insights for future studies using previous research in genomics, metabolomics, transcriptomics, and other fields.

Cholelithiasis is a common biliary system disease with a high incidence worldwide. Abnormal lipid metabolism has been shown to play a key role in the mechanism of gallstones. Therefore, recent research literature on the genes, proteins, and molecular substances involved in lipid metabolism during the pathogenesis of gallstones has been conducted. This study aimed to determine the role of lipid metabolism in the pathogenesis of gallstones and provide insights for future studies using previous research in genomics, metabolomics, transcriptomics, and other fields.

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.

Cholelithiasis is a common biliary system disease with a high incidence worldwide. Abnormal lipid metabolism has been shown to play a key role in the mechanism of gallstones. Therefore, recent research literature on the genes, proteins, and molecular substances involved in lipid metabolism during the pathogenesis of gallstones has been conducted. This study aimed to determine the role of lipid metabolism in the pathogenesis of gallstones and provide insights for future studies using previous research in genomics, metabolomics, transcriptomics, and other fields.