Objective: To address the dual challenges of long-tail distribution and feature sparsity in traditional Chinese medicine (TCM) syndrome differentiation within real clinical settings, we propose a data-efficient learning framework enhanced by knowledge graphs. Methods: We developed Agent-GNN, a three-stage decoupled learning framework, and validated it on the Traditional Chinese Medicine Syndrome Diagnosis (TCM-SD) dataset containing 54 152 clinical records across 148 syndrome categories. First, we constructed a comprehensive medical knowledge graph encoding the complete TCM reasoning system. Second, we proposed a Functional Patient Profiling (FPP) method that utilizes large language models (LLMs) combined with Graph Retrieval-Augmented Generation (RAG) to extract structured symptom-etiology-pathogenesis subgraphs from medical records. Third, we employed heterogeneous graph neural networks to learn structured combination patterns explicitly. We compared our method against multiple baselines including BERT, ZY-BERT, ZY-BERT + Know, GAT, and GPT-4 Few-shot, using macro-F1 score as the primary evaluation metric. Additionally, ablation experiments were conducted to validate the contribution of each key component to model performance. Results: Agent-GNN achieved an overall macro-F1 score of 72.4%, representing an 8.7 percentage points improvement over ZY-BERT + Know (63.7%), the strongest baseline among traditional methods. For long-tail syndromes with fewer than 10 samples, Agent-GNN reached a macro-F1 score of 58.6%, compared with 39.3% for ZY-BERT + Know and 41.2% for GPT-4 Few-shot, representing relative improvements of 49.2% and 42.2%, respectively. Ablation experiments confirmed that the explicit modeling of etiology-pathogenesis nodes contributed 12.4 percentage points to this enhanced long-tail syndrome performance. Conclusion This study proposes Agent-GNN, a knowledge graph-enhanced framework that effectively addresses the long-tail distribution challenge in TCM syndrome differentiation. By explicitly modeling manifestation-mechanism-essence patterns through structured knowledge graphs, our approach achieves superior performance in data-scarce scenarios while providing interpretable reasoning paths for TCM intelligent diagnosis.

ObjectiveThe widespread adoption of portable fundus cameras for primary care and community screening is hindered by limitations in current autofocus(AF) technologies. Image-based methods relying on sharpness evaluation require iterative searches, resulting in slow convergence, while projection-based techniques are susceptible to optical artifacts and calibration errors. To address these challenges, this study introduces a novel AF system based on direct wavefront sensing, designed to deliver simultaneous high speed, high precision, and operational robustness within the compact form factor essential for portable ophthalmic devices. MethodsOur approach fundamentally reimagines the AF process by directly measuring the ocular wavefront aberration. We developed a custom portable fundus camera integrating a miniaturized Shack-Hartmann wavefront sensor (SHWS) into the optical path. An 850 nm laser diode projects a point source onto the retina via oblique illumination to minimize corneal reflections. Light scattered from this spot carries the eye’s refractive error through the imaging optics and is directed to the SHWS, positioned at a plane optically conjugate to the primary color CMOS imaging sensor. A microlens array within the SHWS samples the incident wavefront, generating a pattern of focal spots on a CCD. Real-time centroid analysis of these spots provides a map of local wavefront slopes. These measurements are processed through a singular value decomposition (SVD) algorithm to fit a Zernike polynomial basis set, enabling real-time reconstruction of the wavefront phase. The defocus component (S) is extracted from the second-order Zernike coefficients, providing a direct, quantitative measure of the refractive error in diopters. This value serves as a precise error signal in a closed-loop control system, which commands a voice-coil actuated focusing lens to its null position in a single, deterministic step, eliminating the need for iterative search algorithms. ResultsComprehensive evaluation demonstrated the system’s high performance. Testing on a calibrated model eye (OEMI-7) established a highly linear relationship between the computed defocus S and the focusing lens position across a ±20 Diopter (D) compensation range, achievable within a 5 mm mechanical travel. The system achieved a focusing precision of 0.08 D, corresponding to an 18-fold improvement over a conventional projection spot-size method tested under identical conditions. The total focus acquisition time, encompassing wavefront measurement, computation, and lens actuation, averaged under 0.5 s. Clinical validation with 25 human volunteers (50 eyes, refractive range -15 D to +10 D) confirmed practical efficacy. The wavefront-sensing AF succeeded in 92% of attempts with a mean time of 0.5 s, substantially outperforming a projection-based benchmark which achieved only a 32% success rate with an average time of 4.25 s. The system provided instantaneous directional guidance and maintained stability during minor ocular movements. Objective assessment of image quality, via amplitude contrast of retinal vasculature, showed consistent and significant enhancement following AF correction across the entire tested diopter range. ConclusionThis work successfully implements and validates a direct wavefront-sensing autofocus paradigm for portable fundus cameras. By directly quantifying and compensating for the optical defocus aberration, this method bypasses the fundamental limitations of image-processing and projection-based techniques, enabling rapid, precise, and deterministic diopter compensation. The developed system delivers an exceptional combination of a wide operational range (±20 D), high accuracy (0.08 D), fast convergence (0.5 s), and a compact physical footprint. This technology provides a practical and high-performance focusing solution capable of enhancing the reliability, throughput, and diagnostic utility of portable retinal imaging in large-scale screening applications. Future efforts will be directed towards system cost optimization and performance adaptation for diverse ocular conditions.

Objective: To analyze the epidemiological characteristics of varicella among nursery children in Shenzhen from 2015 to 2024, and to evaluate the impact of optimizing varicella vaccine (VarV) immunization strategies on varicella incidence. Methods: Varicella incidence data for nursery children in Shenzhen from 2015 to 2024 were obtained from the China Disease Prevention and Control Information System. The study period was divided into three phases:one dose self pay VarV (January 2015 to October 2017), two dose self pay VarV (November 2017 to October 2019), and two dose free VarV (November 2019 to December 2024). Interrupted time series (ITS) analysis was conducted to assess changes in the level and trend of varicella incidence associated with each phase of policy implementation. Results: A total of 27 517 varicella cases was reported among nursery children from 2015 to 2024, with an average annual incidence of 514.01/100 000. During the same period, 136 clustered outbreaks were reported in nursery institutions, involving a cumulative total of 1 091 cases. ITS analysis showed that during the self pay 1 dose stage, the varicella incidence among nursery children showed an upward trend, with an average monthly increase of 2.58/100 000 (95% CI =2.21/ 100 000 -2.95/100 000, P <0.01). After the implementation of the self pay 2 dose strategy, the incidence decreased, with a change in incidence of -26.12/100 000 (95% CI =-37.30/100 000 to -14.94/100 000) and a change in slope of -2.65/100 000 (95% CI = -3.38/100 000 to -1.93/100 000)(all P <0.01). After the implementation of the free 2 dose strategy, the incidence decreased further, with a change in incidence of -40.03/100 000 (95% CI =-50.39/100 000 to -29.66/100 000, P <0.01) and a change in slope of -0.56/100 000 (95% CI =-1.20/100 000-0.08/100 000, P =0.09). Conclusion The gradual optimization of the VarV vaccination strategy in Shenzhen from self pay 1 dose to free 2 dose has significantly reduced the varicella incidence among nursery children, demonstrating good short term control and long term intervention effectiveness.

Objective:To analyze the influence factors of urinary tract infection after transurethral bipolar plasma enucleation of the prostate (TUPEP) in patients with benign prostatic hyperplasia(BPH), and the early predictive value of serum inflammatory indicators for postoperative urinary tract infection.Methods:A total of 300 patients with BPH who received TUPEP treatment in the Department of Urology, Kailuan General Hospital from January 2021 to August 2023 were selected, according to whether they had urinary tract infections after the operation, they were divided into infection group ( n=117) and non-infection group ( n=183). The clinical data of the two groups were collected, and the serum inflammatory indexes of the two groups were recorded within 24 hours after the operation, including white blood cell count (WBC), neutrophil granulocyte (NE%), high-sensitivity C-reactive protein (hs-CRP), serum amyloid A (SAA), procalcitonin (PCT), heparin-binding protein (HBP), interleukin-2 (IL-2), interleukin-4 (IL-4), interleukin-6 (IL-6), interleukin-8 (IL-8), interleukin-10 (IL-10), tumor necrosis factor-α (TNF-α), interferon-γ (IFN-γ), and serum ferritin (SF). The differences of clinical data and serum inflammatory indexes between the two groups were analyzed. The measurement data of normal distribution were expressed as mean ± standard deviation ( ± s), and independent sample t-test was used for inter-group comparisons. The measurement data of non- normal distribution were represented by median (interquartile range) [ M ( Q1, Q3)], and the Mann-Whitney U test was used for inter-group comparison. The count data were expressed as cases and percentage, and inter-group comparisons were conducted using the Chi-test. Multivariate Logistic regression analysis was used to explored the influencing factors of urinary tract infections in BPH patients after TUPEP surgery. The receiver operating characteristic (ROC) curve was plotted using GraphPad Prism 8.0.1 medical plotting softwar to evaluate the predictive value of serum inflammatory markers and combined detection of multiple markers for early postoperative urinary tract infections. Results:The duration of disease, history of diabetes, international prostate symptom score (IPSS), prostate volume, preoperative serum prostate-specific antigen (PSA) level, preoperative urine residual volume, operation time, intraoperative blood loss, postoperative catheter indwelling time, and hospitalization time in the infection group were higher than those in the non-infection group ( P<0.05). The preoperative 25-hydroxyvitamin D (25OHD) level and maximum urinary flow rate were lower in the infection group than those in the non- infection group ( P<0.05). Multivariate Logistic regression analysis showed that the course of the disease, history of diabetes, IPSS score, prostate volume, preoperative PSA level, preoperative urine residual volume, operation time, intraoperative blood loss, postoperative catheter indwelling time was positively correlated with urinary tract infection after TUPEP ( B=0.660, 0.242, 0.164, 0.125, 0.230, 0.066, 0.382, 0.022, 0.436, P<0.01), and preoperative 25OHD level and preoperative maximum urinary flow rate were negatively correlated with urinary tract infection after TUPEP ( B=-0.216, -0.372, P<0.01). The levels of hs-CRP, SAA, PCT, HBP, IL-2, IL-4, IL-6, IL-8, IL-10, TNF-α, IFN-γ, SF in the infection group were higher than those in the non-infection group ( P<0.001). The ROC curve analysis showed that the area under the curve (AUC) of hs-CRP, SAA, PCT, HBP, IL-2, IL-4, IL-6, IL-8, IL-10, TNF-α, IFN-γ, SF in early predicting urinary tract infection after TUPEP in BPH patients were 0.697, 0.775, 0.902, 0.873, 0.884, 0.904, 0.917, 0.823, 0.906, 0.852, 0.807, 0.787. The AUC of the combined detection of multiple serum inflammatory markers was 0.972, the sensitivity and specificity were 93.18% and 96.63%, and the sensitivity and specificity of the combined detection of multiple serum inflammatory markers were higher than those of separate detection. Conclusion:The course of BPH, whether to combine history of diabetes, preoperative IPSS score, prostate volume, preoperative PSA level, preoperative 25OHD level, preoperative maximum urinary flow rate, operation time, intraoperative blood loss, and postoperative catheter indwelling time are influencing factors of urinary tract infection after TUPEP, hs-CRP, SAA, PCT, HBP, IL-2, IL-4, IL-6, IL-8, IL-10, TNF-α, IFN-γ, SF had certain value in the early prediction of urinary tract infection after TUPEP in patients with BPH, the combination of multiple indicators can improve the predictive value of early urinary tract infection.

Objective To develop a predictive model for postoperative mortality risk in patients with acute aortic dissection(AAD)using the Extreme Gradient Boosting(XGBoost)algorithm combined with Shapley Additive Explanation(SHAP),and to establish a prediction website to serve as a diagnostic and therapeutic support platform for clinicians and patients.Methods A retrospective cohort study design was adopted.Data from 782 AAD patients who underwent surgical treatment at the Fourth Hospital of Hebei Medical University from January 2013 to December 2023 were collected,including basic information and initial serum biomarker test results.Patients were randomly divided into training and test sets at a 7:3 ratio.An external validation set consisting of 313 AAD patients admitted to the Second Hospital of Hebei Medical University from January 2020 to December 2023 was also established for further model validation.Variables were screened using LASSO regression,and an XGBoost machine learning model was constructed and interpreted using SHAP.The predictive performance of the model was evaluated using receiver operating characteristic(ROC)curve analysis.Using the Shiny package,the XGBoost model was deployed to shinyapps.io to create a prediction website for postoperative mortality risk in AAD patients.One patient was selected by simple random sampling from the test set and the external validation set respectively for the prediction example on the Shiny webpage.Results The XGBoost model demonstrated high predictive performance for postoperative mortality in AAD patients,with area under the ROC curve(AUC)values of 0.928(95%CI 0.901-0.956)in the training set,0.919(95%CI 0.891-0.949)in the test set,and 0.941(95%CI 0.915-0.967)in the external validation set.SHAP values indicated the following order of variable importance in the model(from highest to lowest):"lactate dehydrogenase""blood chlorine""multiple organ injury""carbon dioxide combining power""prothrombin time""α-hydroxybutyric acid""creatine kinase isoenzyme""Stanford classification""combined use of bedside blood purification""gender""acute kidney injury""gastrointestinal bleeding""brain injury"and"shock".A risk prediction website for adverse postoperative outcomes in AAD patients was developed using XGBoost-SHAP method(https://dun-dunxiaolu.shinyapps.io/document/)and validated with examples.One randomly selected patient from each of the test and external validation sets was applied:the predicted mortality risk value for patient 1(who died postoperatively)was 0.9539,and that for patient 2(who survived postoperatively)was 0.0206.Conclusions The XGBoost-SHAP model demonstrates high accuracy in predicting postoperative mortality risk for AAD patients.The online prediction tool established based on this model enhances the identification efficiency of high-risk postoperative mortality patients.

Objective To investigate the effect of Gd-hydroxyapatite(Gd-HA)stents with adipose mesenchymal cells(ADSCs)on the repair of knee articular cartilage defects.Methods To isolate,culture,and identify rabbit ADSCs by establishing a rabbit knee joint full-thickness cartilage defect model,a total of 18 rabbits were randomly divided into blank control group,Gd-HA scaffold group,and ADSCs+Gd-HA scaffold group.At week 12 and 24 after surgery,International Curtilage Repair Society(ICRS)score,HE,toluidine blue,modified red O bright green and ColⅡ were detected by immunohistochemical staining,then ColⅡand GAG mRNA expression levels were detected by O'Driscoll and Real-time PCR.ColⅡ protein expression was detected by Western blotting,GAG content was detected by DMMB,biomechanical strength was detected by indentation test,and PKH26 labeled ADSCs was used to trace the tissue engineering scaffold with Gd-HA composite ADSCs to evaluate the repair effect of rabbit knee cartilage defects.Results The ADSCs isolated and cultured in vitro showed good growth,stable phenotype and good directional differentiation through macroscopic observation and histological staining,it could be seen that the repair degree and effect of the knee joint full-thickness cartilage defect model implanted with Gd-HA scaffold group were better than those of the blank control group,while the cartilage repair situation of the ADSCs+Gd-HA scaffold group was better than that of the Gd-HA scaffold group(P＜0.05);The ICRS and improved O'Driscoll scores were higher than the other two groups(P＜0.05).Compared with the Gd-HA group,the ADSCs+Gd-HA group could produce ColⅡ and GAG during the process of cartilage repair,with stronger mechanical strength of the repaired tissue(P＜0.05);PKH26 labeled ADSCs were found in the repaired tissues of the ADSCs+Gd-HA group,and they were involved in the composition of newly formed tissues.Conclusion Gd-HA scaffold material combined with ADSCs has a good repair effect on full-thickness cartilage defects in the knee joint as a new type of biological material for repairing joint cartilage defects.

Objective:To understand the current situation of the ability to screen health information of the elderly in rural areas and analyze its influencing factors, so as to provide a basis for taking targeted measures.Methods:A cross-sectional survey was adopted, and rural elderly people in Yonghe Town, Dahu Town and Dayao Town of Liuyang City, Hunan Province were selected as the survey subjects by the convenience sampling method. The investigation was conducted using the general information Questionnaire, the Health Information Discrimination Ability Scale, the filial Piety Expectation Scale and the two-way Social Support Scale.Results:A total of 228 questionnaires were distributed, and 215 valid questionnaires were retrieved, with an effective recovery rate of 94.30%. Among the 215 rural elderly people surveyed, 86 were male and 129 were female. The ability to discriminate health information was (69.19 ± 13.41) points, the expectation of filial piety was (37.67 ± 6.12) points, and the two-way social support was (46.82 ± 8.11) points. The ability of rural elderly people to discriminate health information was positively correlated with filial piety expectations and two-way social support ( r = 0.340, 0.456; both P<0.01). The results of hierarchical regression analysis showed that educational level, filial piety expectations and two-way social support were the influencing factors of the current status of health information discrimination ability of rural elderly people ( t values were 2.60 to 5.35, all P<0.05). Conclusions:The ability of discriminating health information of the elderly in rural areas is affected by the educational level, filial piety expectation and two-way social support. The health information of rural elderly people with low education level should be screened and targeted, so as to enrich their cultural life and combine education with fun. Actively build a filial piety culture to promote children′s attention to their parents. In addition to providing social support for the elderly, we should promote their interpersonal and social communication and exert their self-value, so as to improve the health information screening ability of the elderly in rural areas.

With the extended survival period of breast cancer patients and the increasing health demands, the concomitant diseases of breast cancer have gradually attracted the attention of both doctors and patients, and it is imperative to conduct comprehensive management of these diseases, in which the general practitioners, as the more comprehensive and complex medical talents, have not yet played their due roles. In this article, we report two cases of comprehensive management of concomitant diseases of breast cancer through collaboration of general practitioners and specialists (integrated general and specialist care). The role and function of general practitioners in this process were deeply analyzed, and the establishment of a consultation-liaison general practice model to further promote the role of integrated general and specialist care in integrated oncology care was advocated.

Objective:To observe the clinical efficacy of traditional Chinese medicine(TCM)essential oil Tuina(Chinese therapeutic massage)combined with conventional Western medication in treating hypertension and its influence on TCM symptoms and anxiety.Methods:Eighty patients with hypertension were included and divided into an observation group and a control group using the random number table method,with 40 cases in each group.The control group was treated with conventional oral Western medication once a day.The observation group was treated with additional TCM essential oil Tuina once every other day.The two groups were treated for 4 weeks.The changes in blood pressure,TCM symptom score,and anxiety,as well as safety,were observed after treatment.Results:After treatment,the systolic blood pressure,diastolic blood pressure,TCM symptom score,and Hamilton anxiety scale score in the two groups were lower than those before treatment(P<0.05),and those of the observation group were lower compared to the control group with statistically significant differences(P<0.05).There were no adverse reactions,such as allergy and dry cough,in the two groups.Conclusion:Based on conventional Western medication,TCM essential oil Tuina was safe and effective in the treatment of hypertension,which both reduced blood pressure and improved clinical symptoms and anxiety.

OBJECTIVE To analyze the blood components of Suanzaoren Decoction after oral administration using UHPLC-Q Exactive Orbitrap-MS technology.METHODS Female Sprague-Dawley(SD)rats were used as experimental subjects,and Suanza-oren Decoction was administered orally.Serum samples were collected,and the aqueous extract of Suanzaoren Decoction and the serum were analyzed using UHPLC-Q Exactive Orbitrap-MS technology to identify the prototype components and metabolites absorbed into the blood by comparing and analyzing with the LuMet-TCM database.RESULTS It showed that a total of 458 components were iden-tified in the aqueous extract of Suanzaoren Decoction,and 26 chemical components were identified in the blood,including 23 prototype components and 3 metabolites.CONCLUSION The prototype components absorbed into the blood discovered in this study may be the active ingredients of Suanzaoren Decoction,providing a reference for the research on the pharmacodynamic material basis of Suanza-oren Decoction.