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.

Objective:To investigate the application effect of situational simulation combined with the Debriefing-GAS method in the teaching of prenatal genetic counseling.Methods:A total of 30 medical students of the five- and eight-year programs in the classes of 2017 and 2018 who received genetic counseling training in The First Affiliated Hospital of Sun Yat-sen University from May 2021 to May 2022 were selected as research subjects, and situational simulation combined with the debriefing-GAS method was used for the teaching of prenatal genetic counseling. Assessment was performed by the teacher to evaluate the change in genetic counseling abilities during the teaching process, and a questionnaire survey was conducted to investigate the degree of satisfaction with teaching among the students. SPSS 26.0 software was used for data analysis; normally distributed continuous data were expressed as mean±standard deviation, non-normally distributed continuous data were expressed as M d(P 25,P75), and categorical data were expressed as frequency and rate; the paired samples t-test was used for comparison of assessment scores before and after teaching. Results:After teaching, there were significant increases in the assessment scores of genetic counseling [(74.5±18.6) points vs. (87.2±14.5) points, t=4.10, P<0.001] and comprehensive abilities such as clinical ability [(35.4±9.6) points vs. (41.1±6.9) points, t=3.72, P=0.001], doctor-patient communication [(17.5±4.6) points vs. (20.8±3.8) points, t=4.34, P<0.001], professional literacy [(11.0±2.5) points vs. (12.5±2.3) points, t=2.89, P=0.007], teamwork [(3.5±1.0) points vs. (4.2±0.8) points, t=3.67, P=0.001], and organizational effectiveness [(7.1±2.0) points vs. (8.3±1.7) points, t=2.94, P=0.006]. The questionnaire survey showed that the degree of satisfaction among students was rated above satisfaction for the reasonability of the implementation process and links of genetic counseling teaching [3.0 (3.0, 4.0) points], teaching quality [3.5 (3.0, 4.0) points], whether the teaching model could effectively increase the interest and initiative in learning [4.0 (3.0, 4.0) points], the improvement in theoretical knowledge [4.0 (3.0, 4.0) points], communication skills in genetic counseling [3.0 (3.0, 4.0) points], and the understanding of related techniques and application prospect [3.0 (3.0, 4.0) points]. However, two students (6.7%) thought that this teaching model could not efficiently reach teaching objectives, since the teaching process was slightly complicated. Conclusions:Situational simulation combined with the debriefing-GAS method has achieved a good effect in the teaching of prenatal genetic counseling and can help undergraduates to master the theoretical knowledge of prenatal genetic counseling and improve their comprehensive clinical abilities, with a relatively high degree of satisfaction, and therefore, it holds promise for clinical application.

Aim To explore how Danzhi Jiangtang cap-sules(DJC)safeguard the mitochondrial activity of vascular smooth muscle cells(VSMCs)by controlling the LncRNA TUG1/β-catenin signaling pathway to de-crease vascular calcification(VC).Methods Vascu-lar smooth muscle cell calcification models were in-duced with β-glycerin and diabetic vascular calcifica-tion rat models were induced with vitamin D3+high-fat diet.Von Kossa staining was applied to detect cal-cification of cells and vascular tissue.Colorimetric method of phthalein complex was used to determine calcium content.P-nitrobenzene phosphate colorimetry was employed to assess alkaline phosphatase(ALP)activity.RT-qPCR was used to analyze the expression of VSMCs'osteoblast transformation related genes bone morphogenetic protein2(BMP2),smooth muscle actin alpha(α-SMA),taurine up-regulated1,LncRNA Tug1(Lnc-RNA TUG1),and β-catenin.Western blotting was utilized to detect the protein expression of BMP2,α-SMA and β-catenin.The mitochondrial membrane potential was detected by JC-1 fluorescence probe.Mitochondrial structure was observed by trans-mission electron microscope.Results DJC reduced LncRNA TUG1 expression,down-regulated β-catenin expression,decreased ALP activity and calcium depo-sition,protected mitochondrial function,restored mem-brane potential,and decreased osteoblastic transforma-tion of VSMCs induced by glycerin phosphate.Impor-tantly,DJC attenuated diabetic lower limb VC by down-regulating the expression of LncRNA TUG1,β-catenin,and elevating the expression of α-SMA.Con-clusions DJC capsules significantly improved VSMCs by protecting mitochondrial function by LncRNA TUG1/β-catenin signaling to reduce VSMCs'osteo-blast transformation.

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.

Aim To study the regulatory effect of poly-datin on D-galactose-induced aging model mice.Methods Fifty-six ICR mice(half male and half fe-male)were divided into normal group,model group,positive group,low,medium and high polydatin treat-ment groups.Aging model was established by subcuta-neous injection of D-galactose(500 mg·kg-1)into the back of neck every day.During the modeling peri-od,the positive group was given donepezil hydrochlo-ride tablets(0.75 mg·kg-1)by gavage,the treat-ment group was given polydatin(40,70,100 mg·kg1)by gavage,and the normal group was given the same amount of normal saline.The learning and cogni-tive ability of mice was evaluated by nesting experi-ment,new object recognition experiment and Morris water maze experiment.The heart,liver,spleen,kid-ney and thymus of mice were taken to calculate the or-gan index.The pathological changes of whole brain tis-sue in mice were observed by hematoxylin-eosin(HE)staining.The levels of T-SOD,MDA,GSH-Px and AchE in serum and whole brain tissue of mice were de-tected by ELISA.The protein expression levels of Keap1,Nrf2 and HO-1 in hippocampus of mice were detected by Western blot.Results Compared with the model group,the nesting ability,the ability to recog-nize new objects and the ability to find platforms under-water of the mice in the positive group and the low,medium and high dose groups of polydatin were im-proved.The organ index increased.The neuronal dam-age in the cerebral cortex and hippocampus was signifi-cantly ameliorated.The activities of T-SOD and GSH-Px in serum and brain tissue increased and the activi-ties of MDA and AchE decreased.The expression lev-els of Nrf2 and HO-1 protein in hippocampus in-creased,and the expression level of Keap1 protein de-creased.Conclusions Polydatin can ameliorate the learning and cognitive impairment in D-galactose-in-duced aging model mice,and its mechanism may be related to the Keap1/Nrf2/HO-1 pathway.