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.

ObjectiveTo investigate the triglyceride-glucose (TyG) index and the level of serum homocysteine (Hcy) in association with the incidence of stroke in type 2 diabetes mellitus (T2DM) patients. MethodsBased on the chronic disease risk factor surveillance cohort in Pudong New Area, Shanghai, excluding those with stroke in baseline survey, T2DM patients who joined the cohort from January 2016 to October 2020 were selected as the research subjects. During the follow-up period, a total of 318 new-onset ischemic stroke patients were selected as the case group, and a total of 318 individuals matched by gender without stroke were selected as the control group. The Cox proportional hazards regression model was used to adjust for confounding factors and explore the serum TyG index and the Hcy biochemical indicator in association with the risk of stroke. ResultsThe Cox proportional hazards regression results showed that after adjusting for confounding factors, the risk of stroke in T2DM patients with 10 μmol·L⁻¹-¹ and Hcy>15 μmol·L⁻¹ was 1.532 times (95%CI: 1.017‒2.309 times, P=0.041) and 1.738 times (95%CI: 1.119‒2.699 times, P=0.014) higher respectively, compared to T2DM patients with Hcy≤10 μmol·L⁻¹. T2DM patients with TyG>9.074 had 1.396 times higher risk of stroke (95%CI: 1.091‒1.787, P=0.008) compared to those with TyG≤9.074. The study found that urea and α1-antitrypsin (α1-AT) were independent risk factors for the incidence of stroke in T2DM patients. For every unit increase in urea andα1-AT, the risk of stroke in T2DM patients increased by 233.6% (HR=3.336, 95%CI: 1.588‒7.009, P=0.001) and 11.3% (HR=1.113, 95%CI: 1.028‒1.205, P=0.008), respectively. Cumulative risk curves showed that Hcy>10 μmol·L⁻¹ and TyG>9.074 accelerated the time to stroke occurrence in T2DM patients. ConclusionElevated levels of Hcy>10 μmol·L⁻¹ and a higher TyG index are risk factors for stroke in T2DM patients. Effective interventions for Hcy and TyG should be conducted for diabetic patients to reduce the incidence of stroke.

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 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.

Polyunsaturated fatty acids (PUFAs) have diverse health-promoting effects, such as potentially protecting in immune, nervous, and cardiovascular systems by targeting a variety of sites, including most ion channels. Voltage-gated potassium channels of the K_V7 family and large-conductance Ca²⁺- and voltage-activated K⁺ (BK_Ca) channels are expressed in many tissues, therefore, their physiological importance is evident from the various disorders linked to dysfunctional K_V7 channels and BK_Ca channels. Thus, it is extremely important to learn how potassium channels are regulated by PUFAs. The aim of this review is to provide an overview of the effects of PUFAs on K_V7 channels and BK_Ca channels functions, as well as the mechanisms underlying these effects. In summarizing reported effects of PUFAs on K_V7 and BK_Ca channels mediated currents, we generally conclude that PUFAs increase the current amplitude, meanwhile, differential molecular and biophysical mechanisms are associated with the current increase. In K_V7 channels the currents increasement are associated with a shift in the voltage dependence of channel opening and increased maximum conductance in K_V7 channels, while in BK_Ca channels, they are associated with destabilization the pore domain closed conformation. Furthermore, PUFA effects are influenced by auxiliary subunits of K_V7 and BK_Ca channels, associate with channels in certain tissues. although findings are conflicting. A better understanding of how PUFAs regulate K_V7 and BK_Ca channels may offer insight into their physiological regulation and may lead to new therapeutic strategies and approaches.

【Objective】 To understand the prevalence of overweight/obesity among school-age children in Pudong New Area of Shanghai, and to explore the influence of gestational weight gain and pre-pregnancy body mass index (BMI) on weight status of school-age children. 【Methods】 From November to December 2020,a stratified cluster sampling method was adopted to select first-grade students from 13 primary schools in Pudong New Area of Shanghai.After matching with the birth monitoring database, 755 students with complete birth information were selected as the study subjects.The relevant information of mothers before and during pregnancy was retrospectively collected, and the effects of pregnancy weight gain combined with pre-pregnancy BMI on overweight/obesity in school-age children were analyzed. 【Results】 1) The prevalence rates of overweight and obesity of first-grade children were 15.89% and 18.41%, respectively.2) Maternal excessive weight gain during pregnancy (OR=1.678) and overweight/obesity before pregnancy (OR=2.315,2.412) were risk factors for overweight/obesity of the offspring at school age(P<0.05).3) For mothers who were underweight before pregnancy, excessive weight gain during pregnancy was associated with overweight/obesity in school-age children in their offspring (OR=7.436, 95%CI: 1.489 - 37.143,P<0.05).4) Excessive weight gain during pregnancy combined with overweight/obesity before pregnancy significantly increased the risk of overweight/obesity in offspring (OR=3.606, 95%CI: 2.030 - 6.405, P<0.05). Mothers who gained a moderate amount of weight during pregnancy and were emaciated before pregnancy had a significantly lower risk of overweight/obesity in their school-age children (OR=0.217, 95%CI: 0.049 - 0.967, P<0.05). 【Conclusion】 Excessive weight gain during pregnancy increases the risk of overweight/obesity in school-age children in their offspring, strengthening pregnancy health education and perinatal care to help pregnant women maintain appropriate weight gain during pregnancy may be an important and novel strategy to prevent childhood obesity.