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 standardize the bacterial endotoxin testing criteria for zoledronic acid injection and estab-lish a detection method using recombinant factor C(rFC).Methods:The gel-clot method(BET)was utilized to test 13 batches of zoledronic acid injection from national supervision and random inspection.Interference tests were conducted on zoledronic acid injections from three manufacturers at different concentrations(500,100,50,25 μg·mL-1)using rFC test kits from two manufacturers.Results:Detection was performed for the specification of 100 mL∶5 mg and other specifications according to＜0.50 EU per 1 mL and＜5.0 EU per 1 mg,respectively,and all results met the criteria.The recovery rate for 25 μg·mL-1 using rFC kits from both manufacturers ranged between 50％and 200％.Validation of rFC.Methods:Eight batches of zoledronic acid injection were validated at 25 μg·mL-1,five batches of zoledronic acid injection(100 mL∶5 mg)were validated at 0.5 EU·mL-1,and all recovery rates were between 50％and 200％.Conclusion:The bacterial endotoxin testing method for zoledronic acid injection can be established as follows:for large volume injection products with 100 mL or more,each 1 mL should contain less than 0.50 EU of endotoxin(following the Chinese Pharmacopoeia 2020,general chapter 1143).For other specifications,each 1 mg of zoledronic acid should contain less than 10.0 EU of endotoxin.The rFC test kit method for bacterial endotoxins involved diluting the sample with water for bacterial endotoxin testing to contain 25 μg of zoledronic acid per 1 mL,or performing 1∶1 dilution for large volume injections(100 mL∶5.0 mg specifi-cation),with recovery rate between 50％and 200％as per the kit instructions.

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.

This experiment was conducted to investigate the effects of agaric polysaccharides on an-tioxidant capacity,immune function,and intestinal flora of calves.Twenty-four healthy Holstein calves of(30±3)days of age and with the similar body weight at(55.33±1.86)kg were selected and randomly divided into two groups:the control group(group C)and test group(group T)with 12 replicates in each group and one calves in each replicate.Group C was fed starter and milk repla-cer,and group T was fed starter and milk replacer with 10 g of agaric polysaccharides to each calve for 10 d.Serum antioxidant,immune indexes and intestinal flora were tested.The results showed as follows:compared with group C,the enzyme activities of SOD and GSH-Px in serum of calves in group T were significantly increased(P＜0.05),and were increased by 29.09％and 15.35％,re-spectively;compared with group C,IgA,IL-2 and TNF-α were significantly increased in T group(P＜0.05).Adding agaric polysaccharides significantly increased the relative abundance of Firmi-cutes(P＜0.05)and decreased the relative abundance of Proteobacteria in feces of calf(P＞0.05);the relative abundance of Lactobalillus and Faecalibacterium were increased(P＜0.05);the relative abundance of Butyricoccus-pullicaecorum was increased(P＜0.05).LEfSe analysis results showed that there were 11 marker species in group T,such as Firmicutes and Lactobacillus,and 9 marker species in group C,such as Proteobacteria.The results showed that agaric polysaccharides could improve the antioxidant capacity and immune function of calves,and also could improve the structure of intestinal flora.

Objective:To explore the efficacy and safety of haploidentical hematopoietic stem cell transplantation combined with umbilical cord blood infusion for the treatment of aplastic anaemia in children.Methods:Nine cases of children with aplastic anaemia treated with umbilical cord blood combined with haploidentical hematopoietic stem cell transplantation at the People's Hospital of Henan University of Chinese Medicine from January 1,2021 to September 15,2023 with a median age of 11(2-13)years and a median follow up of 18(7.5-21)months were included,and the clinical data were retrospectively analyzed.Hematopoiesis reconstitution,the incidence of graft-versus-host disease(GVHD),infections and survival of the patients were analyzed.Results:All 9 children were successfully implanted.The median time to neutrophil and platelet implantation was 11.11±1.27 d and 12.44±3.36 d,respectively.One case developed acute gastrointestinal GVHD of degree I,which was improved after treatment,and the patient developed superficial gastritis and chronic gastrointestinal GVHD at a later stage,which is currently under clinical follow-up.Acute GVHD of Ⅱ-Ⅳ degree was 0％.Hemorrhagic cystitis in 3 cases,CMV infection in 5 cases and bacterial and fungal infections in 5 cases improved with symptomatic treatment.All 9 children demonstrated complete donor chimerism within 1 month after transplantation,at two years of follow-up,all nine children survived without recurrence or development of grade Ⅱ-Ⅳ GVHD,and there were no children with transplant-related deaths.Conclusion:Haploidentical hematopoietic stem cell transplantation combined with umbilical cord blood transfusion for aplastic anaemia in children has a low incidence and mild degree of GVHD,with significant efficacy,and can be used as a therapeutic option for children without an HLA full donor chimeric match.

Objective:To investigate the clinical and genetic characteristics of a male carrier of exceptional complex chromo-some rearrangement(CCR)and the outcome of preimplantation genetic testing for chromosomal structural rearrangement(PGT-SR).Methods:Using the modified high resolution G banding technique and whole-genome low-coverage sequencing(WGLCS),we analyzed the cellular karyotype and molecular karyotype of a male carrier of CCR,performed an analysis of the single-sperm chromosome copy number and conducted PGT-SR for the patient by next-generation sequencing(NGS).In addition,we reviewed the literature on repor-ted male carriers of CCRs and summarized their normal/balanced sperm ratios and PGT-SR outcomes.Results:The karyotype of the patient was 46,XY,der(5)inv(5)(q14.3q23.2)t(5;14;11)(q23.2;q31.1;q21),der(11)t(5;14;11);der(14)t(5;14;11),with the translocation breakpoints located in the intergenic region.Single-sperm sequencing revealed 20.0%(7/35)of normal haploids in the male's spermatozoa,and the results PGT-SR showed a proportion of 25.0%(4/16)of normal/balanced embryos.After thawing and transferring of 2 euploid blastocysts,a healthy male infant was successfully delivered.Conclusion:The proportion of normal hap-loids in the spermatozoa of male CCR carriers may be higher than theoretically predicted,and PGT-SR can effectively improve the preg-nancy outcome in male CCR carriers and provide valuable data for genetic counseling.