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.

Through consulting herbal medicine， medical books， and local chronicles from past dynasties to modern times， this paper systematically researched Spatholobi Caulis from name， origin， producing areas， harvesting， processing， usage， quality evaluation， functions and indications， providing a reference for the development and utilization of famous classical formulas containing Spatholobi Caulis. According to the research， Spatholobi Caulis was first recorded in the Annals of Shunning Prefecture from the Qing dynasty. It was originally a medicinal herb commonly used in Shunning， Yunnan， and was named from the red juice resembling chicken blood that flowed out after the vein was cut off. The mainstream original plants of each dynasty were Kadsura heteroclita and Spatholobus suberectus. Among them， K. heteroclita mainly focused on dispersing blood stasis and unblocking meridians， mainly treating rheumatic pain and injuries caused by falls or blows， and it is mostly used as the raw material of Jixueteng ointments. S. suberectus was commonly used as decoction pieces in decoction， which had the functions of promoting blood circulation and replenishing blood， activating meridians and collaterals， and mainly used for treating anemia， irregular menstruation， and rheumatic bone pain. The production area of Spatholobi Caulis recorded in the Qing dynasty was Yunnan. Currently， the main production area of S. suberectus is Guangxi， while the main production area of K. interior is Yunnan. In the Qing dynasty， the usage of Spatholobi Caulis was an individual prescription with other herbs before making ointments， which was usually composed of the juice of it， safflower， angelica， and glutinous rice. But in modern times， Spatholobi Caulis is mostly sliced and dried for use. The quality of Spatholobi Caulis is often determined by the number of reddish-brown concentric circles on the cut surface， with a higher number indicating better quality. Additionally， the presence of resinous secretions is also considered desirable. Based on the research findings， it is suggested that when developing famous classical formulas containing Spatholobi Caulis， the choice of the primary source should be S. suberectus or K. heteroclita， taking into consideration the therapeutic effects of the formula. It is also recommended that the latest plant classification be referenced in the next edition of Chinese Pharmacopoeia， adjusting the primary source of Kadsurae Caulis to K. heteroclita to avoid confusion caused by inconsistent original names， and the functions adjust to promote Qi circulation and relieve pain， disperse blood stasis and unblock collaterals， treating injuries caused by falls and bruises.

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 study the active ingredients and mechanism of action of Xinkeshu tablets against myo-cardial ischemia by network pharmacology and ze-brafish model.Methods The anti-myocardial ische-mia activity of Xinkeshu tablets was evaluated by iso-prenaline hydrochloride(ISO)-induced zebrafish myo-cardial ischemia model and H2O2-induced H9c2 dam-age model.The active ingredients of Xinkeshu tablets were retrieved using databases such as TCMSP.The potential targets were predicted by PharmaMapper data-base.Myocardial ischemic disease targets were searched by OMIM database.The potential therapeutic targets of Xinkeshu tablets against myocardial ischemia were analyzed.GO and KEGG enrichment analysis were conducted on core targets.The active ingredients were verified by zebrafish and cell model.qRT-PCR was used to detect the expression of key targets.Re-sults Xinkeshu tablets could significantly alleviate ISO-induced pericardial edema and bradycardia.It al-so could increase sinus venous-bulb aortic(SV-BA)distance and improve the cell viability.The 30 poten-tial active ingredients of Xinkeshu tables mainly acted on 30 core targets,including ALB,AKT1 and MAPK1,to regulate 627 GO items,including protein phosphorylation,negative regulation of apoptosis and positive regulation of PI3K signal transduction.KEGG results showed that 117 signaling pathways,including PI3K/Akt,FOXO and Ras,exerted anti-myocardial ischemia effect.Salvianolic acid A,lithospermic acid,rosmarinic acid,salvianolic acid D,salvianolic acid B,ginsenoside Rg2,hyperoside,3'-methoxypuerarin,3'-hydroxypuerarin and ginsenoside Rg1 could alleviate ISO-induced zebrafish myocardial ischemia and im-prove the cell viability.Xinkeshu tablets could upregu-late the expression of genes such as ras and akt1,and downregulate the expression of genes such as mapk1 and mapk8.Conclusion The active ingredients,in-cluding salvianolic acid A in Xinkeshu tablets,exert anti-myocardial ischemia effects by targeting targets,such as AKT1,MAPK1,and regulating signaling path-ways,such as PI3K/Akt,MAPK and Ras.

Immunotherapy is an important breakthrough in canc-er treatment.Unfortunately,low drug concentration in tumor sites almost ineffectively initiates immune responses and thereby severely limits immune therapy applications in clinics.Nanoma-terials are well-recognized drug delivery system in cancer thera-py.Nanographene oxide(NGO)have shown immense perti-nence for anti-cancer drug delivery owing to their ultra-high sur-face area,chemical stability,good biocompatibility and excel-lent photosensitivity.In addition,functionalized modifications on the surface of NGO increase tumor targeting and minimize cy-totoxicity.This study focuses on reviewing the literature and up-dates on NGO in drug delivery and discussing the possibilities and challenges of NGO in cancer synergetic therapy.

Redox-sensitive cysteine(RSC)thiol plays an important role in many biological processes such as photosynthesis,cellular metabolism,and transcription.Therefore,it is necessary to identify red-ox-sensitive cysteine accurately.However,traditional redox-sensitive cysteine identification is very ex-pensive and time-consuming.At present,there is an urgent need for a mathematical calculation method to identify sequence information and redox-sensitive cysteines quickly and accurately.Here,we devel-oped an effective predictor called iRSC-PseAAC,which used the dimension reduction algorithm LDA combined with the support vector machine to predict redox-sensitive cysteine sites.In the cross-validation results,the specificity(Sp),sensitivity(Sn),accuracy(Acc)and Matthews correlation coefficient(MCC)were 0.841,0.868,0.859 and 0.692 respectively.In the independent dataset results,the Sp,Sn,Acc and MCC were 0.906,0.882,0.890 and 0.767 respectively.compared with existing prediction methods,iRSC-PseAAC had obvious improvement effect.The method proposed for this study can also be used for many problems in computational proteomics.

Objective:To compare the short-term effect and adverse reaction of venetoclax(VEN)combined with azacitidine(AZA)versus"7+3"regimen in newly diagnosed elder patients with acute myeloid leukemia(AML).Methods:From January 2021 to January 2022,the clinical data of seventy-nine newly diagnosed elder patients with AML at the Second Hospital of Shanxi Medical University and the Shanxi Bethune Hospital were retrospectively analyzed,including VEN+AZA group(41 cases)and"7+3"group(38 cases).The propensity score matching(PSM)method was used to balance confounding factors,then response,overall survival(OS),progression-free survival(PFS)and adverse reactions between the two groups were compared.Results:The ORR of VEN+AZA group and"7+3"group was 68％and 84％,respectively,and the CRc was 64％and 72％,respectively,the differents were not statistically significant(P＞0.05).In the VEN+AZA group,there were 5 non-remission(NR)patients,4 with chromosome 7 abnormality(7q-/-7),and 1 with ETV6 gene mutation.Median followed-up time between the two groups was 8 months and 12 months,respectively,and the 6-months OS was 84％vs 92％(P=0.389),while 6-months PFS was 84％vs 92％(P=0.258).The main hematological adverse reactions in two groups were stage Ⅲ-Ⅳmyelosuppression,and the incidence rate was not statistically different(P＞0.05).The median time of neutrophil recovery in two groups was 27(11-70)d,25(14-61)d(P=0.161),and platelet recovery was 27(11-75)d,25(16-50)d(P=0.270),respectively.The infection rate of VEN+AZA group was lower than that of"7+3"group(56％vs 88％,P=0.012).The rate of lung infections of two groups was 36％and 64％,respectively,the difference was statistically significant(P=0.048).Conclusion:The short-term effect of VEN+AZA group and"7+3"regimens in eldrly AML patients are similar,but the VEN+AZA regimen had a lower incidence of infection.The presence of chromosome 7 abnormality(7q-/-7)may be a poor prognostic factor for elderly AML patients treated with VEN+AZA.