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 clarify the risk factors of diaphragmatic dysfunction (DD) after cardiac surgery with extracorporeal circulation. Methods A retrospective analysis was conducted on the data of patients who underwent cardiac surgery with extracorporeal circulation in the Department of Cardiovascular Surgery of Peking University People's Hospital from January 2023 to March 2024. Patients were divided into two groups according to the results of bedside diaphragm ultrasound: a DD group and a control group. The preoperative, intraoperative, and postoperative indicators of the patients were compared and analyzed, and independent risk factors for DD were screened using multivariate logistic regression analysis. Results A total of 281 patients were included, with 32 patients in the DD group, including 23 males and 9 females, with an average age of (64.0±13.5) years. There were 249 patients in the control group, including 189 males and 60 females, with an average age of (58.0±11.2) years. The body mass index of the DD group was lower than that of the control group [(18.4±1.5) kg/m2 vs. (21.9±1.8) kg/m2, P=0.004], and the prevalence of hypertension, chronic obstructive pulmonary disease, heart failure, and renal insufficiency was higher in the DD group (P<0.05). There was no statistical difference in intraoperative indicators (operation method, extracorporeal circulation time, aortic clamping time, and intraoperative nasopharyngeal temperature) between the two groups (P>0.05). In terms of postoperative aspects, the peak postoperative blood glucose in the DD group was significantly higher than that in the control group (P=0.001), and the proportion of patients requiring continuous renal replacement therapy was significantly higher than that in the control group (P=0.001). The postoperative reintubation rate, tracheotomy rate, mechanical ventilation time, and intensive care unit stay time in the DD group were higher or longer than those in the control group (P<0.05). Multivariate logistic regression analysis showed that low body mass index [OR=0.72, 95%CI (0.41, 0.88), P=0.011], preoperative dialysis [OR=2.51, 95%CI (1.89, 4.14), P=0.027], low left ventricular ejection fraction [OR=0.88, 95%CI (0.71, 0.93), P=0.046], and postoperative hyperglycemia [OR=3.27, 95%CI (2.58, 5.32), P=0.009] were independent risk factors for DD. Conclusion The incidence of DD is relatively high after cardiac surgery, and low body mass index, preoperative renal insufficiency requiring dialysis, low left ventricular ejection fraction, and postoperative hyperglycemia are risk factors for DD.

Aim To study the effect of emetine on in-sulin secretion through glucagon-like peptide-1 receptor(GLP-1R).Methods Isolating rat islets were used to carry out insulin secretion experiment.Islets were incubated with different concentrations of emetine(2,10,50 μmol·L-1),different concentrations of glu-cose solution(2.8,11.1,16.7 mmol·L-1)or spe-cific GLP-1R antagonist Exendin(9-39).The amount of insulin secretion in the supernatant of each group was determined by an enzyme-linked radioimmunoas-say.Small molecule compounds were docked to GLP-1R(PDB code:5NX2)using SYBYL-X2.0 software.Results Emetine could promote insulin secretion in high glucose(11.1 mmol·L-1)in a dose-dependent manner.In low glucose(2.8 mmol·L-1),insulin secretion did not change after intervention of emetine.But in high glucose(11.1,16.7 mmol·L-1),insu-lin secretion significantly increased under the treatment of emetine in a glucose-dependent manner.The doc-king score of emetine and GLP-1R was Total Score=6.82,C Score=5,indicating that emetine had a good binding affinity with GLP-1R.Using Exendin(9-39)to block GLP-1R,the insulinotropic effect of emetine was reduced.Conclusion Emetine could promote in-sulin secretion,which is related to the activation of GLP-1R.

Objective:RS4;11 cell line was used to establish BCL-2 inhibitor-resistant cell lines of B-cell acute lymphoblastic leukemia(B-ALL)and explore the possible mechanisms of drug resistance.Methods:RS4;11 cell line was continuously induced and cultured by low and ascending concentrations of BCL-2 inhibitors navitoclax and venetoclax to construct navitoclax-resistant cell line RS4;11/Nav and venetoclax-resistant cell line RS4;11/Ven.The cell viability was detected by MTT assay,and the cell apoptosis was detected by flow cytometry.Differentially expressed genes(DEGs)between RS4;11 drug-resistant cell lines and parental cell line were detected by transcriptome sequencing technology(RNA-seq),and mRNA expression levels of DEGs between drug-resistant cell lines and parental cell line were detected by real-time PCR(RT-PCR).Western blot was used to detect the expression levels of BCL-2 family anti-apoptotic proteins in drug-resistant cell lines and parental cell line.Results:The drug-resistant cell lines RS4;11/Nav and RS4;11/Ven were successfully established.The resistance index(RI)of RS4;11/Nav to navitoclax and RS4;11/Ven to venetoclax was 328.655±47.377 and 2 894.027±300.311,respectively.The results of cell apoptosis detection showed that compared with the drug-resistant cell lines,RS4;11 parental cell line were significantly inhibited by BCL-2 inhibitors,while the apoptosis rate of drug-resistant cell lines was not affected by the drugs.Western blot assay showed that the expression of anti-apoptotic proteins of BCL-2 family did not increase significantly in drug-resistant cell lines.RNA-seq,RT-PCR and Western blot assays showed that the expression of EP300 in drug-resistant cell lines was significantly higher than that in parental cell line(P＜0.05).Conclusion:Drug-resistant B-ALL cell lines could be successfully established by exposing RS4;11 cell line to the ascending concentration of BCL-2 inhibitors,and the drug resistance mechanism may be related to the overexpression of EP300.

Objective:To explore the potential action mechanism of Huotu Jiji Pellets(HJP)in the treatment of erectile dys-function(ED)based on network pharmacology and molecular docking.Methods:We identified the main effective compounds and active molecular targets of HJP from the database of Traditional Chinese Medicine Systems Pharmacology(TCMSP)and Integrative Pharmacology-Based Research Platform of Traditional Chinese Medicine(TCMIP)and the therapeutic target genes of ED from the data-bases of Genecards.Then we obtained the common targets of HJP and ED using the Venny software,constructed a protein-protein in-teraction(PPI)network of HJP acting on ED,and screened out the core targets with the Cytoscape software.Lastly we performed GO functional enrichment and KEGG pathway enrichment analyses of the core targets followed by molecular docking of HJP and the core targets using Chem3D and AutoDock Tools and QuickVina-W software.Results:A total of 64 effective compounds,822 drug-related targets,1 783 disease-related targets and 320 common targets were obtained in this study.PPI network analysis showed that the core targets of HJP for ED included ESR1,HSP90AA1,SRC,and STAT3.GO functional enrichment analysis indicated the involvement of the core targets in such biological processes as response to xenobiotic stimulus,positive regulation of kinase activity,and positive regu-lation of MAPK cascade.KEGG pathway enrichment analysis suggested that PI3K-Akt,apoptosis,MAPK,HIF-1,VEGF,autophagy and other signaling pathways may be related to the mechanism of HJP acting on ED.Molecular docking prediction exhibited a good doc-king activity of the key active molecules of HJP with the core targets.Conclusion:This study showed that HJP acted on ED through multi-components,multi-targets and multi-pathways,which has provided some evidence and reference for the clinical treatment and subsequent studies of the disease.

AIM To investigate the effects of Zuogui Jiangtang Tongmai Recipe on necroptosis pathway in a rat model of type 2 diabetes mellitus(T2DM)complicated with cerebral infarction(CI).METHODS The SD rats were randomly divided into the sham operation group,the model group,the metformin group(0.045 g/kg),and the low,medium and high dose Zuogui Jiangtang Tongmai Recipe groups(6.5,13,26 g/kg),with 9 rats in each group.In contrast to rats of the sham operation group,rats of the other groups were given 4 weeks feeding of high-sugar and high-fat diet combined with intraperitoneal injection of streptozotocin to establish a T2DM rat model with one week stable blood glucose,followed by gavage of corresponding drugs 3 days before the establishment of the middle cerebral artery occlusion(MCAO)model.After 7 days of administration,the rats had their CI injury assessed by mNSS method and TTC staining;their level of blood glucose detected by blood glucose meter;their levels of glycated serum protein,serum TNF-α and IL-1β detected by ELISA;their cerebral mRNA expressions of FADD,RIPK1,RIPK3 and MLKL detected by RT-qPCR;and their cerebral protein expressions of FADD,p-RIPK1,p-RIPK3 and p-MLKL detected by Western blot.RESULTS Compared with the sham operation group,the model group displayed increased levels of blood glucose value,glycosylated serum protein,neurological function score,cerebral infarction volume,cerebral FADD,RIPK1,RIPK3 and MLKL mRNA expressions,cerebral FADD,p-RIPK1,p-RIPK3 and p-MLKL protein expressions,serum TNF-α and IL-1β levels(P＜0.01);and more disordered and morphologically diverse neurons with smaller nucleus.Compared with the model group,the groups intervened with medium or high dose Zuogui Jiangtang Tongmai Recipe,or metformin shared improvement in terms of the aforementioned indices(P＜0.05,P＜0.01);and more neurons with regular morphology neat arrangement,and reduced cell gap.CONCLUSION Zuogui Jiangtang Tongmai Recipe can improve the neurological dysfunction of the rat model of T2DM complicated with CI,which may associate with the inhibited activation of necroptosis signaling pathway.