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.

ObjectiveTo investigate the epidemiological and clinical characteristics of human bocavirus (HBoV) in hospitalized children with acute lower respiratory tract infection (ALRTI) at a single-center children’s hospital in Shanghai, thereby providing evidence for the diagnosis, treatment, and prevention of HBoV infection. MethodsA retrospective study was conducted on 19 537 hospitalized children with ALRTI at Shanghai Children’s Hospital from January 2021 to December 2023. Multiplex polymerase chain reaction (PCR) combined with capillary electrophoresis was used to detect HBoV and 12 other common respiratory viruses /atypical pathogens. The positive detection rate, demographic characteristics (sex, age), temporal distribution (year, season) of HBoV, as well as the clinical characteristics of severe and non-severe pneumonia were analyzed. ResultsThe overall HBoV-positive rate was 2.57% (503/19 537), with 59.44% (299/503) being single infections and 40.56% (204/503) being co-infections. The positive detection rate was significantly higher in boys than that in girls (2.78% vs 2.33%, χ²=3.88, P=0.049). The highest infection rate was observed in toddlers, followed by infants (χ²=379.57, P<0.001). The positive rate peaked in 2021 and reached its lowest point in 2023 (χ²=45.49, P<0.001), with epidemics mainly prevalent in summer and autumn. The main clinical symptoms were cough (90.06%, 453/503), fever (75.94%, 382/503), and wheezing (39.96%, 201/503). Children with severe pneumonia showed a higher incidence of wheezing compared with the non-severe group (P<0.001), while underlying diseases and co-infections had no significant association with disease severity (P>0.05). ConclusionHBoV was an important pathogen of ALRTI in children, predominantly affecting infants and toddlers, with higher susceptibility in boys and seasonal peaks in autumn and summer. The main clinical manifestations included cough, fever, and wheezing, with wheezing being more prevalent in children with severe pneumonia.

Objective To investigate the diagnostic value of endoscopic sign of light blue crest(LBC)capsuling papillary lesion(LCPL)for high-risk intestinal metaplasia(IM).Methods A total of 314 patients(352 biopsy specimens)who underwent endoscopic examination and biopsy in Department of Gastroenterology of Army Medical Center of PLA from January 2021 to June 2023 were recruited,and HE and HID-AB staining(the golden standard of high-risk IM)were apllied to detect the histological types and IM types.The samples were subsequently divided into chronic inflammation group,low-risk IM group,high-risk IM group,well-differentiated intestinal-type gastric cancer group,and poorly-differentiated intestinal-type gastric cancer group.The positive rate of LCPL in each group and its diagnostic efficacy were analyzed based on endoscopic images of the biopsy sites.Logistic regression analysis was used to investigate the relationship between LCPL sign and high-risk IM,as well as the clinical and pathological features associated with LCPL sign.Receiver operating characteristic(ROC)curve was plotted to evaluate the diagnostic efficacy of LCPL for high-risk IM,using indicators such as sensitivity,specificity,Youden index and area under the curve(AUC).Results The positive rate of the LCPL sign in high-risk IM group was 75.70%,significantly higher than that of the other groups(all P<0.001).Logistic regression analysis showed that LCPL sign was significantly correlated with high-risk IM(OR=30.286,95%CI:13.528～67.804,P<0.001).When the sign was employed in diagnosing high-risk IM,the sensitivity was 69.84%,the specificity was 93.75%,the Youden's index was 0.636,and the AUC value was 0.818(95%CI:0.773～0.857).Besides sensitivity,all above parameters of LCPL sign showed significantly better diagnostic efficacy than those of traditional LBC sign,which is used as a sign for diagnosing IM(P<0.001).Moreover,recognition of LCPL sign was not easily affected by age(OR=1.130,95%CI:0.709～1.800,P=0.607),lesion site(Angular incisure:OR=2.360,95%CI:0.732～7.613,P=0.151;Autrum:OR=2.257,95%CI:0.756～6.744,P=0.145),and presence of peptic ulcers(OR=1.085,95%CI:0.208～5.652,P=0.923).Significantly,94.12%of positive and 66.94%of negative LCPL signs could be rapidly recognized within 3 s(OR=4.536,95%CI:1.372～14.997,P=0.013).Conclusion LCPL sign shows high efficacy and potential clinical application value for high-risk IM in gastric mucosa of endoscopic diagnosis.

Objective To investigate the change in choroid plexus(CP)volume in Parkinson's disease(PD)patients with different cognitive states and its correlation with structural volumes of other brain regions.Methods A cross-sectional study was conducted on 48 PD patients admitted in Department of Neurosurgery of the First Affiliated Hospital of Army Medical University between May 2023 and April 2024,and on 35 healthy controls(HC)recruited through a physical exam center.According to the results of Mini-Mental State Examination(MMSE),the patients were divided into PD with cognitive impairment(PD-CI)group(n=27)and PD with normal cognitive function(PD-NC)group(n=21).3.0T magnetic resonance imaging(MRI)was performed using MPRAGE sequences,and CP volume and volumes of other brain regions were obtained using FreeSurfer 6.0 software.The CP volume was adjusted by calculating the ratio of its volume to estimated total intracranial volume(eTIV).After controlling for confounders,partial correlation analysis was used to assess the relationship between the CPV/eTIV ratio and the volumes of other brain regions as well as cognitive scale scores.Additionally,multiple linear regression analysis was performed to further explore the relationship between CPV and cognitive function in the PD-CI group.Results Compared to the HC group,the CPV in the PD-CI group was significantly larger(P=0.029).In the PD-CI group,the CPV/eTIV ratio showed significant positive correlations with the volume of the lateral ventricles(r=0.689,P=0.001),the volume of the third ventricle(r=0.592,P=0.006),the volume of cerebrospinal fluid(CSF)(r=0.508,P=0.022),and white matter hyperintensities(WMH)(r=0.486,P=0.030),but was negatively correlated with the volume of the caudate nucleus(r=-0.530,P=0.016),the volume of the thalamus(r=-0.477,P=0.033),and the MMSE scores(r=-0.483,P=0.031).But in the PD-NC group,the CPV/eTIV ratio was only positively correlated with CSF volume(r=0.571,P=0.021).Multiple linear regression analysis indicated that the CPV/eTIV ratio and MMSE scores remained significantly negatively correlated in the PD-CI group(β=-0.388,P=0.046).Conclusion Cognitive impairment in PD patients may be closely associated with the change in CP volume,suggesting that the volume can serve as a potential imaging marker in assessment of cognitive impairment in PD patients.

Obese type 2 diabetes belongs to the category of"consumptive thirst"in traditional Chinese medicine,and obesity is its main cause.This paper summarizes the pathogenesis of obese type 2 diabetes from three aspects:thirst caused by fat evil,deficiency caused by fat evil,and fat evil causing various pathogens.That is to say,the congestion of fat evil produces heat and hurts Yin,lead-ing to consumptive thirst.The accumulation of ointment and fat will damage Yang in the middle energizer and hinder spleen transport.Phlegm and dampness originate from spleen deficiency,which gather in veins and generate blood stasis and heat.The com-plicated combination of phlegm,blood stasis and heat leads to the relapse or development of consumptive thirst.Based on the theory of"maintaining the sweet and restoring the body fluids",this paper skillfully uses sweet herbs and cooperates with other nature and flavors to treat the pathogenesis of"thirst,deficiency and blood stasis"caused by fat evil injuring body fluids,to achieve the purposes of clear-ing away heat and nourishing Yin,strengthening spleen and protecting middle energizer,removing turbidity and blood stasis.Finally,the body fluid is continuously produced,transported smoothly,and the consumptive thirst is relieved.

Objective:To systematically evaluate studies validating the performance of the Global Leadership Initiative on Malnutrition (GLIM) in diagnosing malnutrition.Methods:Seven Chinese and English databases including Embase, Web of Science (WOS), PubMed, CINAHL, Cochrane Library, SinoMed, CNKI, Wanfang Data, and VIP Database were searched for articles on the validation of GLIM criteria published between September 2018 and September 2024. Two researchers independently performed literature screening and data extraction. The concurrent and predictive validity of the criteria was analyzed.Results:A total of 136 papers were included for analysis. The GLIM criteria for diagnosing malnutrition had a sensitivity of 77%, a specificity of 87%, and an area under the curve (AUC) of 0.90. Malnutrition diagnosed by the GLIM criteria predicted prolonged hospital and intensive care unit (ICU) stays, increased readmission and complication rates (both overall and infectious), reduced survivals (median, overall, and disease-free), and increased in-hospital and follow-up mortalities. Both moderate and severe malnutrition predicted decreased overall survival. However, only three studies analyzed the impact of nutritional therapy on the clinical outcomes of malnourished patients.Conclusions:The GLIM criteria accurately differentiate malnutrition and are a valid predictive tool of clinical outcomes. However, the validity criteria in these validation studies were questionable, along with high methodological heterogeneity. Furthermore, there is a lack of studies validating the role of nutritional therapy in improving the clinical outcomes of malnourished patients.

Objective To observe the effect of scalp acupuncture points including Shenting(GV24),Benshen(GB13)and Sishen-cong(EX-HN1)combined with computer-assisted training on memory impairment after stroke.Methods From May,2023 to December,2024,62 patients with post-stroke memory dysfunction who received rehabilita-tion treatment in Beijing Bo'ai Hospital were selected and divided into control group(n=31)and observation group(n=31)randomly.Both groups received conventional treatment and computer-assisted training,while the observation group received additional scalp acupuncture treatment,for four weeks.They were evaluated with Montreal Cognitive Assessment(MoCA),auditory memory span,and modified Barthel Index(MBI)before and after treatment.Results No adverse reaction occured during treatment.After treatment,the total score of MoCA and the memory dimen-sion score,and auditory memory span score improved in both groups(|t|>3.838,P<0.001),and the d-value was more in the observation group than in the control group(|t|>2.160,P<0.05);the score of MBI improved in both groups(|t|>7.471,P<0.001),however,there was no significant difference between two groups(P>0.05).Conclusion Computer-assisted training could significantly improve the cognitive function of patients with post-stroke memory dysfunction,especially the memory function,and is more effective while combining with scalp acupunc-ture.

Obese type 2 diabetes belongs to the category of"consumptive thirst"in traditional Chinese medicine,and obesity is its main cause.This paper summarizes the pathogenesis of obese type 2 diabetes from three aspects:thirst caused by fat evil,deficiency caused by fat evil,and fat evil causing various pathogens.That is to say,the congestion of fat evil produces heat and hurts Yin,lead-ing to consumptive thirst.The accumulation of ointment and fat will damage Yang in the middle energizer and hinder spleen transport.Phlegm and dampness originate from spleen deficiency,which gather in veins and generate blood stasis and heat.The com-plicated combination of phlegm,blood stasis and heat leads to the relapse or development of consumptive thirst.Based on the theory of"maintaining the sweet and restoring the body fluids",this paper skillfully uses sweet herbs and cooperates with other nature and flavors to treat the pathogenesis of"thirst,deficiency and blood stasis"caused by fat evil injuring body fluids,to achieve the purposes of clear-ing away heat and nourishing Yin,strengthening spleen and protecting middle energizer,removing turbidity and blood stasis.Finally,the body fluid is continuously produced,transported smoothly,and the consumptive thirst is relieved.

Objective To explore the role of postdoctoral talent cultivation in high-quality development of public hospi-tals.Methods The data of 165 postdoctoral fellows were analyzed from Zhongshan Ophthalmology Center,Sun Yat-sen Univer-sity over the past decade.The analysis involved examining the entire management process from recruitment to completion,inclu-ding the improvement of relevant systems,evaluation standards,implementation of hierarchical management,mentor-student in-teractions,and academic exchanges,as well as studying the quality enhancement of the postdoctoral talent pool,research output,and employment analysis.Results The standardized management of whole postdoctoral cultivation process and the continuous improvement of systems significantly enhanced the achievements of postdoctoral fellows in research,publications,and commer-cialization of the scientific and research findings.For instance,from 2018 to 2022,the number of National Science Foundation-funded programs that the postdoctoral fellows obtained accounted for 26.7％of the total number,while the number of provincial and ministerial funded programs accounted for 73.3％.In 2020,the proportion of postdoctoral researchers who obtained the Na-tional Natural Science Foundation of China's Youth Program was 80％of the total.In 2021,the proportion of postdoctoral fellows who published papers with an impact factor of above 10 as the first author or co-first author was 45.83％.Conclusion The training of high-level medical postdoctoral talents is crucial for high-quality development of public hospitals,improving interdisci-plinary adaptability of postdoctoral fellows and collaborative mentorship awareness.

Objective:To explore the correlation between nurses' electronic health literacy and their health education competence.Methods:A convenience sampling method was used to select nurses from 24 secondary and tertiary hospitals in Jincheng for the study from July to August 2022. The Mobile-e Health Literacy Scale and the Nurse Health Education Competence Self-assessment Scale were used to survey the subjects. Pearson correlation analysis was performed to analyze the correlation between nurses' electronic health literacy and their health education competence. Canonical correlation analysis was employed to build a standardized canonical correlation model, conduct canonical structure analysis, and canonical redundancy analysis to explore the relationship between electronic health literacy and health education competence in nurses.Results:A total of 705 questionnaires were distributed, 74 were excluded due to short response times (<120 seconds), regular responses, or incorrect fillings, leaving 631 valid questionnaires, with an effective response rate of 89.5%. The total score of the Mobile-e Health Literacy Scale for 631 nurses was (50.40±8.75), with scores of (12.69±2.41) for self-perception, (21.35±3.70) for information acquisition, and (16.36±3.29) for interaction judgment. The total score for the Nurse Health Education Competence Self-assessment Scale was (366.32±57.51), with subscale scores of (29.71±4.77) for knowledge and experience, (95.65±14.20) for comprehensive quality, and (240.97±40.85) for skills and abilities. The total score of electronic health literacy and the scores of each dimension were positively correlated with the scores of each subscale of health education competence ( P<0.01). Canonical correlation analysis identified three pairs of canonical variables, with correlation coefficients of 0.750, 0.279, and 0.067 for the first, second, and third pairs, respectively. The correlation coefficients of the first and second pairs were statistically significant ( P<0.01). Nurses' electronic health literacy was primarily determined by interaction judgment ( r=-0.982), while health education competence was primarily determined by skills and abilities ( r=-0.995) . Conclusions:There is a positive correlation between nurses' electronic health literacy and health education competence. Enhancing nurses' electronic health literacy is of significant importance for improving their health education competence.