Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Aim To establish a stable hepatic stellate cell ( HSC ) -specific G protein-coupled receptor kinase 2 ( GRK2 ) knockout mice and provide the important animal model for further studying the biological function of GRK2 in HSC. Methods The loxP-labeled Grk2 gene mouse (Grk2

Objective To investigate the clinical efficacy of Yiqi Huayu Decoction(mainly composed of Astragali Radix,Dioscoreae Rhizoma,Poria,fried Euryales Semen,Ecliptae Herba,Rosae Laevigatae Fructus,charred Crataegi Fructus,Ligustri Lucidi Fructus,Salviae Miltiorrhizae Radix et Rhizoma,and Leonuri Herba)combined with Calcium Dobesilate in the treatment of diabetic nephropathy(DN)with qi deficiency and blood stasis syndrome,and to observe the effect of the therapy on vascular endothelial growth factor(VEGF)and insulin-like growth factor 1(IGF-1).Methods Ninety patients with DN of qi deficiency and blood stasis type were randomly divided into an observation group and a control group,with 45 patients in each group.All patients received basic hypoglycemic therapy and treatment for controlling blood pressure and regulating lipid metabolism disorders.Moreover,the patients in the control group were given Calcium Dobesilate orally,and the patients in the observation group were given Yiqi Huayu Decoction combined with Calcium Dobesilate.The course of treatment lasted for 3 months.The changes of traditional Chinese medicine(TCM)syndrome scores,renal function parameters and serum VEGF and IGF-1 levels in the two groups of patients were observed before and after the treatment,and the clinical efficacy of the two groups was evaluated after treatment.Results(1)After 3 months of treatment,the total effective rate of the observation group was 91.11%(41/45),and that of the control group was 75.56%(34/45).The intergroup comparison(tested by chi-square test)showed that the therapeutic effect of the observation group was significantly superior to that of the control group(P＜0.05).(2)After one month and 3 months of treatment,the TCM syndrome scores of both groups were significantly lower than those before treatment(P＜0.05),and the scores after 3 months of treatment in the two groups were significantly lower than those after one month of treatment(P＜0.05).The intergroup comparison showed that the reduction of TCM syndrome scores of the observation group was significantly superior to that of the control group after one month and 3 months of treatment(P＜0.01).(3)After treatment,the levels of renal function parameters such as serum creatinine(Scr),blood urea nitrogen(BUN),and glomerular filtration rate(GFR)in the two groups of patients were significantly improved compared with those before treatment(P＜0.05),and the observation group's effect on the improvement of all renal function parameters was significantly superior to that of the control group(P＜0.01).(4)After treatment,the serum VEGF and IGF-1 levels in the two groups of patients were significantly lower than those before treatment(P＜0.05),and the observation group's effect on the decrease of serum VEGF and IGF-1 levels was significantly superior to that of the control group(P＜0.01).(5)In the course of treatment,no significant adverse reactions occurred in the two groups of patients,with a high degree of safety.Conclusion Yiqi Huayu Decoction combined with Calcium Dobesilate exerts certain therapeutic effect in treating DN patients with qi deficiency and blood stasis syndrome.The combined therapy can effectively down-regulate the serum levels of VEGF and IGF-1,significantly improve the renal function,and alleviate the clinical symptoms of the patients,with a high degree of safety.

Objective To explore the relationship and internal path between activities of daily living(ADL),sleep quality and mental health of community elderly people in Shanghai.Methods A questionnaire survey was conducted among community residents aged 60 years and older seeing doctors in community health care center of five streets in Shanghai during Sept to Dec,2021 using convenience sampling.Activities of Daily Living(ADL),Pittsburgh Sleep Quality Index(PSQI)and 10-item Kessler Psychological Distress Scale(K10)were adopted in the survey.Single factor analysis,correlation analysis and multiple linear regression were used to analyze the data.The effect relationship between the variables was tested using Bootstrap's mediated effects test.Results A total of 1 864 participants were included in the study.The average score was 15.53±4.47 for ADL,5.60±3.71 for PSQI and 15.50±6.28 for K10.The rate of ADL impairment,poor sleep quality,poor and very poor mental health of the elderly were 23.6%,27.3%,11.9%and 4.9%,respectively.ADL and sleep quality were all positively correlated with mental health(r=0.321,P＜0.001;r=0.466,P＜0.001);ADL was positively correlated with sleep quality(r=0.294,P＜0.001).Multiple linear results of factors influencing mental health showed that ADL(β= 0.457,95%CI:0.341-0.573),sleep quality(β =0.667,95%CI:0.598-0.737)and mental health were positively correlated(P＜0.001).Sleep quality partially mediated the relationship between ADL and mental health(95%CI:0.078-0.124)with an effect size of 33.0%.Conclusion Sleep quality is a mediator between ADL and mental health among community elderly people.Improving ADL and sleep quality may improve mental health in the population.

ObjectiveBased on fluorescence lifetime imaging technology, a novel method for viscosity detection is proposed and the capability of different weighting of fluorescence lifetimes in distinguishing the viscosity of glycerol-water mixtures is evaluated, aiming to enhance the accuracy and reliability of viscosity differentiation. MethodsThis approach incorporates the principles of electronic weighting, introducing both amplitude-weighted average fluorescence lifetime (τ_m) and intensity-weighted average fluorescence lifetime (τ_i). Viscosity changes in glycerol-water mixtures are detected through τ_m and τ_i. τ_m Reflects the relationship between fluorescence signal amplitude and time, while τ_i focuses on the time-varying characteristics of fluorescence signal intensity. ResultsThe results of both τ_m and τ_i mutually corroborate each other, not only enhancing the reliability in detecting viscosity changes in glycerol-water mixtures but also revealing their unique roles in the detection process. Although τ_m plays a crucial role in capturing changes in fluorescence signal amplitude, τ_i exhibits higher accuracy in viscosity detection when considering the time-varying characteristics of fluorescence signal intensity. It is particularly noteworthy that, due to τ_i’s greater sensitivity, microenvironment viscosity detection can be directly analyzed using τ_i. This provides a more convenient approach for real-time, highly sensitive microfluidic viscosity monitoring. Therefore, through the comprehensive utilization of τ_m and τ_i, a more thorough and accurate understanding of the viscosity information in glycerol-water mixtures can be obtained, and specific parameters can be selected for in-depth analysis based on specific needs. ConclusionThe combination of amplitude weighting and intensity weighting allows for a more sensitive identification of subtle changes in viscosity under different conditions. The innovation of this method lies in its simultaneous consideration of multiple parameters, enhancing sensitivity and distinguishability to variations in viscosity. Therefore, this weighted-dependent fluorescence lifetime imaging technique not only introduces a novel approach for viscosity detection in glycerol-water mixtures but also provides a powerful analytical tool for various fields, including microfluidics, rheology, and research on novel functional materials.

This paper outlines the common aspects of constructing integrated urban medical groups,focusing on governance,organizational restructuring,operational modes,and mechanism synergy.It then delves into the challenges in China's group construction,highlighting issues with power-responsibility alignment,capacity evolution,incentive alignment,and performance evaluation.Finally,the paper suggests strategies to enhance China's compact urban medical groups,focusing on governance reform,capacity building,benefit integration,and performance evaluation.