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 investigate the preventive and therapeutic effects of the mfat-1 gene therapy on exper-imental autoimmune encephalomyelitis in mice.Meth-ods mfat-1 gene therapy was used to render the host endogenous capability of producing ω-3 PUFAs,con-comitantly reduce the levels of ω-6 PUFAs,and change the proportion of ω-3/ω-6 PUFAs.Then,the levels of PUFAs in blood were analyzed by gas chromatography.The neurological deficits in mice were evaluated by neurological dysfunction score.HE staining and LFB staining of mouse spinal cord slices were used to ob-serve central nervous system inflammation infiltration and demyelinating lesions.Flow cytometry microsphere microarray technology was used to detect the content of cytokines in serum.Results The mfat-1 gene therapy could significantly raise the proportion of ω-3/ω-6 PU-FAs(P＜0.05),markedly delay the incubation period and peak period and reduce neurological dysfunction scores(P＜0.05),and improve inflammation and de-myelination of spinal cords(P＜0.05).It could also greatly increase the levels of IL-2,IFN-γ,IL-4 and IL-17 in serum(P＜0.05).Conclusion The pro-portion of ω-3/ω-6 PUFAs in blood circulation en-hanced by mfat-1 gene therapy can effectively prevent and treat experimental autoimmune encephalomyelitis in mice.

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.

Objective:To investigate the effects of Xiongcan Yishen Formula(XYF)on ferroptosis in mouse TM3 Leydig cells after oxidative stress injury(OSI)induced by H2O2.Methods:An oxidative stress injury model was established in mouse TM3 Leydig cells using H2O2 induction.The modeled TM3 cells were randomly divided into OSI group,XYF group,the ferroptosis inhibitor Ferrostatin-1(F-1)group,and F-1+XYF group,which were respectively intervened with blank serum,20%drug-containing serum,2μmol/L F-1,and2μmol/L F-1+20%drug-containing serum.A control group(normal TM3 cells+blank serum)was also set up.The morphology of cells in each group was observed,and the levels of testosterone,superoxide dismutase(SOD),reactive oxygen spe-cies(ROS),malondialdehyde(MDA),ferritin heavy chain 1(FTH1),solute carrier family 7 member 11(SLC7A11),glutathione(GSH),glutathione peroxidase 4(GPX4),fatty acid CoA ligase 4(FACL4),total iron ions,and ferrous ions were detected.Re-sults:Compared with the model group,the control group showed significantly decreased expression of ROS,MDA,FACL4,total iron,and ferrous ions(P<0.05),and significantly increased levels of testosterone,SOD,GSH,FTH1,SLC7A11,and GPX4(P<0.05).The male silkworm kidney-tonifying formula group significantly promoted testosterone secretion by TM3 cells and upregulated the expression of FTH1,SLC7A11,GPX4,GSH,and SOD in TM3 cells(P<0.05),while significantly downregulating ROS,MDA,FACL4,total iron ions,and ferrous ions(P<0.05).Conclusion:Following H2O2 exposure,oxidative stress can induce ferroptosis in mouse TM3 Leydig cells.XYF can antagonize OSI and ferroptosis in TM3 cells by activating the SLC7A11/GSH/GPX4 axis,which may underlie the mechanism of XYF in the treatment of male late-onset hypogonadism.

Objective To investigate the clinical and genetic features of children with 3-methylcrotonyl-coenzyme A carboxylase deficiency(MCCD).Methods A retrospective analysis was conducted on the clinical manifestations and genetic testing results of six children with MCCD who attended Children's Hospital Affiliated to Zhengzhou University from January 2018 to October 2023.Results Among the six children with MCCD,there were 4 boys and 2 girls,with a mean age of 7 days at the time of attending the hospital and 45 days at the time of confirmed diagnosis.Of all children,one had abnormal urine odor and five had no clinical symptoms.All six children had increases in blood 3-hydroxyisovaleryl carnitine and urinary 3-hydroxyisovaleric acid and 3-methylcrotonoylglycine,and five of them had a reduction in free carnitine.A total of six mutations were identified in the MCCC1 gene,i.e.,c.1630del(p.R544Dfs*2),c.269A>G(p.D90G),c.1609T>A(p.F537I),c.639+2T>A,c.761+1G>T,and c.1331G>A(p.R444H),and three mutations were identified in the MCCC2 gene,i.e.,c.838G>T(p.D280Y),c.592C>T(p.Q198*,366),and c.1342G>A(p.G448A).Among these mutations,c.269A>G(p.D90G)and c.1609T>A(p.F537I)had not been previously reported in the literature.There was one case of maternal MCCD,and the child carried a heterozygous mutation from her mother.Five children with a reduction in free carnitine were given supplementation of L-carnitine,and free carnitine was restored to the normal level at the last follow-up visit.Conclusions This study identifies two new mutations,c.269A>G(p.D90G)and c.1609T>A(p.F537I),thereby expanding the mutation spectrum of the MCCC1 gene.A combination of blood amino acid and acylcarnitine profiles,urine organic acid analysis,and genetic testing can facilitate early diagnosis and treatment of MCCD,and provide essential data for genetic counseling.

Objective To investigate the distribution and antimicrobial susceptibility of clinically isolated bacteria from intensive care units(ICUs)in hospitals of Hunan Province Antimicrobial Resistance Surveillance System from 2012 to 2021.Methods According to China Antimicrobial Resistance Surveillance System,data of clinically isolated bacterial strains and antimicrobial susceptibility testing results of bacteria from ICUs reported by all member units of Hunan Province Antimicrobial Resistance Surveillance System were analyzed with WHONET 2022 software.Results From 2012 to 2021,the total number of bacteria isolated from ICUs of member units of the Hunan Province Antimi-crobial Resistance Surveillance System was 5 777-22 369,with Gram-negative bacteria accounting for 76.1％-78.0％annually.Staphylococcus aureus ranked first among isolated Gram-positive bacteria each year.The top 5 bacteria among Gram-negative bacteria were Acinetobacter baumannii,Klebsiella pneumoniae,Escherichia coli,Pseudo-monas aeruginosa,and Stenotrophomonas maltophilia.Detection rate of methicillin-resistant Staphylococcus aureus showed a downward trend year by year.No Staphylococcus spp.were found to be resistant to vancomycin,teico-planin and linezolid.Detection rates of vancomycin-resistant Enterococcus faecalis and vancomycin-resistant Entero-coccus faecium were 0.6-1.1％and 0.6％-2.2％,respectively.Resistance rates of Escherichia coli and Kleb-siella pneumoniae to imipenem were 3.1％-5.7％and 7.7％-20.9％,respectively.Resistance rates of Pseudo-monasaeruginosa and Acinetobacter baumannii to imipenem were 24.6％-40.1％and 76.1％-80.9％,respective-ly.Detection rates of carbapenem-resistant Pseudomonas aeruginosa declined year by year.Acinetobacter baumannii maintained high susceptibility to polymyxin B,with resistance rate＜10％.Conclusion Antimicrobial resistance of bacteria from ICUs is serious.Carbapenem-resistant Enterobacteriales has an upward trend after 2019.It is nece-ssary to strengthen the surveillance of bacterial resistance and carry out multidisciplinary collaboration.