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 expression and prognostic value of spindle and kinetochore-associated complex subunit 2(SKA2)in cervical cancer tissues,as well as its impact on the proliferation,migration and invasion of cervical cancer cells.Methods The expression of SKA2 in cervical cancer tissues was analyzed by bioinformatics database and immunohistochemical SP method,and the relationship between SKA2 expression level and clinicopathological features of cervical cancer patients and its prognostic value was analyzed.The mRNA expression of SKA2 in human normal cervical cells(HcerEpic)and cervical cancer cells(HeLa,SiHa,CaSki,C-33A)was detected by RT-qPCR.Cervical cancer cells SiHa with higher SKA2 expression level was selected for further study.SiHa cell model with down-regulated SKA2 expression was constructed,and its knockdown effect was verified.Cell proliferation capacity was detected by CCK-8 method,cell migration capacity was detected by cell scratch wound healing assay,and cell migration and invasion capacity was detected by Transwell assay.Results Compared with normal cervical tissues and cells,the expression levels of SKA2 mRNA and protein were higher in cervical cancer tissues and cells,and the differences were statistically significant(P<0.05).High SKA2 expression was associated with FIGO staging in patients with cervical cancer.Furthermore,SKA2 knockdown could inhibit the proliferation,migration and invasion of SiHa cells in cervical cancer(P<0.05).Conclusion SKA2 is up-regulated in cervical cancer tissues and cells,and can promote the proliferation,migration and invasion of cervical cancer cells.The expression level of SKA2 is associated with the progression of cervical cancer,and the prognosis of cervical cancer patients with high SKA2 expression is worse.

Objective:To carry out the policy diffusion analysis of centralized and volume-based drug procurement in China in recent years,and to provide reference for the formulation of centralized and volume-based drug procurement policy.Methods:Through the official websites of the central and provincial governments,the official websites of the Health Commission and the official websites of the Medical Security Bureau,the policy documents related to centralized and volume-based drug procurement from January 1,2009 to December 31,2023 were searched.Based on the policy diffusion theory,the reference network analysis method is used to analyze the intensity,breadth and speed of policy diffusion,and the sequential analysis method of policy keywords is used to analyze the direction of policy diffusion.Results:In the two stages of the development of centralized and volume-based drug procurement policy,the number of policies issued in the medical insurance management stage reached the peak;The top ten policies with the highest diffusion intensity and breadth are all central policies,and most of them are notices and opinions.In addition,the newly promulgated policies have a faster diffusion speed.In the direction of diffusion,top-down and parallel diffusion trends are obvious.Conclusion:The diffusion of centralized and volume-based drug procurement policy in China focuses on the central policy,and the diffusion speed is increasing year by year.It is suggested to strengthen the policy coordination between the central and local governments,establish a unified national information platform for centralized drug procurement,optimize the learning and competition mechanism between governments at all levels,and give play to the advantages of"policy experiment".

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.

Objective:To investigate the surgical situations and perioperative outcome of pancreaticoduodenectomy in Jiangsu Province and the influencing factors for postoperative 90-day mortality.Methods:The retrospective case-control study was conducted. The clinicopathological data of 2 886 patients who underwent pancreaticoduodenectomy in 21 large tertiary hospitals of Jiangsu Quality Control Center for Pancreatic Diseases, including The First Affiliated Hospital of Nanjing Medical University, from March 2021 to December 2022 were collected. There were 1 732 males and 1 154 females, aged 65(57,71)years. Under the framework of the Jiangsu Provincial Pancreatic Disease Quality Control Project, the Jiangsu Quality Control Center for Pancreatic Diseases adopted a multi-center registration research method to establish a provincial electronic database for pancrea-ticoduodenectomy. Observation indicators: (1) clinical characteristics; (2) intraoperative and post-operative conditions; (3) influencing factors for 90-day mortality after pancreaticoduodenectomy. Measurement data with skewed distribution were represented as M( Q1, Q3) or M(IQR), and comparison between groups was conducted using the Mann-Whitney U test. Count data were expressed as absolute numbers or constituent ratio, and comparison between groups was conducted using the chi-square test, continuity correction chi-square test and Fisher exact probability. Maximal Youden index method was used to determine the cutoff value of continuous variables. Univariate analysis was performed using the corresponding statistical methods based on data types. Multivariate analysis was performed using the Logistic multiple regression model. Results:(1) Clinical characteristics. Of the 2 886 patients who underwent pancreaticoduodenectomy, there were 1 175 and 1 711 cases in 2021 and 2022, respectively. Of the 21 hospitals, 8 hospitals had an average annual surgical volume of <36 cases for pancreaticoduodenectomy, 10 hospitals had an average annual surgical volume of 36-119 cases, and 3 hospitals had an average annual surgical volume of ≥120 cases. There were 2 584 cases performed pancreaticoduodenectomy in thirteen hospitals with an average annual surgical volume of ≥36 cases, accounting for 89.536%(2 584/2 886)of the total cases. There were 1 357 cases performed pancrea-ticoduodenectomy in three hospitals with an average annual surgical volume of ≥120 cases, accounting for 47.020%(1 357/2 886) of the total cases. (2) Intraoperative and postoperative conditions. Of the 2 886 patients, the surgical approach was open surgery in 2 397 cases, minimally invasive surgery in 488 cases, and it is unknown in 1 case. The pylorus was preserved in 871 cases, not preserved in 1 952 cases, and it is unknown in 63 cases. Combined organ resection was performed in 305 cases (including vascular resection in 209 cases), not combined organ resection in 2 579 cases, and it is unknown in 2 cases. The operation time of 2 885 patients was 290(115)minutes, the volume of intra-operative blood loss of 2 882 patients was 240(250)mL, and the intraoperative blood transfusion rate of 2 880 patients was 27.153%(782/2 880). Of the 2 886 patients, the invasive treatment rate was 11.342%(327/2 883), the unplanned Intensive Care Unit (ICU) treatment rate was 3.087%(89/2 883), the reoperation rate was 1.590%(45/2 830), the duration of postoperative hospital stay was 17(11)days, the hospitalization mortality rate was 0.798%(23/2 882), and the failure rate of rescue data in 2 083 cases with severe complications was 6.529%(19/291). There were 2 477 patients receiving postoperative 90-day follow-up, with the 90-day mortality of 2.705%(67/2477). The total incidence rate of complication in 2 886 patients was 58.997%(1 423/2 412). The incidence rate of severe complication was 13.970%(291/2 083). The comprehensive complication index was 8.7(22.6) in 2 078 patients. (3) Influencing factors for 90-day mortality after pancreaticoduodenectomy. Results of multivariate analysis showed that age ≥ 70 years, postoperative invasive treatment, and unplanned ICU treatment were independent risk factors for 90-day mortality after pancreaticoduodenectomy ( odds ratio=2.403, 2.609, 16.141, 95% confidence interval as 1.281-4.510, 1.298-5.244, 7.119-36.596, P<0.05). Average annual surgical volume ≥36 cases in the hospital was an independent protective factor for 90-day mortality after pancreaticoduodenectomy ( odds ratio=0.368, 95% confidence interval as 0.168-0.808, P<0.05). Conclusions:Pancreaticoduodenectomy in Jiangsu Province is highly con-centrated in some hospitals, with a high incidence of postoperative complications, and the risk of postoperative 90-day mortality is significant higher than that of hospitallization mortality. Age ≥ 70 years, postoperative invasive treatment, and unplanned ICU treatment are independent risk factors for 90-day motality after pancreaticoduodenectomy, and average annual surgical volume ≥36 cases in the hospital is an independent protective factor.