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.

ObjectiveThe essence of syndrome manifestation recognition in traditional Chinese medicine (TCM) is to infer the body’s latent pathogenesis state from clinical observational information, rather than to perform simple label matching. However, previous studies have largely modeled this task as syndrome pattern classification within a fixed label space, which does not adequately reflect the cognition process of TCM syndrome differentiation centered on pathogenesis reasoning, and is also insufficient to capture the openness, semantic variability, and cross-disease reusability of syndrome manifestation expression. This study aimed to investigate whether introducing pathogenesis reasoning chain-of-thought (PR-CoT) supervision into large language models (LLMs) could improve the quality and cognitive consistency of syndrome manifestation recognition and support cross-disease transfer. MethodsSyndrome manifestation recognition was formulated as a conditional generation task under the framework of clinical observational information (X)→pathogenesis structure (Z)→syndrome pattern output (Y), where Z serves as an explicit intermediate structural variable linking the clinical evidence and syndrome judgment. Within this framework, a PR-CoT-supervised dataset for syndrome manifestation recognition was constructed based on medical case records of spleen-stomach disorders. After preprocessing, information extraction, manual proofreading, and data cleaning, the dataset comprised 4 800 training cases, 400 development cases, and 400 test cases. Each sample was annotated with a structured PR-CoT consisting of three progressive levels: clinical information summarization, comprehensive pathogenesis analysis, and syndrome pattern output. Supervised fine-tuning was conducted on open-source LLMs, with an end-to-end model serving as the baseline. Qwen3-32B was used as the primary experimental model, and Qwen3-14B as the scale comparison model. A progressive multidimensional evaluation framework was further established, comprising a structural parsing level, a semantic similarity level, and an expert blind review level. At the structural parsing level, syndrome pattern expressions were decomposed into structural elements and evaluated using Precision, Recall, F1 score, and Jaccard similarity. At the semantic similarity level, independent LLMs scored the theoretical proximity between predicted and reference syndrome patterns. At the expert blind review level, three TCM experts independently evaluated model outputs on two dimensions: syndrome differentiation consistency and terminology standardization of syndrome patterns. In addition, zero-shot cross-disease transfer evaluation was conducted on gynecological and heart-system disorder test sets. ResultsAt the structural parsing level, PR-CoT supervision did not lead to a stable improvement in the element-wise overlap of syndrome pattern structural components. Compared with the corresponding baselines, neither Qwen3-32B nor Qwen3-14B showed consistent advantages in structural matching metrics after the introduction of PR-CoT supervision. In contrast, at the semantic similarity level, PR-CoT supervision produced stable positive gains across different model scales and evaluation systems. The average semantic score of Qwen3-32B increased from 6.425 8 in the baseline model to 6.585 0 after PR-CoT supervision, and that of Qwen3-14B increased from 5.870 0 to 5.964 2. At the expert blind review level, the overall score of Qwen3-32B (PR-CoT) was 7.026 0±0.107 7, higher than 6.416 3±0.288 9 for its baseline. In zero-shot cross-disease testing, the PR-CoT model still showed advantages in semantic evaluation and expert evaluation on both gynecological and heart-system disorder test sets, indicating a certain degree of transferability. ConclusionThe benefits of PR-CoT supervision are mainly reflected in TCM semantic consistency and clinical plausibility, rather than in improved hard matching of structural elements. These findings support understanding syndrome manifestation recognition as a process of generating and expressing latent pathogenesis structures, rather than as a classification task within a traditional fixed label space. By introducing pathogenesis reasoning as an explicit intermediate structure into the modeling process and combining it with a progressive multidimensional evaluation framework, this study provides a methodological pathway for intelligent TCM syndrome differentiation that integrates theoretical alignment, interpretability, and multi-level evaluation.

ObjectiveThe essence of syndrome manifestation recognition in traditional Chinese medicine (TCM) is to infer the body’s latent pathogenesis state from clinical observational information, rather than to perform simple label matching. However, previous studies have largely modeled this task as syndrome pattern classification within a fixed label space, which does not adequately reflect the cognition process of TCM syndrome differentiation centered on pathogenesis reasoning, and is also insufficient to capture the openness, semantic variability, and cross-disease reusability of syndrome manifestation expression. This study aimed to investigate whether introducing pathogenesis reasoning chain-of-thought (PR-CoT) supervision into large language models (LLMs) could improve the quality and cognitive consistency of syndrome manifestation recognition and support cross-disease transfer. MethodsSyndrome manifestation recognition was formulated as a conditional generation task under the framework of clinical observational information (X)→pathogenesis structure (Z)→syndrome pattern output (Y), where Z serves as an explicit intermediate structural variable linking the clinical evidence and syndrome judgment. Within this framework, a PR-CoT-supervised dataset for syndrome manifestation recognition was constructed based on medical case records of spleen-stomach disorders. After preprocessing, information extraction, manual proofreading, and data cleaning, the dataset comprised 4 800 training cases, 400 development cases, and 400 test cases. Each sample was annotated with a structured PR-CoT consisting of three progressive levels: clinical information summarization, comprehensive pathogenesis analysis, and syndrome pattern output. Supervised fine-tuning was conducted on open-source LLMs, with an end-to-end model serving as the baseline. Qwen3-32B was used as the primary experimental model, and Qwen3-14B as the scale comparison model. A progressive multidimensional evaluation framework was further established, comprising a structural parsing level, a semantic similarity level, and an expert blind review level. At the structural parsing level, syndrome pattern expressions were decomposed into structural elements and evaluated using Precision, Recall, F1 score, and Jaccard similarity. At the semantic similarity level, independent LLMs scored the theoretical proximity between predicted and reference syndrome patterns. At the expert blind review level, three TCM experts independently evaluated model outputs on two dimensions: syndrome differentiation consistency and terminology standardization of syndrome patterns. In addition, zero-shot cross-disease transfer evaluation was conducted on gynecological and heart-system disorder test sets. ResultsAt the structural parsing level, PR-CoT supervision did not lead to a stable improvement in the element-wise overlap of syndrome pattern structural components. Compared with the corresponding baselines, neither Qwen3-32B nor Qwen3-14B showed consistent advantages in structural matching metrics after the introduction of PR-CoT supervision. In contrast, at the semantic similarity level, PR-CoT supervision produced stable positive gains across different model scales and evaluation systems. The average semantic score of Qwen3-32B increased from 6.425 8 in the baseline model to 6.585 0 after PR-CoT supervision, and that of Qwen3-14B increased from 5.870 0 to 5.964 2. At the expert blind review level, the overall score of Qwen3-32B (PR-CoT) was 7.026 0±0.107 7, higher than 6.416 3±0.288 9 for its baseline. In zero-shot cross-disease testing, the PR-CoT model still showed advantages in semantic evaluation and expert evaluation on both gynecological and heart-system disorder test sets, indicating a certain degree of transferability. ConclusionThe benefits of PR-CoT supervision are mainly reflected in TCM semantic consistency and clinical plausibility, rather than in improved hard matching of structural elements. These findings support understanding syndrome manifestation recognition as a process of generating and expressing latent pathogenesis structures, rather than as a classification task within a traditional fixed label space. By introducing pathogenesis reasoning as an explicit intermediate structure into the modeling process and combining it with a progressive multidimensional evaluation framework, this study provides a methodological pathway for intelligent TCM syndrome differentiation that integrates theoretical alignment, interpretability, and multi-level evaluation.

Objective To investigate the epidemiological characteristics and changing trend of typhus in Shaanxi Province from 2005 to 2023 to provide a scientific basis for its prevention and control. Methods Excel 2007, SPSS 25.0, Joinpoint 4.9.1.0, and Geoda 1.6 were used for data collection and statistical analysis. Super Map was used for data visualization to describe the changing characteristics of the disease. Results A total of 394 typhus cases were reported in Shaanxi Province from 2005 to 2023. The average annual incidence of typhus was 0.054/100 000, showing a dynamic fluctuation trend(AAPC=-3.3, t=-0.3, P>0.05). The cases were mainly concentrated in Baoji, Hanzhong and Xi′an, accounting for 78.68%. The incidence peak was from May to October, accounting for 64.21% of annual incidence. The epidemic season was from May to October and December. The incidence of the disease was concentrated in the 40-69 age group, accounting for 58.88%, and the sex was 1.07:1. The main occupation was farmers, accounting for 72.08%. The median time from onset to diagnosis was 7 days. Global spatial autocorrelation analysis showed that there were significant spatial autocorrelations in 11 years from 2005 to 2023(P<0.05). Local spatial autocorrelation analysis detected a total of 43“high-high”clustering areas, mainly concentrated in Baoji City. Conclusions The overall incidence of typhus in Shaanxi Province showed a dynamic fluctuation trend, with notable seasonal and regional aggregation. The incidence of typhus was higher in middle-aged and elderly people in rural areas. Surveillance should be strengthened in typhus endemic areas in summer and autumn, and health education should be conducted for key population to form good health habits and reduce the incidence of typhus.

Mild cognitive impairment due to Alzheimer′s disease is an inevitable pathological stage in the early development of Alzheimer′s disease, which can be classified as "microlumps in the brain collaterals" in traditional Chinese medicine. Based on the theory of latent toxin blocking collaterals, this article discusses the etiology and pathogenesis, clinical sequelae, and traditional Chinese medicine intervention strategies for mild cognitive impairment due to Alzheimer′s disease. The onset of mild cognitive impairment due to Alzheimer′s disease is very similar to the latent pathogen theory, which states that "the latent pathogen is latent and then develops, the poison is deep and difficult to cure, and the development can be recognized but the latent pathogen cannot be detected." Combining clinical experience, our team believes that the basic nature of the disease is a slight deficiency and a slight excess of symptoms. A slight deficiency of the five zang viscera and six fu viscera as root and a latent toxin colling collaterals of qi, fire, phlegm, and blood stasis as manifestaion. These usually start from the qi depression and develop into phlegm coagulation and blood stasis, then end up in latent toxin and gradually become the healthy qi deficiency. Therefore, the deficiency of vital qi and incubation of evil, latent toxin blocking collaterals the pathogenesis of early intervention of this disease should be carried out, upholding the idea that "the upper workman treats the disease before it is diagnosed." The principle of strengthening vital qi to eliminate pathogenic factors, slowing down and promoting pathogenic factors elimination, establishing the method of supporting correctness and wisdom, simultaneously detoxifying and clearing the blood stasis, pattern differentiation as the main and the disease differentiation as the first, combining the disease and pattern, and adjusting the macroscopic and microscopic, focusing simultaneously on eliminating and replenishing, dispel phlegm and remove blood stasis, achieve a strong vital qi and the elimination of evil, and enhance intelligence, delay or even block the progression of mild cognitive impairment due to Alzheimer′s disease, improve patients′ quality of life, and provide a theoretical basis for the early clinical prevention and treatment of Alzheimer′s disease.

The innate immune system serves as the body’s first line of defense against pathogens and plays a central role in inflammation regulation, immune homeostasis, and tumor immunosurveillance. In recent years, with the growing recognition of the concept “exercise is medicine”, increasing attention has been paid to the immunoregulatory effects of physical activity. Accumulating evidence suggests that regular, moderate-intensity exercise significantly enhances innate immunity by strengthening the skin-mucosal barrier, increasing levels of secretory immunoglobulin A (sIgA), and improving the functional capacity of key immune cells such as natural killer (NK) cells, neutrophils, macrophages, and dendritic cells. It also modulates the complement system and various inflammatory mediators. This review comprehensively summarizes the effects of exercise on each component of the innate immune system and highlights the underlying molecular mechanisms, including activation of AMP-activated protein kinase (AMPK), inhibition of nuclear factor-kappa B (NF-κB), enhancement of mitochondrial function via the PGC-1α/TFAM axis, and initiation of autophagy through the ULK1/mTOR pathway. Emerging mechanisms are also discussed, such as exercise-induced epigenetic modifications (e.g., histone acetylation and miRNA regulation), modulation of the gut microbiota, and metabolite-mediated immune programming (e.g., short-chain fatty acids (SCFAs), β‑hydroxybutyrate). The effects of exercise on innate immunity vary considerably among individuals, depending on factors such as age, sex, and comorbidities. For example, adolescents exhibit enhanced NK cell mobilization, whereas older adults benefit from reduced chronic inflammation and immune aging. Sex hormones and metabolic conditions (e.g., obesity, diabetes, chronic obstructive pulmonary disease, cancer) further modulate the immune response to exercise. Based on these insights, we propose a personalized approach to exercise prescription guided by the FITT (frequency, intensity, time, and type) principle, aiming to optimize immune outcomes across diverse populations. Importantly, given the dual role of exercise in immune activation and regulation, caution is warranted: while moderate exercise enhances immune defense, excessive or high-intensity activity may induce transient immunosuppression. In pathological contexts such as infection, autoimmune diseases, or tissue injury, exercise intensity and timing must be carefully adjusted. This review provides practical guidelines for exercise-based immune modulation and underscores the need for dose-response studies and advancements in precision exercise medicine. In conclusion, exercise represents a safe and effective strategy for enhancing innate immune function and mitigating chronic inflammatory diseases.

Metabolic-associated fatty liver disease (MAFLD) and osteoporosis (OP) are two very common metabolic diseases. A growing body of experimental evidence supports a pathophysiological link between MAFLD and OP. MAFLD is often associated with the development of OP. Rutaecarpine (RUT) is one of the main active components of Chinese medicine Euodiae Fructus. Our previous studies have demonstrated that RUT has lipid-lowering, anti-inflammatory and anti-atherosclerotic effects, and can improve the OP of rats. However, whether RUT can improve both fatty liver and OP symptoms of MAFLD mice at the same time remains to be investigated. In this study, we used C57BL/6 mice fed a high-fat diet (HFD) for 4 months to construct a MAFLD model, and gave the mice a low dose (5 mg·kg^-1) and a high dose (15 mg·kg^-1) of RUT by gavage for 4 weeks. The effects of RUT on liver steatosis and bone metabolism were then evaluated at the end of the experiment [this experiment was approved by the Experimental Animal Ethics Committee of Institute of Medicinal Biotechnology, Chinese Academy of Medical Sciences (approval number: IMB-20190124D₃03)]. The results showed that RUT treatment significantly reduced hepatic steatosis and lipid accumulation, and significantly reduced bone loss and promoted bone formation. In summary, this study shows that RUT has an effect of improving fatty liver and OP in MAFLD mice.

OBJECTIVE: To explore the accuracy of human-computer interaction software in identifying and locating type C1 distal radius fractures. METHODS: Based on relevant inclusion and exclusion criteria, 14 cases of type C1 distal radius fractures between September 2023 and March 2024 were retrospectively analyzed, comprising 3 males and 11 females(aged from 27 to 82 years). The data were assigned randomized identifiers. A senior orthopedic physician reviewed the films and measured the ulnar deviation angle, radial height, palmar inclination angle, intra-articular step, and intra-articular gap for each case on the hospital's imaging system. Based on the reduction standard for distal radius fractures, cases were divided into reduction group and non-reduction group. Then, the data were sequentially imported into a human-computer interaction intelligent software, where a junior orthopedic physician analyzed the same radiological parameters, categorized cases, and measured fracture details. The categorization results from the software were consistent with manual classifications (6 reduction cases and 8 non-reduction cases). For non-reduction cases, the software performed further analyses, including bone segmentation and fracture recognition, generating 8 diagnostic reports containing fracture recognition information. For the 6 reduction cases, the senior and junior orthopedic physicians independently analyzed the data on the hospital's imaging system and the AI software, respectively. Bone segments requiring reduction were identified, verified by two senior physicians, and measured for displacement and rotation along the X (inward and outward), Z (front and back), and Y (up and down) axes. The AI software generated comprehensive diagnostic reports for these cases, which included all measurements and fracture recognition details. RESULTS: Both the manual and AI software methods consistently categorized the 14 cases into 6 reduction and 8 non-reduction groups, with identical data distributions. A paired sample t-test revealed no statistically significant differences (P>0.05) between the manual and software-based measurements for ulnar deviation angle, radial ulnar bone height, palmar inclination angle, intra-articular step, and joint space. In fracture recognition, the AI software correctly identified 10 C-type fractures and 4 B-type fractures. For the 6 reduction cases, a total of 24 bone fragments were analyzed across both methods. After verification, it was found that the bone fragments identified by the two methods were consistent. A paired sample t-tests revealed that the identified bone fragments and measured displacement and rotation angles along the X, Y, and Z axes were consistent between the two methods. No statistically significant differences(P>0.05) were found between manual and software measurements for these parameters. CONCLUSION Human-computer interaction software employing AI technology demonstrated comparable accuracy to manual measurement in identifying and locating type C1 distal radius fractures on CT imaging.
Humans ; Male ; Female ; Radius Fractures/surgery* ; Middle Aged ; Adult ; Aged ; Aged, 80 and over ; Tomography, X-Ray Computed/methods* ; Retrospective Studies ; Software ; Wrist Fractures

OpenSim is an open source, free motion simulation and gait analysis software, which can be used to dynamically simulate and analyze the complex motion of the human body, and is widely used in human biomechanical research. Since OpenSim can analyze multi-dimensional motion data such as muscle strength, joint torque, and muscle synergistic activation during human movement, it can be used to study the biomechanical mechanism of musculoskeletal imbalance diseases and various treatment methods in TCM orthopedics, and has a broad application prospect in the field of TCM orthopedics. By the analysis of the basic characteristics, elements, analysis process, and application prospects of OpenSim, it is concluded that OpenSim musculoskeletal model has a large application space in the field of traditional Chinese medicine orthopedic, which is helpful to explain the pathogenesis and mechanism of diseases, and promote the precision diagnosis and treatment of orthopedics diseases;the application of OpenSim musculoskeletal model can solve the problem that the previous research paid attention to the bone malalignment and not enough attention to the tendon, and provide a new method for the research of orthopedic diseases. At present, there are still problems in the promotion and application of OpenSim, such as large equipment requirements and high operation threshold. Therefore, multidisciplinary cooperation, clinical research, and data sharing are the basic research strategies in this field.
Humans ; Biomechanical Phenomena ; Orthopedics ; Traumatology ; Software ; Medicine, Chinese Traditional ; Musculoskeletal System ; Models, Biological