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.

In the past few decades,supercritical fluid chromatography(SFC)as a supplement to liquid chromatography(LC)separation technology has attracted people's interest,especially in the combination of SFC and mass spectrometry(MS),which has shown important application prospects in metabolomics,lipidomics,and other fields.Compared to the interface of LC-MS,the interface of SFC-MS presents some unique challenges that require special solutions to be designed.This article categorizes and summarizes the existing interfaces used for SFC-MS,focuses on the impact of different interface designs on detection performance,provides the applicable characteristics of different types of interfaces,and finally briefly introduces the application progress of SFC-MS in different fields.

Objective To evaluate and compare the success rate and short-term clinical prognosis of transfemoral transcatheter aortic valve replacement(TF-TAVR)for patients with pure aortic regurgitation(PAR)of different annulus sizes.Methods This study is a single center retrospective study,selecting symptomatic PAR patients who received TF-TAVR treatment at Zhongshan Hospital Fudan University from September 2019 to September 2023.Based on preoperative CT results,all patients were divided into three groups:Group A(aortic annulus circumference＜80 mm),Group B(80 mm≤aortic annulus circumference＜85 mm),and Group C(aortic annulus circumference≥ 85 mm).The primary endpoint was success rate and 30d all-cause mortality,while the secondary endpoint was TAVR related complications.Results A total of 61 PAR patients were included in this study,including 27 in Group A,21 in Group B,and 13 in Group C.The overall success rate is 82.0％,and the 30 d all-cause mortality rate is 3.3％.The success rate of Group C patients was significantly lower(P=0.012),with higher rates of conversion to surgery and valve-in-valve implantation(P=0.022 and P=0.040).In terms of secondary endpoint events,there were no significant differences among the three groups in major bleeding events,major vascular complications,stroke,myocardial infarction,newly developed atrial fibrillation,implantation of new pacemakers,coronary artery occlusion,and postoperative moderate to severe perivalvular leakage(all P＞0.05).Conclusions The circumference of the aortic valve annulus is a key factor affecting the success rate of TF-TAVR in PAR,and PAR patients with an aortic valve annulus circumference less than 85mm may be more suitable for TF-TAVR.

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.

Objective To examine the changing antimicrobial resistance profile of Enterobacter spp.isolates in 53 hospitals across China from 2015 t0 2021.Methods The clinical isolates of Enterobacter spp.were collected from 53 hospitals across China during 2015-2021 and tested for antimicrobial susceptibility using Kirby-Bauer method or automated testing systems according to the CHINET unified protocol.The results were interpreted according to the breakpoints issued by the Clinical & Laboratory Standards Institute(CLSI)in 2021(M100 31st edition)and analyzed with WHONET 5.6 software.Results A total of 37 966 Enterobacter strains were isolated from 2015 to 2021.The proportion of Enterobacter isolates among all clinical isolates showed a fluctuating trend over the 7-year period,overall 2.5％in all clinical isolates amd 5.7％in Enterobacterale strains.The most frequently isolated Enterobacter species was Enterobacter cloacae,accounting for 93.7％(35 571/37 966).The strains were mainly isolated from respiratory specimens(44.4±4.6)％,followed by secretions/pus(16.4±2.3)％and urine(16.0±0.9)％.The strains from respiratory samples decreased slightly,while those from sterile body fluids increased over the 7-year period.The Enterobacter strains were mainly isolated from inpatients(92.9％),and only(7.1±0.8)％of the strains were isolated from outpatients and emergency patients.The patients in surgical wards contributed the highest number of isolates(24.4±2.9)％compared to the inpatients in any other departement.Overall,≤ 7.9％of the E.cloacae strains were resistant to amikacin,tigecycline,polymyxin B,imipenem or meropenem,while ≤5.6％of the Enterobacter asburiae strains were resistant to these antimicrobial agents.E.asburiae showed higher resistance rate to polymyxin B than E.cloacae(19.7％vs 3.9％).Overall,≤8.1％of the Enterobacter gergoviae strains were resistant to tigecycline,amikacin,meropenem,or imipenem,while 10.5％of these strains were resistant to polycolistin B.The overall prevalence of carbapenem-resistant Enterobacter was 10.0％over the 7-year period,but showing an upward trend.The resistance profiles of Enterobacter isolates varied with the department from which they were isolated and whether the patient is an adult or a child.The prevalence of carbapenem-resistant E.cloacae was the highest in the E.cloacae isolates from ICU patients.Conclusions The results of the CHINET Antimicrobial Resistance Surveillance Program indicate that the proportion of Enterobacter strains in all clinical isolates fluctuates slightly over the 7-year period from 2015 to 2021.The Enterobacter strains showed increasing resistance to multiple antimicrobial drugs,especially carbapenems over the 7-year period.