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.

Background::Carotid intima-media thickness (IMT) and diameter, stiffness, and wave reflections, are independent and important clinical biomarkers and risk predictors for cardiovascular diseases. The purpose of the present study was to establish nationwide reference values of carotid properties for healthy Chinese adults and to explore potential clinical determinants.Methods::A total of 3053 healthy Han Chinese adults (1922 women) aged 18-79 years were enrolled at 28 collaborating tertiary centers throughout China between April 2021 and July 2022. The real-time tracking of common carotid artery walls was achieved by the radio frequency (RF) ultrasound system. The IMT, diameter, compliance coefficient, β stiffness, local pulse wave velocity (PWV), local systolic blood pressure, augmented pressure (AP), and augmentation index (AIx) were then automatically measured and reported. Data were stratified by age groups and sex. The relationships between age and carotid property parameters were analyzed by Jonckheere-Terpstra test and simple linear regressions. The major clinical determinants of carotid properties were identified by Pearson’s correlation, multiple linear regression, and analyses of covariance.Results::All the parameters of carotid properties demonstrated significantly age-related trajectories. Women showed thinner IMT, smaller carotid diameter, larger AP, and AIx than men. The β stiffness and PWV were significantly higher in men than women before forties, but the differences reversed after that. The increase rate of carotid IMT (5.5 μm/year in women and 5.8 μm/year in men) and diameter (0.03 mm/year in both men and women) were similar between men and women. For the stiffness and wave reflections, women showed significantly larger age-related variations than men as demonstrated by steeper regression slopes (all P for age by sex interaction <0.05). The blood pressures, body mass index (BMI), and triglyceride levels were identified as major clinical determinants of carotid properties with adjustment of age and sex. Conclusions::The age- and sex-specific reference values of carotid properties measured by RF ultrasound for healthy Chinese adults were established. The blood pressures, BMI, and triglyceride levels should be considered for clinical application of corresponding reference values.

Objective To screen the differentially expressed genes of lung metastasis of osteosarcoma by bioinformatics,and explore their functions and regulatory networks.Methods The data set of GSE14359 was screened from GEO database(http://www.ncbi.nlm.nih.gov/gds)and the differentially expressed gene(DEG)was identified using GEO2R online tool.Download osteosarcoma disease related miRNAs from the online HMMD database(http://www.cuilab.cn/hmdd)and then FunRich software was used to predict the target gene,intersects with DEG to obtains the target gene.The miRNA-mRNA rela-tionship pairs were formed according to the targeted joints,then the data was imported into Cytoscape for visualization,DAVID was used to performe GO and KEGG analysis on target genes,STRING was used to construct PPI network,Cytoscape visualiza-tion,CytoHubba plug-in screening central genes and online website for expression and survival analysis.Results Total 704 DEGs were identified,consisting of 477 up-regulated genes and 227 down regulated genes.FunRich predicted 7 888 mRNAs and 343 target genes were obtained through intersection of the two.KEGG analysis showed that it was mainly involved in focal adhesion,ECM receptor interaction,TNF signal pathway,PI3K-Akt signal pathway,IL-17 signal pathway and MAPK signal pathway.Ten central genes(CCNB1,CHEK1,AURKA,DTL,RRM2,MELK,CEP55,FEN1,KPNA2,TYMS)were identified as potential key genes.Among them,CCNB1,DTL,MELK were highly correlated with poor prognosis.Conclusion The key genes and functional pathways identified in this study may be helpful to understand the molecular mechanism of the occurrence and progression of lung metastases from osteosarcoma,and provide potential therapeutic targets.

Acute mitral regurgitation(MR)in the setting of myocardial infarction(MI)may be the result of papillary muscle rupture(PMR).The clinical presentation can be catastrophic,with refractory cardiogenic shock.This condition is associated with high morbidity and mortality.Transcatheter edge-to-edge repair(TEER)has become increasingly common in treating severe mitral regurgitation.This case details a successful TEER is feasible and safe in patients with acute MR following MI.TEER is an emerging treatment option in this clinical scenario that should be taken into consideration.

This study investigated the risk factors for treatment failure in patients with a single infection of Mycobacterium avium.Patients with Mycobacterium avium infection meeting the guidelines for diagnosis and treatment of non-tuberculous mycobacteriosis between January 2016 and December 2020 at Shanghai Pulmonary Hospital were included.A logistic regression model was used to analyze the risk factors for treatment failure.A total of 26(49％)of 53 patients with Mycobacterium avium infection included in the study had treatment failure.A higher proportion of patients with fever,anemia,and lung cavitation in the treatment failure group had significantly higher neutrophils and direct bilirubin,and significantly lower prealbumin.Multi-factorial logistic regression demonstrated that cavitation was an independent risk factor for treatment failure in patients with Mycobacterium avium infection,and Kaplan-Meier analysis indicated significantly lower cumulative 12-month cure rates in pa-tients with cavitation.Patients with Mycobacterium avium infection had a higher rate of treatment failure,and cavitation was found to be a risk factor for treatment failure.Our findings suggest that clinicians should pay attention to the monitoring and treatment of patients with Mycobacterium avium pulmonary cavities to improve the cure rate among patients.

Objective:To evaluate the efficacy of acute T-cell lymphoblastic leukemia(T-ALL)in children and explore the prognostic risk factors.Methods:The clinical data of 127 newly diagnosed children with T-ALL admitted to five hospitals in Fujian province from April 2011 to December 2020 were retrospectively analyzed,and compared with children with newly diagnosed acute precursor B-cell lymphoblastic leukemia(B-ALL)in the same period.Kaplan-Meier analysis was used to evaluate the overall survival(OS)and event-free survival(EFS),and COX proportional hazard regression model was used to evaluate the prognostic factors.Among 116 children with T-ALL who received standard treatment,78 cases received the Chinese Childhood Leukemia Collaborative Group(CCLG)-ALL 2008 protocol(CCLG-ALL 2008 group),and 38 cases received the China Childhood Cancer Collaborative Group(CCCG)-ALL 2015 protocol(CCCG-ALL 2015 group).The efficacy and serious adverse event(SAE)incidence of the two groups were compared.Results:Proportion of male,age ≥ 10 years old,white blood cell count(WBC)≥ 50 × 109/L,central nervous system leukemia,minimal residual disease(MRD)≥ 1％during induction therapy,and MRD ≥ 0.01％at the end of induction in T-ALL children were significantly higher than those in B-ALL children(P＜0.05).The expected 10-year EFS and OS of T-ALL were 59.7％and 66.0％,respectively,which were significantly lower than those of B-ALL(P＜0.001).COX analysis showed that WBC ≥ 100 x 109/L at initial diagnosis and failure to achieve complete remission(CR)after induction were independent risk factors for poor prognosis.Compared with CCLG-ALL 2008 group,CCCG-ALL 2015 group had lower incidence of infection-related SAE(15.8％vs 34.6％,P=0.042),but higher EFS and OS(73.9％vs 57.2％,PEFS=0.090;86.5％vs 62.3％,PoS=0.023).Conclusions:The prognosis of children with T-ALL is worse than children with B-ALL.WBC ≥ 100 × 109/L at initial diagnosis and non-CR after induction(especially mediastinal mass has not disappeared)are the risk factors for poor prognosis.CCCG-ALL 2015 regimen may reduce infection-related SAE and improve efficacy.