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 study the active ingredients and mechanism of action of Xinkeshu tablets against myo-cardial ischemia by network pharmacology and ze-brafish model.Methods The anti-myocardial ische-mia activity of Xinkeshu tablets was evaluated by iso-prenaline hydrochloride(ISO)-induced zebrafish myo-cardial ischemia model and H2O2-induced H9c2 dam-age model.The active ingredients of Xinkeshu tablets were retrieved using databases such as TCMSP.The potential targets were predicted by PharmaMapper data-base.Myocardial ischemic disease targets were searched by OMIM database.The potential therapeutic targets of Xinkeshu tablets against myocardial ischemia were analyzed.GO and KEGG enrichment analysis were conducted on core targets.The active ingredients were verified by zebrafish and cell model.qRT-PCR was used to detect the expression of key targets.Re-sults Xinkeshu tablets could significantly alleviate ISO-induced pericardial edema and bradycardia.It al-so could increase sinus venous-bulb aortic(SV-BA)distance and improve the cell viability.The 30 poten-tial active ingredients of Xinkeshu tables mainly acted on 30 core targets,including ALB,AKT1 and MAPK1,to regulate 627 GO items,including protein phosphorylation,negative regulation of apoptosis and positive regulation of PI3K signal transduction.KEGG results showed that 117 signaling pathways,including PI3K/Akt,FOXO and Ras,exerted anti-myocardial ischemia effect.Salvianolic acid A,lithospermic acid,rosmarinic acid,salvianolic acid D,salvianolic acid B,ginsenoside Rg2,hyperoside,3'-methoxypuerarin,3'-hydroxypuerarin and ginsenoside Rg1 could alleviate ISO-induced zebrafish myocardial ischemia and im-prove the cell viability.Xinkeshu tablets could upregu-late the expression of genes such as ras and akt1,and downregulate the expression of genes such as mapk1 and mapk8.Conclusion The active ingredients,in-cluding salvianolic acid A in Xinkeshu tablets,exert anti-myocardial ischemia effects by targeting targets,such as AKT1,MAPK1,and regulating signaling path-ways,such as PI3K/Akt,MAPK and Ras.

Aim To investigate the expression level of CBX4 in esophageal squamous cell carcinoma(ESCC)and the effect of CBX4 on ESCC proliferation and un-derlying molecular mechanisms.Methods The ex-pression of CBX4 in different cancers was analyzed in Pan-cancers.The expression level of CBX4 in ESCC was analyzed by t-test based on Gene Expression Omni-bus(GEO)data.The viability of CBX4-overex-pressed/knockdown ESCC cells was detected by MTT assay,colony formation assay and flow cytometry assay.Furthermore,the tumor volumn,tumor weight and Ki67 expression were measured by mouse xenograft assay and immunohistochemistry.The mRNA and protein ex-pression levels of apoptosis-related genes PARP、Bcl-2、Bax were determined by qRT-PCR and Western blot,respectively.In addition,the underlying molecular mechanism of CBX4 in ESCC was revealed by qRT-PCR and Western blot.Results CBX4 was upregulat-ed in various cancers.The expression level of CBX4 in ESCC was higher than that in normal tissues(P＜0.05)based on Gene Expression Omnibus(GEO)da-ta.Compared with the normal group,the proliferation of CBX4 knockdown ESCC cells was significantly in-hibited and the apoptosis was promoted(P＜0.05).Meanwhile,the mRNA and protein expression levels of cleaved PARP and Bax were upregulated while that of Bcl-2 was downregulated.In CBX4 overexpression group,tumor volume in vivo increased(P＜0.05).Immunohistochemical results also showed an increase in Ki67 expression.Furthermore,the results of RNA-seq,bioinformatics analysis and qRT-PCR experiments indicated that CBX4 probably regulated the prolifera-tion and apoptosis of ESCC through p38 MAPK signa-ling pathway.Conclusion CBX4 is highly expressed in ESCC and plays as an oncogene role,which might regulate cell proliferation through the p38 MAPK signa-ling pathway.

Objective To explore the difference in the effectiveness between proximal femoral nail anti-rotation(PFNA)and proximal femoral locking compression plate(PFLCP)of intertrochanteric fracture in the elderly patients combined with knee osteoarthritis.Methods The clinical data of 65 intertrochanteric femoral fractures combined with knee osteoarthritis be-tween June 2015 and February 2021 were retrospectively analyze.They were divided into two groups according to the different surgical methods.PFNA group was composed of 36 patients,12 males and 24 females,aged from 61to 88 years old with an av-erage of(77.0±6.4)years old.There were 17 cases of left injury and 19 cases of right injury.According to modified Evans clas-sification,there were 3 cases of type Ⅱ,19 cases of type Ⅲ,10 cases of type Ⅳ,and 4 cases of type Ⅴ.PFLCP group was com-posed of 29 patients,11 males and 18 females,aged from 60 to 92 years old with an average of(78.8±6.5)years old.There were 14 cases of left injury and 15 cases of right injury.According to modified Evans classification,there were 2 cases of typeⅡ,18 cases of type Ⅲ,7 cases of type Ⅳ,and 2 cases of type Ⅴ.Comparison of operation time,intraoperation blood loss,postoperative bed time,incidence of postoperative complications,Harris score at 6 months and 1 year postoperation.Results All 65 patients were followed up ranging from 12 to 24 months with an average of(16.9±3.6)months.In the PFNA and PFLCP groups,the operation time was respectively(57.6±6.8)min and(77.4±6.5)min,the intraoperative blood loss was(128.3±50.3)ml and(156.3±23.9)ml,postoperative bed time was(4.0±2.5)days and(8.1±2.0)days,Harris score at 6 months post-operative was(45.3±8.6)points and(36.3±7.0)points.There were significant differences between two groups(P＜0.05).Inci-dence of postoperative complications was 19.4％(7/36)and 34.5％(10/29),Harris score at 1 year postoperative was(60.8±6.7)points and(59.0±8.1)points.There was no significant difference between the two groups(P＞0.05).Conclusion Compared with PFLCP,PFNA treatment of elderly patients with knee osteoarthritis between the femoral intertrochanteric fractures shorter surgical time,less intraoperative blood loss,bed rest after surgery,short-term hip function recovery better,when the affected knee joint can tolerate traction,can be used as a priority.

Objective To investigate the distribution and antimicrobial resistance profiles of the common pathogens isolated from urine from 2015 to 2021 in the CHINET Antimicrobial Resistance Surveillance Program.Methods The bacterial strains were isolated from urine and identified routinely in 51 hospitals across China in the CHINET Antimicrobial Resistance Surveillance Program from 2015 to 2021.Antimicrobial susceptibility was determined by Kirby-Bauer method,automatic microbiological analysis system and E-test according to the unified protocol.Results A total of 261 893 nonduplicate strains were isolated from urine specimen from 2015 to 2021,of which gram-positive bacteria accounted for 23.8％(62 219/261 893),and gram-negative bacteria 76.2％(199 674/261 893).The most common species were E.coli(46.7％),E.faecium(10.4％),K.pneumoniae(9.8％),E.faecalis(8.7％),P.mirabilis(3.5％),P.aeruginosa(3.4％),SS.agalactiae(2.6％),and E.cloacae(2.1％).The strains were more frequently isolated from inpatients versus outpatients and emergency patients,from females versus males,and from adults versus children.The prevalence of ESBLs-producing strains in E.coli,K.pneumoniae and P.mirabilis was 53.2％,52.8％and 37.0％,respectively.The prevalence of carbapenem-resistant strains in E.coli,K.pneumoniae,P.aeruginosa and A.baumannii was 1.7％,18.5％,16.4％,and 40.3％,respectively.Lower than 10％of the E.faecalis isolates were resistant to ampicillin,nitrofurantoin,linezolid,vancomycin,teicoplanin and fosfomycin.More than 90％of the E.faecium isolates were ressitant to ampicillin,levofloxacin and erythromycin.The percentage of strains resistant to vancomycin,linezolid or teicoplanin was＜2％.The E.coli,K.pneumoniae,P.aeruginosa and A.baumannii strains isolated from ICU inpatients showed significantly higher resistance rates than the corresponding strains isolated from outpatients and non-ICU inpatients.Conclusions E.coli,Enterococcus and K.pneumoniae are the most common pathogens in urinary tract infection.The bacterial species and antimicrobial resistance of urinary isolates vary with different populations.More attention should be paid to antimicrobial resistance surveillance and reduce the irrational use of antimicrobial agents.

Objective To understand the distribution and changing resistance profiles of clinical isolates of Enterococcus in hospitals across China from 2015 to 2021.Methods Antimicrobial susceptibility testing was conducted for the clinical isolates of Enterococcus according to the unified protocol of CHINET program by automated systems,Kirby-Bauer method,or E-test strip.The results were interpreted according to the Clinical & Laboratory Standards Institute(CLSI)breakpoints in 2021.WHONET 5.6 software was used for statistical analysis.Results A total of 124 565 strains of Enterococcus were isolated during the 7-year period,mainly including Enterococcus faecalis(50.7％)and Enterococcus faecalis(41.5％).The strains were mainly isolated from urinary tract specimens(46.9％±2.6％),and primarily from the patients in the department of internal medicine,surgery and ICU.E.faecium and E.faecalis strains showed low level resistance rate to vancomycin,teicoplanin and linezolid(≤3.6％).The prevalence of vancomycin-resistant E.faecalis and E.faecium was 0.1％and 1.3％,respectively.The prevalence of linezolid-resistant E.faecalis increased from 0.7％in 2015 to 3.4％in 2021,while the prevalence of linezolid-resistant E.faecium was 0.3％.Conclusions The clinical isolates of Enterococcus were still highly susceptible to vancomycin,teicoplanin,and linezolid,evidenced by a low resistance rate.However,the prevalence of linezolid-resistant E.faecalis was increasing during the 7-year period.It is necessary to strengthen antimicrobial resistance surveillance to effectively identify the emergence of antibiotic-resistant bacteria and curb the spread of resistant pathogens.