Objective: To develop a depression recognition model by integrating the spirit-expression diagnostic framework of traditional Chinese medicine (TCM) with machine learning algorithms. The proposed model seeks to establish a TCM-informed tool for early depression screening, thereby bridging traditional diagnostic principles with modern computational approaches. Methods: The study included patients with depression who visited the Shanghai Pudong New Area Mental Health Center from October 1, 2022 to October 1, 2023, as well as students and teachers from Shanghai University of Traditional Chinese Medicine during the same period as the healthy control group. Videos of 3 – 10 s were captured using a Xiaomi Pad 5, and the TCM spirit and expressions were determined by TCM experts (at least 3 out of 5 experts agreed to determine the category of TCM spirit and expressions). Basic information, facial images, and interview information were collected through a portable TCM intelligent analysis and diagnosis device, and facial diagnosis features were extracted using the Open CV computer vision library technology. Statistical analysis methods such as parametric and non-parametric tests were used to analyze the baseline data, TCM spirit and expression features, and facial diagnosis feature parameters of the two groups, to compare the differences in TCM spirit and expression and facial features. Five machine learning algorithms, including extreme gradient boosting (XGBoost), decision tree (DT), Bernoulli naive Bayes (BernoulliNB), support vector machine (SVM), and k-nearest neighbor (KNN) classification, were used to construct a depression recognition model based on the fusion of TCM spirit and expression features. The performance of the model was evaluated using metrics such as accuracy, precision, and the area under the receiver operating characteristic (ROC) curve (AUC). The model results were explained using the Shapley Additive exPlanations (SHAP). Results: A total of 93 depression patients and 87 healthy individuals were ultimately included in this study. There was no statistically significant difference in the baseline characteristics between the two groups (P > 0.05). The differences in the characteristics of the spirit and expressions in TCM and facial features between the two groups were shown as follows. (i) Quantispirit facial analysis revealed that depression patients exhibited significantly reduced facial spirit and luminance compared with healthy controls (P < 0.05), with characteristic features such as sad expressions, facial erythema, and changes in the lip color ranging from erythematous to cyanotic. (ii) Depressed patients exhibited significantly lower values in facial complexion L, lip L, and a values, and gloss index, but higher values in facial complexion a and b, lip b, low gloss index, and matte index (all P < 0.05). (iii) The results of multiple models show that the XGBoost-based depression recognition model, integrating the TCM “spirit-expression” diagnostic framework, achieved an accuracy of 98.61% and significantly outperformed four benchmark algorithms—DT, BernoulliNB, SVM, and KNN (P < 0.01). (iv) The SHAP visualization results show that in the recognition model constructed by the XGBoost algorithm, the complexion b value, categories of facial spirit, high gloss index, low gloss index, categories of facial expression and texture features have significant contribution to the model. Conclusion This study demonstrates that integrating TCM spirit-expression diagnostic features with machine learning enables the construction of a high-precision depression detection model, offering a novel paradigm for objective depression diagnosis.

Objective To explore the effects of home-based exercise rehabilitation on cardiac structure, valvular function, and exercise capacity in patients with severe aortic stenosis (AS) after transcatheter aortic valve replacement (TAVR). Methods 49 patients with severe AS who underwent TAVR at Zhongshan Hospital, Fudan University, from January 2024 to February 2025 were enrolled. They were divided into an exercise group (n＝25) or a non-exercise group (n＝24) based on participating or not in home-based rehabilitation after TAVR. The exercise group received 12 weeks of home-based exercise training (aerobic exercise plus resistance training every week); the non-exercise group received routine care. Transthoracic echocardiography (TTE) was used to assess cardiac structural parameters before discharge (T0) and after 12 weeks of exercise (T1). Functional outcomes including the 6-minute walk test (6MWT), Duke Activity Status Index (DASI), and Short Physical Performance Battery (SPPB) were compared between the two groups. A linear mixed-effects model was used to analyze the effect of home-based rehabilitation on echocardiographic parameters. Patients were stratified by baseline 6MWT (＜240 m as low-function subgroup, ≥240 m as high-function subgroup) to compare exercise-related outcomes between subgroups. Results At T1, the exercise group had a longer 6MWT distance than the non-exercise group (P＝0.012). The linear mixed-effects model showed that after 12 weeks of exercise, the left ventricular end-diastolic diameter (LVEDD) decreased in the exercise group but slightly increased in the non-exercise group, with a significant difference in changes over time between the two groups (P_interaction＝0.030). The exercise group also showed greater improvement in effective orifice area index (P_interaction＝0.028) and effective orifice area (P_interaction＝0.042) than the non-exercise group. Subgroup analysis revealed that in the low-function subgroup, the exercise group showed greater improvement in the 6MWT (P_interaction＝0.035) and the effective orifice area index (P_interaction＝0.046) compared to the non-exercise group; in the high-function subgroup, the exercise group showed greater improvement only in LVEDD compared to the non-exercise group (P_interaction＝0.046). Conclusions Home-based exercise rehabilitation improves exercise capacity, optimizes left ventricular remodeling, and enhances valvular function in patients with severe AS after TAVR, with greater benefits observed in patients with lower baseline 6MWT.

Objective To explore the compatibility and combination patterns of traditional Chinese medicine(TCM)formulas in treating kidney deficiency and blood stasis type osteoporosis,to identify the most frequently used drug pairs,and to explore their mechanisms of action in treating kidney deficiency and blood stasis type osteoporosis through network pharmacology and molecular docking,providing theoretical guidance for clinical medication.Methods Formulas used for treating kidney deficiency and blood stasis type osteopo-rosis in the past 10 years were screened from databases such as CNKI and Wanfang.SPSS,Origin,and IBM SPSS Modeler software were used for frequency,taste and meridian statistics,and drug combination analysis.Cluster analysis was applied to identify the core drug combinations.The best drug pair for treating kidney de-ficiency and blood stasis type osteoporosis was selected.Network pharmacology analysis was conducted on this drug pair to identify core targets,main components,and signaling pathways.Molecular docking was performed using AutoDockTools,AutoDock Vina,and PyMOL software to further verify the possibility of their interac-tions.Results A total of 117 formulas containing 148 TCMs were screened out.The frequently used drugs and combinations were mainly kidney-yang and kidney-yin tonics and blood-activating and stasis-eliminating drugs,with sweet and warm tastes,mostly attributed to the liver and kidney meridians.Further cluster analy-sis of drugs with a frequency greater than 20 yielded five categories.The Epimedium-Bupleurum combination was selected for network pharmacology analysis,which identified 89 targets.Core targets included STAT3,IL-6,and JUN.Main components were cryptotanshinone,kaempferol,luteolin,and quercetin.Molecular docking was performed on the main components and core targets to verify the treatment effect of the drugs on osteopo-rosis.Conclusion TCM treatment of kidney deficiency and blood stasis type OP mainly focuses on tonifying the liver and kidney and activating blood circulation to remove stasis,supplemented by tonifying the spleen and boosting qi.This can provide a theoretical basis for the clinical treatment of OP.Additionally,the Epime-dium-Bupleurum drug pair can exert therapeutic effects on osteoporosis through a multi-target and multi-pathway mechanism,laying the foundation for subsequent experiments and clinical applications.

Ankylosing spondylitis (AS) combined with lower cervical fracture is often categorized into unstable fracture, with a high incidence of neurological injury and a high rate of disability and morbidity. As factors such as shoulder occlusion may affect the accuracy of X-ray imaging diagnosis, it is often easily misdiagnosed at the primary diagnosis. Non-operative treatment has complications such as bone nonunion and the possibility of secondary neurological damage, while the timing, access and choice of surgical treatment are still controversial. Currently, there are no clinical practice guidelines for the treatment of AS combined with lower cervical fracture with or without dislocation. To this end, the Spinal Trauma Group of Orthopedics Branch of Chinese Medical Doctor Association organized experts to formulate Clinical guidelines for the treatment of ankylosing spondylitis combined with lower cervical fracture in adults ( version 2024) in accordance with the principles of evidence-based medicine, scientificity and practicality, in which 11 recommendations were put forward in terms of the diagnosis, imaging evaluation, typing and treatment, etc, to provide guidance for the diagnosis and treatment of AS combined with lower cervical fracture.

Objective:To explore the relationship between serum levels of transforming growth factor- β1 (TGF- β1), vascular endothelial growth factor (VEGF) and tumor markers and local recurrence after breast-conserving surgery in patients with breast cancer. Methods:104 patients with breast cancer who underwent breast-conserving surgery in Xi’ an Central Hospital from Jan. 2020 to Dec. 2022 were selected and followed up for 1 year after surgery. According to the occurrence of local recurrence, they were divided into recurrence group ( n=16) and non-recurrence group ( n=88). The levels of serum TGF- β1, VEGF and tumor markers [carbohydrate antigen 125 (CA125), carcinoembryonic antigen (CEA) ] were compared between the two groups of patients. Univariate and multivariate Logistic regression analyses were used to analyze the influencing factors of local recurrence after breast-conserving surgery. Receiver operating characteristic (ROC) curve was applied to analyze the predictive value of TGF- β1, VEGF, CA125 and CEA on local recurrence after breast-conserving surgery. Results:The levels of VEGF, TGF- β1, CAl25 and CEA in recurrence group [ (358.83±38.00) ng/L, (849.90±74.19) U/mL, (18.34±1.61) ng/L and (40.20±5.64) ng/mL] were higher than those of (296.05±39.57) ng/L (742.85±79.96) ng/L, (14.97±1.66) U/mL and (32.79±4.72) ng/mL in non-recurrence group (all P<0.05). Lymph node metastasis, postoperative adjuvant therapy, tumor diameter and TNM staging were independent risk factors of local recurrence after breast-conserving surgery (all P<0.05). The areas under the ROC curves (AUCs) of serum VEGF, TGF- β1, CAl25 and CEA in predicting local recurrence after breast-conserving surgery were 0.847, 0.834, 0.925 and 0.935 respectively. The AUC of CEA was the largest, with sensitivity of 85.23% and specificity of 100% (all P<0.05) . Conclusions:The levels of TGF- β1, VEGF, CAl25 and CEA in patients with local recurrence after breast-conserving surgery are increased, and their levels are more effective in predicting local recurrence after breast-conserving surgery. Local recurrence after breast-conserving surgery is also affected by lymph node metastasis, postoperative adjuvant therapy, tumor diameter and TNM staging.

Objective To analyze the relationships between pulmonary ground-glass nodules(GGN)and bronchi and blood vessels and their diagnostic values for infiltrative lesions based on high-resolution computed tomography(HRCT)target scanning technology.Methods Patients with GGN detected by HRCT target scanning and complete pathological results were retrospectively selected as the research subjects.The relationships between GGN and bronchi and blood vessels in patients with different pathological types were analyzed,and the relationships for detecting infiltrative lesions were further analyzed,using pathological results as the gold standard.Results Three hundred patients were divided into 237 cases of pre-invasive lesions and 63 cases of infiltrative lesions according to pathological results.There were statistically significant differences in lesion properties and lesion morphology in patients with different types of GGN(P＜0.05).There were statistically significant differences in the relationships between GGN and bronchi and blood vessels in the pre-invasive lesions and the infiltrative lesions(P＜0.05).Based on the pathological results as the gold standard,the sensitivity of HRCT bronchial classification,vascular classification,and their combined detection of infiltrative lesions were 84.13％(53/63),95.24％(60/63),and 95.24％(60/63);specificity were 83.12％(197/237),87.34％(207/237),and 87.34％(207/237);accuracy were 83.33％(250/300),89.00％(267/300),and 89.00％(267/300).Conclusion Evaluating the classification of pulmonary GGN and bronchi and blood vessels by HRCT target scanning technology has good value in identifying infiltrative lesions.The combined diagnosis of the two signs can further improve the accuracy of detection.

Objective:To explore the mediation effects of perceived social support and work-family conflict on clinical nurses′ self-efficacy and parenting stress, and to provide theoretical basis for formulating intervention programs for parenting stress.Methods:A total of 631 clinical nurses from 8 grade A hospitals in Anhui Province were selected by convenience sampling method from August to October 2023. A cross-sectional survey was conducted with the general data questionnaire, the Chinese version of Work-Family Behavioral Role Conflict Scale, the Parenting Stress Scale for Clinical Nurses, the Perceptived Social Support Evaluation Scale and the General Self Efficacy Scale to analyze the relationship between perceptive social support, work-family conflict, self-efficacy and parenting stress and the mediating effect.Results:A total of 603 clinical nurses were included, including 9 males and 594 females, aged (35.16 ± 4.59) years. The total scores of work-family conflict, parenting stress, understanding of social support and self-efficacy were (87.10 ± 14.38), (51.00 ± 9.51), (59.91 ± 11.57) and (26.68 ± 6.27) points. The total effect of self-efficacy on parenting stress was - 0.385. The mediating paths of self-efficacy on parenting stress included: self-efficacy→perceived social support→parenting stress; self-efficacy→work-family conflict→parenting stress; self-efficacy→perceived social support→work-family conflict→parenting stress. The three indirect effects accounted for 18.69%, 53.72% and 16.87% of the total effect.Conclusions:Social support and work-family conflict have a chain mediation effect between clinical nurses′self-efficacy and parenting stress. Nursing managers can improve the self-efficacy of clinical nurses and enhance the understanding of social support to help reduce work-family conflict, so as to effectively alleviate the level of child-rearing stress of clinical nurses.

Objective:To understand the use of post-exposure prophylaxis (PEP) and analyze related factors among men who have sex with men (MSM) in Qingdao, and provide a reference for the AIDS prevention and control in this population.Methods:A cross-sectional survey conducted from April 2022 to February 2023. Relying on MSM social groups in Qingdao, a snowball sampling method was applied to recruit research subjects who met the inclusion criteria of age ≥18 years old, having had homosexual anal or oral sex in the past six months, and HIV-negative or infection status unknown. The sample size was estimated at 566. Data on demographic characteristics, sexual behavior characteristics, PEP use, and others of the research subjects was collected through on-site questionnaires. The logistic regression model was used to analyze the factors associated with using PEP.Results:A total of 811 participants were recruited, mainly aged 25-34 (53.6%, 435/811), unmarried (74.7%, 606/811), with an average monthly income of ≥5 000 yuan (52.2%, 423/811), and having lived in Qingdao for ≥10 years (75.6%, 613/811). The proportion of those who knew the HIV status of their sexual partners in the last six months was 67.1% (544/811), and those with HIV-positive partners were 3.6% (29/811). In the last six months, the proportion of participants who had group sex (86.4%, 701/811), unprotected anal sex (98.2%, 796/811), and use of club drugs (80.3%, 651/811) was high. Moreover, 28.4% (230/811) had used PEP. The multivariate logistic regression analysis showed that the factors related to the use of PEP included divorced or widowed (a OR=5.46,95% CI:1.96-15.17), average monthly income ≥5 000 yuan (a OR=2.04,95% CI:1.44-2.89), same-sex sexual orientation (a OR=0.40,95% CI:0.22-0.71), having HIV-positive sexual partners in the last six months (a OR=2.54,95% CI:1.13-5.71) and having been tested for HIV ≥3 times in the last six months (a OR=1.46,95% CI:1.04-2.06). Conclusions:The prevalence of risk behaviors among MSM in Qingdao was high, and the use of PEP was low. In the future, it is essential to increase HIV/AIDS prevention education among MSM, promote MSM to know the HIV status of their sexual partners, and reduce the prevalence of risk behaviors among this population. Additionally, explore medical insurance reimbursement plans for PEP to reduce utilization costs and promote the use of PEP by MSM after HIV exposure occurs as soon as possible.