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.

Objective To observe the effects of pegylated losenatide injection combined with metformin tablets on serum metabolism,lipid levels and intestinal flora in obese type 2 diabetes mellitus(T2DM)patients after axial gastrectomy.Methods Obese T2DM patients who underwent axial gastrectomy were divided into treatment group and control group by cohort methods.The control group was treated with metformin hydrochloride tablet 0.5 g orally,tid.The treatment group was treated by subcutaneous injection of pegylated losenatide injection 0.2 mg once a week on the basis of control group.Both groups were treated continuously for 3 months.Body mass index(BMI),serum metabolic indexes,blood lipid levels,blood glucose levels,intestinal flora and adverse drug reactions were compared between the two groups.Results In this study,a total of 70 subjects were included in the treatment group,and 50 subjects were included in the control group.After three months of treatment,the BMI indices of the treatment and control groups were(26.35±2.36)and(29.34±3.59)kg·m-2,respectively;the glutathione peroxidase levels were(192.42±13.18)and(134.27±12.86)U;interleukin-6 levels were(6.14±1.78)and(7.65±2.09)μg·L-1;fasting blood glucose levels were(5.36±0.41)and(7.43±0.78)mmol·L-1;total cholesterol levels were(2.55±0.67)and(3.47±0.79)mmol·L-1 for the treatment and control groups,respectively.The levels of Bifidobacteria,Bacteroides,Lactobacilli,Enterobacteria,and Enterococci in the treatment group were(8.79±1.36),(9.62±1.37),(6.74±2.15),(7.98±0.61),and(7.23±1.29)logN·g-1,respectively;in the control group,these levels were(7.98±1.79),(8.13±1.45),(5.71±2.41),(9.21±0.88),and(8.15±1.54)logN·g-1.The differences in the above indicators between the treatment and control groups were statistically significant(all P＜0.05).The main adverse drug reactions in the treatment group included nausea,headache,dizziness,elevated blood pressure,and indigestion.In the control group,the main adverse drug reactions were nausea,headache,and indigestion.The total incidence of adverse drug reactions in the treatment and control groups was 8.57％and 6.00％,respectively,with no statistically significant difference(P＞0.05).Conclusion Pegylated losenatide injection combined with metformin tablets has a significant effect on axial gastrectomy in obese type 2 diabetes patients.

Objective To compare the application effect of intermittent androgen deprivation(IAD)and continued androgen deprivation(CAD)on advanced prostate cancer and influence on prognosis.Methods The patients with advanced prostate cancer were divided into treatment group(86 cases)and control group(62 cases)according to the cohort method.The treatment group was given IAD regimen(subcutaneous injection of 3.6 mg goserelin once every 28 days)combined with oral administration of flutamide(250 mg every 3 times a day)or combined with oral administration of bicalutamide(50 mg once a day),and the control group was treated with CAD regimen(bilateral orchiectomy combined with continuous flutamide or bicalutamide orally,with the same dosage as the treatment group).The observation follow-up time of both groups was ≥9 months.Efficacy,serum total testosterone(TT),prostate specific antigen(PSA)and vascular endothelial growth factor(VEGF)were compared between the two groups after treatment,and the side effects of treatment,quality of life[Functional Assessment of Cancer Therapy-Prostate(FACT-P)]and disease progression were evaluated.Results At 9 months after treatment,the objective response rates(ORR)in treatment group and control group were 30.99％(22 cases/71 cases)and 29.09％(16 cases/55 cases),and the disease control rates(DCR)were 71.83％(51 cases/71 cases)and 69.09％(38 cases/55 cases)respectively(P＞0.05).Serum TT levels in treatment group and control group were(25.53±9.44)and(22.51±8.28)ng·dL-1,PSA levels were(4.48±1.02)and(4.32±0.95)ng·mL-1,and VEGF levels were(121.03±35.26)and(118.65±33.42)pg·mL-1 respectively(all P＞0.05).The incidence rates of hot flash in treatment group and control group were 21.13％and 56.36％,the incidence rates of breast swelling pain were 16.90％and 34.55％,and the incidence rates of osteoporosis were 8.45％and 25.45％respectively(all P＜0.05).The scores of physical condition of FACT-P in treatment group and control group were(24.15±4.22)and(20.28±3.71)points,the scores of life condition were(20.28±2.94)and(17.81±2.84)points,scores of prostate cancer specific(PCS)module were(33.21±6.32)and(28.42±5.43)points,respectively,the difference were all statistically significant(all P＜0.05).The cumulative progression-free survival rates in treatment group and control group were 61.97％and 58.18％(P＞0.05).Conclusion IAD is as effective as CAD in the treatment of advanced prostate cancer and has a similar effect on the prognosis of patients,but the former one has fewer side effects of treatment and helps to improve the quality of life of patients.

Quercetin can mediate the activation of mitogen-activated protein kinase(MAPK)signaling pathways to prevent osteoporosis(OP).This paper comprehensively discusses the interrelationship between MAPK and osteoporosis-related cells based on the latest domestic and international research.Additionally,it elucidates the research progress of quercetin in mediating the MAPK signaling pathway for OP prevention.The aim is to provide an effective foundation for the clinical prevention and treatment of OP and the in-depth development of quercetin.

Objective: To explore the association between lifestyle and fat mass index (FMI) in different positions of children and adolescents aged 7-18, so as to provide a scientific basis for health promotion in children and adolescents. Methods: A total of 1 531 students aged 7-18 was selected by intentional sampling from 4 schools in Tongzhou District, Beijing from September to December in 2020 and August in 2022. Questionnaire survey was used to collect lifestyle including dietary behavior, moderate to vigorous physical activity, smoke and drink behaviors, sleep time and sleep quality. Dual energy Xray absorptiometry was employed to assess fat mass, and calculated total, android, trunk, hip, gynoid and leg fat mass index (FMI). The ttest and Chisquare test were used to compare the differences of different lifestyle. Logistic regression was used to analysis association between lifestyle and body composition in different positions. Results: Compared with healthy lifestyle, unhealthy lifestyle had higher risk for hightrunk FMI (OR=1.40, P<0.05). After adjusted for sex and age, unhealthy lifestyle had higher risk for hightotal FMI, highandroid FMI, hightrunk FMI (OR=1.37, 1.37, 1.50, P<0.05), compared with healthy lifestyle. Stratified analysis found the associations between unhealthy lifestyle and hightotal FMI, highandroid FMI, hightrunk FMI, and highthigh FMI were only significant in girls with 7-12 years old (OR=2.13, 2.46, 2.13, 2.13, P<0.05). Conclusions Unhealthy lifestyle is associated with hightotal FMI, highandroid FMI and hightrunk FMI. A healthy lifestyle should be maintained during puberty, especially before puberty, to help children and adolescents reduce body fat and promote a balanced distribution of body composition.

Objective:To study the expression levels and clinical significance of microR-NA-183-5p(miR-183-5p)and thioesterase superfamily member 4(THEM4)in colon cancer tissues.Methods:A total of 96 patients with colon cancer who in Hebei China Petroleum Central Hospital gathered as the research objects.During the course of radical resection of colon cancer patients,the colon cancer tissues and adjacent normal tissues were collected.The relative expression levels of miR-183-5p and THEM4 mRNA in colon cancer tissues and adjacent normal tissues were detected.Analysis of the correlation between miR-183-5pand THEM4mRNA in colon cancer and their relation-ship with prognosis.COX regression was used to analyze the risk factors affecting the prognosis of pa-tients with colon cancer.Results:Compared with adjacent normal tissues,the expression level of miR-183-5p in colon cancer tissues increased(P＜0.05),and the expression level of THEM4 mRNA decreased(P＜0.05).MiR-183-5p was negatively correlated with THEM4 mRNA expression in colon cancer tissue(r=-0.529,P＜0.05).The survival rate of the high expression group of miR-183-5p lower than that of the low expression group(P＜0.05),the survival rate of the high expression group of THEM4 was obviously higher than that of the low expression group(P＜0.05).TNM stage(Ⅲ-Ⅳ),high expres-sion of miR-183-5p and low expression of THEM4 were risk factors for poor prognosis in patients with colon cancer(P＜0.05).Conclusion:The expression level of miR-183-5p in cancer tissues of patients with colon cancer is increased,and the expression level of THEM4 is decreased,both are closely relat-ed to the clinicopathological characteristics and prognosis of patients.