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.

ObjectiveTo investigate the mechanisms of Runmu Dihuang decoction （RMDHD） in treating perimenopausal dry eye with liver-kidney Yin deficiency syndrome based on the silent information regulator 3 （SIRT3）/hypoxia-inducible factor-1α （HIF-1α）/nuclear factor-κB （NF-κB） signaling pathway. MethodsSixty female Sprague-Dawley rats were randomly divided into six groups （n=10 per group）： Sham operation group， model group， sodium hyaluronate eye drop group， and low-， medium-， and high-dose RMDHD groups （5.625， 11.25， 22.50 g·kg^-1）. Except for the sham operation group， all rats underwent bilateral ovariectomy and were administered 0.1% benzalkonium chloride eye drops combined with long-term chronic irritation to establish a perimenopausal dry eye model with liver-kidney Yin deficiency syndrome. Drug administration began in the 11th week after modeling and continued for 21 days. General conditions， screen-grip test scores， tear secretion volume， tear film breakup time （TFBUT）， and corneal fluorescein staining were recorded. Serum levels of reactive oxygen species （ROS）， follicle-stimulating hormone （FSH）， estradiol （E₂）， and progesterone （PROG） were measured by enzyme-linked immunosorbent assay （ELISA）. Pathological changes in the lacrimal glands， corneas， and uteri were observed using hematoxylin-eosin （HE） staining. Protein expression levels of SIRT3， HIF-1α， phosphorylated NF-κB p65 （p-NF-κB p65）， and total NF-κB p65 in the lacrimal glands were detected by Western blot. The expression of inflammatory cytokines interleukin-1β （IL-1β） and tumor necrosis factor-α （TNF-α） in the lacrimal glands was assessed by immunohistochemistry （IHC）. ResultsAfter model establishment， no significant differences were observed among the groups except the sham operation group. Compared with the sham operation group， the other groups exhibited slowed movement， dull responses， increased irritability， reduced body weight， elevated rectal temperature， decreased screen-grip test scores， reduced tear secretion， and significantly shortened TFBUT （P<0.05）. After treatment， compared with the model group， the sodium hyaluronate eye drop group and all RMDHD groups showed improved general conditions， significantly increased tear secretion （P<0.05）， prolonged TFBUT （P<0.05）， and elevated screen-grip test scores （P<0.05）. Serum ROS and FSH levels were significantly decreased， while E₂ and PROG levels were significantly increased （P<0.05）. Pathological damage to the cornea， lacrimal glands， and uterus was ameliorated. In addition， protein expression levels of SIRT3 and HIF-1α in the lacrimal glands were significantly upregulated （P<0.05）， whereas the expression of p-NF-κB p65， IL-1β， and TNF-α was significantly downregulated （P<0.05）. ConclusionRMDHD increases tear secretion and TFBUT， improves lacrimal gland and corneal injury， and alleviates dry eye symptoms in a perimenopausal dry eye rat model with liver-kidney Yin deficiency syndrome. The underlying mechanism may be related to regulation of the SIRT3/HIF-1α/NF-κB signaling pathway， inhibition of oxidative stress and inflammatory responses， and reduction of ocular surface tissue damage.

OBJECTIVE To study the imaging characteristics of the normal cricoarytenoid joint.METHODS A retrospective study was conducted on the upper airway CT images of 175 subjects with normal laryngoscopic findings.According to age groups,a qualitative evaluation was made of the calcification of the arytenoid cartilage(AC),the hyperplasia of the AC,and the degree of stenosis of the cricoarytenoid joint(CAJ).The study aimed to explore the changing trends of these factors with age.We evaluated the spatial position structures such as the length of the vocal cords(l-VC),the distance between the muscle process of the arytenoid cartilage and the thyroid cartilage(d-MPCC),and the angle of the cricoarytenoid joint(a-CAJ).RESULTS There were differences in calcification of AC,hyperplasia of AC and stenosis of CAJ among different age groups.The calcification of AC(r=0.36,P<0.001),hyperplasia of AC(r=0.49,P<0.001)and stenosis of CAJ(r=0.54,P<0.001)the were positively correlated with age.Bilateral l-VC and a-CAJ were symmetry(all P>0.05).CONCLUSION The morphology of the CAJ was symmetrical in the normal population.It gradually underwent calcification,hyperplasia,and stenosis with age.Upper airway CT examination could evaluate the morphology and spatial position of the CAJ,providing an anatomical reference for clinical practice

Abstract Modern western medicine typically focuses on treating specific symptoms or diseases, and traditional Chinese medicine (TCM) emphasizes the interconnections of the body’s various systems under external environment and takes a holistic approach to preventing and treating diseases. Phenomics was initially introduced to the field of TCM in 2008 as a new discipline that studies the laws of integrated and dynamic changes of human clinical phenomes under the scope of the theories and practices of TCM based on phenomics. While TCM Phenomics 1.0 has initially established a clinical phenomic system centered on Zhenghou (a TCM definition of clinical phenome), bottlenecks remain in data standardization, mechanistic interpretation, and precision intervention. Here, we systematically elaborates on the theoretical foundations, technical pathways, and future challenges of integrating digital medicine with TCM phenomics under the framework of “TCM phenomics 2.0”, which is supported by digital medicine technologies such as artificial intelligence, wearable devices, medical digital twins, and multi-omics integration. This framework aims to construct a closed-loop system of “Zhenghou–Phenome–Mechanism–Intervention” and to enable the digitization, standardization, and precision of disease diagnosis and treatment. The integration of digital medicine and TCM phenomics not only promotes the modernization and scientific transformation of TCM theory and practice but also offers new paradigms for precision medicine. In practice, digital tools facilitate multi-source clinical data acquisition and standardization, while AI and big data algorithms help reveal the correlations between clinical Zhenghou phenomes and molecular mechanisms, thereby improving scientific rigor in diagnosis, efficacy evaluation, and personalized intervention. Nevertheless, challenges persist, including data quality and standardization issues, shortage of interdisciplinary talents, and insufficiency of ethical and legal regulations. Future development requires establishing national data-sharing platforms, strengthening international collaboration, fostering interdisciplinary professionals, and improving ethical and legal frameworks. Ultimately, this approach seeks to build a new disease identification and classification system centered on phenomes and to achieve the inheritance, innovation, and modernization of TCM diagnostic and therapeutic patterns.

Objective: To investigate the prevalence of sleep quality among the elderly in nursing homes in Changning District, Shanghai Municipality, so as to provide insights into prevention and intervention strategies for improving sleep quality and overall quality of life for the elderly. Methods: The elderly from 25 nursing homes in Changning District were selected using a two-stage sampling method. Basic information including gender, age and types of medication were collected. Sleep quality was assessed using the Athens Insomnia Scale, and depressive symptoms were measured using the Geriatric Depression Scale. Factors affecting sleep quality among the elderly in nursing homes were analyzed using a multivariable logistic regression model. Results: A total of 739 participants were surveyed, including 516 males (69.82%) and 223 females (30.18%). The majority of participants were aged 80 to <90 years (478, 64.68%). Among them, 432 participants (58.46%) had normal sleep, 144 (19.49%) had suspected insomnia, and 163 (22.06%) had insomnia. Multivariable logistic regression analysis showed that older age (OR=1.030, 95%CI: 1.005-1.055), more medication types (OR=1.971, 95%CI: 1.381-2.812), frequent nighttime bathroom visits (OR=2.921, 95%CI: 1.853-4.605) and depressive symptoms (OR=3.295, 95%CI: 2.440-4.449) were associated with a higher risk of insomnia among the elderly in nursing homes. Conclusions Insomnia was reported in 22.06% of the elderly in nursing homes in Changning District. Age, the number of medication types, frequency of nighttime bathroom visits, and depressive symptoms are the main influencing factors for their sleep quality.

Objective To analyze the urban drinking water quality and its influencing factors in Anhui Province from 2014 to 2022, and to provide a scientific basis for water quality improvement and protection. Methods The data were collected, saved and monitored according to the Standard Test Method for Drinking Water (GB/T5750-2006) and evaluated according to the Hygienic Standard for Drinking Water (GB 5749-2006). Results A total of 20 941 samples were collected, and the overall qualified rate was 84.26%. The qualified rate of urban drinking water increased from 76.9% in 2014 to 93.3% in 2022, and the qualified rate of water quality was on the rise (χ²=544.43, P＜0.01). From 2014 to 2022, the qualified rate of water quality in dry season was higher than that in wet season (χ²=35.98, P<0.001), the qualified rate of surface water was higher than that of ground water (χ²=4440.8, P<0.001), and the qualified rate of peripheral tap water was higher than that of factory water (χ²=145.1, P<0.001). Among all kinds of disinfection methods, chlorination disinfection had the highest qualified rate (χ²=1483.8, P<0.001). The qualified rate of water quality increased with the increase of the scale of water plant. Among the inspected indicators, the main unqualified indicators were chlorine dioxide (7.72%), fluoride (7.41%), free residual chlorine (3.90%), and total bacterial count (2.13%). Conclusion The passing rate of urban drinking water quality in Anhui Province is on an upward trend, and the quality of urban drinking water has improved. However, it is still important to pay attention to the problem of excessive microorganism and fluoride in water, and the quality of drinking water varies from place to place.

Objectives:To investigate the relationship between QRS duration and its changes during hospitalization and long-term all-cause mortality in patients with chronic heart failure.Methods:A total of 3 580 patients who attended three tertiary hospitals in Shanxi Province(First Hospital of Shanxi Medical University,Shanxi Cardiovascular Hospital,Shanxi Bethune Hospital)and were diagnosed with chronic heart failure from March 2014 to November 2021,were enrolled in this study.QRS duration at admission and discharge were collected,and the changes in QRS duration during hospitalization(ΔQRS)and the ΔQRS ratio(ΔQRS/admission QRS duration×100% )were calculated.Patients were divided into three group according to tertiles of ΔQRS:the group with decreasing QRS duration(n=1 364),the group with stable QRS duration(n=1 248),and the group with progressing QRS duration(n=968).Telephone follow-up was conducted at months 1,3,6,12,and every 6 months thereafter after discharge till May 1,2023,long-term all-cause mortality was the primary endpoint.Survival curves were plotted using the Kaplan-Meier method,and comparisons between groups were made using the log-rank method.Cox proportional risk regression model was used for prognostic analysis,and restricted cubic spline curves were calculated to evaluate QRS duration-related variables during hospitalization and the risk of long-term all-cause mortality in patients with chronic heart failure.Results:The median follow-up was 71(56,92)months,and all-cause mortality occurred in 502(14.0% )patients.Long-term all-cause mortality was lower in the group with decreasing QRS duration and the group with stable QRS duration compared with the progressing QRS duration group(13.9% vs.10.7% vs.18.6%,χ2=28.607,P<0.001).Multifactorial Cox regression analysis showed that admission QRS duration(HR=1.005,95% CI:1.002-1.009,P=0.003)and higher ΔQRS ratio during hospitalization(HR=2.071,95% CI:1.247-3.440,P=0.005)were independent influencing factors of long-term all-cause mortality in chronic heart failure patients.Restricted cubic spline curves showed that when the admission QRS duration was>96.36 ms,the longer the QRS duration,the higher the risk of all-cause mortality;when the admission QRS duration fluctuated from 89.32-96.36 ms,the QRS duration was a protective factor for long-term all-cause mortality in patients with chronic heart failure;and when the ΔQRS ratio during hospitalization was≥3.40%,higher ΔQRS ratio was linked with increased risk of all-cause mortality.Conclusions:QRS duration and ΔQRS ratio during hospitalization are independent predictors of long-term all-cause mortality in patients with chronic heart failure.Admission QRS duration>96.36 ms and ΔQRS ratio during hospitalization≥3.40% are associated with increased risk of long-term all-cause mortality in patients with chronic heart failure.

Objectives:To investigate the relationship between QRS duration and its changes during hospitalization and long-term all-cause mortality in patients with chronic heart failure.Methods:A total of 3 580 patients who attended three tertiary hospitals in Shanxi Province(First Hospital of Shanxi Medical University,Shanxi Cardiovascular Hospital,Shanxi Bethune Hospital)and were diagnosed with chronic heart failure from March 2014 to November 2021,were enrolled in this study.QRS duration at admission and discharge were collected,and the changes in QRS duration during hospitalization(ΔQRS)and the ΔQRS ratio(ΔQRS/admission QRS duration×100% )were calculated.Patients were divided into three group according to tertiles of ΔQRS:the group with decreasing QRS duration(n=1 364),the group with stable QRS duration(n=1 248),and the group with progressing QRS duration(n=968).Telephone follow-up was conducted at months 1,3,6,12,and every 6 months thereafter after discharge till May 1,2023,long-term all-cause mortality was the primary endpoint.Survival curves were plotted using the Kaplan-Meier method,and comparisons between groups were made using the log-rank method.Cox proportional risk regression model was used for prognostic analysis,and restricted cubic spline curves were calculated to evaluate QRS duration-related variables during hospitalization and the risk of long-term all-cause mortality in patients with chronic heart failure.Results:The median follow-up was 71(56,92)months,and all-cause mortality occurred in 502(14.0% )patients.Long-term all-cause mortality was lower in the group with decreasing QRS duration and the group with stable QRS duration compared with the progressing QRS duration group(13.9% vs.10.7% vs.18.6%,χ2=28.607,P<0.001).Multifactorial Cox regression analysis showed that admission QRS duration(HR=1.005,95% CI:1.002-1.009,P=0.003)and higher ΔQRS ratio during hospitalization(HR=2.071,95% CI:1.247-3.440,P=0.005)were independent influencing factors of long-term all-cause mortality in chronic heart failure patients.Restricted cubic spline curves showed that when the admission QRS duration was>96.36 ms,the longer the QRS duration,the higher the risk of all-cause mortality;when the admission QRS duration fluctuated from 89.32-96.36 ms,the QRS duration was a protective factor for long-term all-cause mortality in patients with chronic heart failure;and when the ΔQRS ratio during hospitalization was≥3.40%,higher ΔQRS ratio was linked with increased risk of all-cause mortality.Conclusions:QRS duration and ΔQRS ratio during hospitalization are independent predictors of long-term all-cause mortality in patients with chronic heart failure.Admission QRS duration>96.36 ms and ΔQRS ratio during hospitalization≥3.40% are associated with increased risk of long-term all-cause mortality in patients with chronic heart failure.

Objective To investigate the prevalence and risk factors of cognitive impairment in the nursing home population in Changning District, Shanghai. Methods In this study, random cluster sampling method was used to select 570 elderly people from 5 nursing homes in Changning District. Multivariate logistic regression was used to analyze the risk factors influencing cognitive function. Results The total prevalence of cognitive impairment in Changning nursing home population was 22.5%. The prevalence rates of ≤80 and >80 age groups were 16.8% and 23.9%, respectively, and the prevalence rates of men and women were 19.2% and 23.9%, respectively. Multivariate analysis showed that age ≥ 80 years old (OR=1.839, 95% CI: 1.045~3.235), no habit of reading book or newspaper (OR=2.087, 95%CI: 1.282~3.398), limitation of daily activity ability (OR=1.577, 95% CI: 1.023~2.431), and having depressive symptoms (OR=2.809, 95% CI: 1.840~4.288) were all influencing factors for cognitive impairment. Conclusion More than one fifth of elderly people in nursing homes in Changning District have symptoms of cognitive impairment. It is necessary to carry out routine cognitive assessment and appropriate cognitive intervention for the nursing home population to reduce the health and economic losses caused by cognitive impairment.

Objective To build a dataset encompassing a large number of stained tongue coating images and process it using deep learning to automatically recognize stained tongue coating images. Methods A total of 1 001 images of stained tongue coating from healthy students at Hunan University of Chinese Medicine and 1 007 images of pathological(non-stained)tongue coat-ing from hospitalized patients at The First Hospital of Hunan University of Chinese Medicine with lung cancer,diabetes,and hypertension were collected.The tongue images were randomi-zed into the training,validation,and testing datasets in a 7:2:1 ratio.A deep learning model was constructed using the ResNet50 for recognizing stained tongue coating in the training and validation datasets.The training period was 90 epochs.The model's performance was evaluated by its accuracy,loss curve,recall,F1 score,confusion matrix,receiver operating characteristic(ROC)curve,and precision-recall(PR)curve in the tasks of predicting stained tongue coating images in the testing dataset.The accuracy of the deep learning model was compared with that of attending physicians of traditional Chinese medicine(TCM). Results The training results showed that after 90 epochs,the model presented an excellent classification performance.The loss curve and accuracy were stable,showing no signs of overfitting.The model achieved an accuracy,recall,and F1 score of 92%,91%,and 92%,re-spectively.The confusion matrix revealed an accuracy of 92%for the model and 69%for TCM practitioners.The areas under the ROC and PR curves were 0.97 and 0.95,respectively. Conclusion The deep learning model constructed using ResNet50 can effectively recognize stained coating images with greater accuracy than visual inspection of TCM practitioners.This model has the potential to assist doctors in identifying false tongue coating and prevent-ing misdiagnosis.