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.

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.

Aim To explore the effects of Huannao Yicong decoction(HYD)on the learning and memory ability and brain iron metabolism in APP/PS1 mice and the correlation of HAMP knockout mice and APP/PS1 double transgenic model mice.Methods The ex-periment was divided into five groups,namely,HAMP-/-group(6-month HAMP gene knockout mice),APP/PS1 group(6-month APP/PS1-double-transgenic mice),HAMP-/-+HYD,APP/PS1+HYD,and negative control group(6-month C57BL/6J mice),with six mice in each group.The dose was ad-ministered(13.68 g·kg-1 weight),and the other groups received distilled water for gavage once a day for two months.After the administration of the drug,the mice in each group were tested for learning and memory in the Morris water maze;Biochemical detec-tion was performed to detect iron ion content in each mouse brain;Western blot and RT-qPCR were carried out to analyze hippocampal transferrin(TF),transfer-rin receptor1(TFR1),membrane iron transporter1(FPN1)divalent metal ion transporter 1(DMT1)and β-amyloid protein(Aβ)protein and mRNA expression levels in each group.Results Compared with the normal group,both HAMP-/-mice and APP/PS1 mice had reduced the learning and memory capacity,in-creased iron content in brain tissue,Aβ protein ex-pression increased in hippocampus of HAMP-/-group and APP/PS1 group mice(P＜0.01),the protein and mRNA expression of TF,TFR1 and DMT1 increased in hippocampal tissues of HAMP-/-and APP/PS1 groups(P＜0.01),and the FPN1 protein and mRNA expres-sion decreased(P＜0.01).Compared with the HAMP-and APP/PS1 groups,respectively,HAMP-/-+HYD group and APP/PS1+HYD group had improved learning and memory ability,decreased iron content,decreased Aβ protein expression(P＜0.01),decreased TF,TFR1,DMT1 protein and mR-NA expression(P＜0.01),and increased expression of FPN1 protein and mRNA(P＜0.01).Conclusions There is some association between HAMP-/-mice and APP/PS1 mice,HYD can improve the learning and memory ability of HAMP-/-and APP/PS1 mice and reduce the Aβ deposition.The mechanism may be related to the regulation of TF,TFR1,DMT1,FPN1 expression and improving brain iron overload.

Cardio-cerebrovascular and neurodegenerative diseases are diseases of high-incidence diseases among middle-aged and elderly people,with high disability and mortality rates,which se-riously threaten human health.PK2 is a newly discovered secre-ted protein that plays an important role in many physiological and pathological processes by binding to its receptor PKR1 or 2.Numerous studies related to PK2/PKRs have shown that this sig-naling pathway also plays a very important role in the occurrence and development of cardiovascular,cerebrovascular and neuro-degenerative diseases,and through exploring the connection be-tween them,PK2/PKRs may become a new target for the clini-cal treatment of these diseases.

Aim To investigate the effect of total glu-cosides of paeony on inflammatory injury and TLR4/NF-κB/NLRP3 pathway in autoimmune thyroiditis(AIT)rats.Methods The experiment was divided into control group,model group,total glucosides of pae-ony(TGP),TLR4 inhibitor group and TGP+TLR4 ag-onist group,with 10 animals in each group.Except for the control group,the rats in other groups were subcu-taneously injected with thyroglobulin and Freund's ad-juvant to induce the AIT rat model.After six weeks of administration,thyroid histopathological changes were observed using hematoxylin-eosin(HE)staining;ser-um levels of TPOAb,TgAb,TSH,T3,T4,TNF-α,INF-γ,IL-1 β and IL-1 β were detected by enzyme-linked immunosorbent assay(ELISA);TLR4/NF-κB/NLRP3 pathway mRNAs and proteins expression in thyroid tis-sues were detected by RT-qPCR and Western blot.Re-sults Compared with the control group,the thyroid follicular epithelium of rats was significantly damaged,and the serum levels of TPOAb,TgAb,TSH,T3,T4,TNF-α,INF-γ,IL-1 β and IL-1 β increased(P＜0.01).The expression of TLR4/NF-κB/NLRP3 path-way mRNAs and proteins increased in the model group(P＜0.01).Compared with the model group,the damage of thyroid follicular epithelium was alleviated,and the serum levels of TPOAb,TgAb,TSH,T3,T4,TNF-α,INF-γ,IL-1 β and IL-1 β were reduced(P＜0.01),the expression of TLR4/NF-κB/NLRP3 path-way mRNAs and proteins were down-regulated in the TGP group and TLR4 inhibitor group(P＜0.01).Compared with TGP group,the damage of thyroid follic-ular epithelium was aggravated,and the levels of serum TPOAb,TgAb,TSH,T3,T4,TNF-α,INF-γ,IL-1 β and IL-1 β were elevated(P＜0.05 or P＜0.01),the pro-tein expressions of TLR4/NF-κB/NLRP3 pathway mR-NAs and proteins were up-regulated in TGP+TLR4 ag-onist group(P＜0.05 or P＜0.01).Conclusions TGP may play a protective role in thyroid by inhibiting the TLR4/NF-κB/NLRP3 pathway and improving the inflammatory injury of thyroid tissues.

Aim To observe the changes in hippocam-pal 2A subunit of N-methyl-D-aspartate receptor(NR2A)before and after the learning and memory training,and then investigate the neuropharmacological effects of NR2A by microinjection of NVP-AAM077(NR2A specific antagonist)into the hippocampal den-teta gyrus,based on the spatial learning and memory behavior paradigm induced by Mirror water maze train-ing.Methods Three-month old SD rats were random-ly divided into the training and non-training group,and the rats in the two groups were randomly divided into control group and NVP-AAM077 group(NVP).The expressions of NR2A,brain-derived neurotrophic factor(BDNF),transcriptional activator 4(ATF4)and eu-karyotic transcription initiation factor 2 α(eIF2α)phosphorylation levels in denteta gyrus were detected by Western blot.Then,integrated stress response in-hibitor ISRIB was microinjected into the dentate gyrus after the NVP,the expression of ATF4 and p-eIF2αlevels,and the spatial memory abilities were detected.Results Compared with non-training,behavioral training promoted the expression of NR2A and BDNF of rats in denteta gyrus,and this effect could be inhibi-ted by NVP,which significantly increased the expres-sion of p-eIF2α and ATF4.Injection of ISRIB into denteta gyrus significantly inhibited the expression of ATF4,and reversed the spatial memory impairment caused by NVP.Conclusion NVP-induced hipp-ocampal dentate gyrus NR2A-mediated spatial learning and memory impairment in rats may be related to hipp-ocampal integrated stress response.