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.

Mitochondria, functioning not only as the central hub of cellular energy metabolism but also as semi-autonomous organelles, orchestrate cellular fate decisions through their endogenous mitochondrial DNA (mtDNA), which encodes core components of the electron transport chain. Emerging research has identified microRNAs localized within mitochondria, termed mitochondria-located microRNAs (mitomiRs). Recent studies have revealed that mitomiRs are transcribed from nuclear DNA (nDNA), processed and matured in the cytoplasm, and subsequently transported into mitochondria. mitomiRs regulate mtDNA through diverse mechanisms, including modulation of mtDNA expression at the translational level and direct binding to mtDNA to influence transcription. Aberrant expression of mitomiRs leads to mitochondrial dysfunction and contributes to the pathogenesis of metabolic diseases. Restoring mitomiR expression to physiological levels using mitomiRs mimics or inhibitors has been shown to improve mitochondrial function and alleviate related diseases. Consequently, the regulatory mechanisms of mitomiRs have become a major focus in mitochondrial research. Given that mitomiRs are located in mitochondria, targeted delivery strategies designed for mtDNA can be adapted for the delivery of mitomiRs mimics or inhibitors. However, numerous intracellular and extracellular barriers remain, highlighting the need for more precise and efficient delivery systems in the future. The regulation of mtDNA expression mediated by mitomiRs not only expands our understanding of miRNA functions in post-transcriptional gene regulation but also provides promising molecular targets for the treatment of mitochondrial-related diseases. This review systematically summarizes recent research progress on mitomiRs in regulating mtDNA expression and discusses the underlying mechanisms of mitomiRs-mtDNA interactions. Additionally, it provides new perspectives on precision therapeutic strategies, with a particular emphasis on mitomiRs-based regulation of mitochondrial function in mitochondrial-related diseases.

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 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.

Objective To establish the finite element model of spinal canal reconstruction and internal fixation,analysis influence of spinal canal reconstruction and internal fixation on spinal stability,and verify the effectiveness and reliability of spinal canal reconstruction and internal fixation in spinal canal surgery.Methods A 30-year-old male healthy volunteer with a height of 172 cm and weight of 75 kg was selected and his lumbar CT data were collected to establish a finite element model of normal lumbar Lo3-L,and the results were compared with in vitro solid results and published finite element analysis results to verify the validity of the model.They were divided into normal group,laminectomy group and spinal canal reconstruction group according to different treatment methods.Under the same boundary fixation and physiological load conditions,six kinds of ac-tivities were performed,including forward bending,backward extension,left bending,right bending,left rotation and right rota-tion,and the changes of range of motion(ROM)of L3-L4,L4-L5 segments and overall maximum ROM of L3-L5 were analyzed under the six conditions.Results The ROM displacement range of each segment of the constructed L3-L5 finite element model was consistent with the in vitro solid results and previous literature data,which confirms the validity of the model.In L3-L4,ROM of spinal canal reconstruction group was slightly increased than that of normal group during posterior extension(＞5％dif-ference),and ROM of other conditions was similar to that of normal group(＜5％difference).ROM in laminectomy group was significantly increase than that in normal group and spinal canal reconstruction group under the condition of flexion,extension,left and right rotation.In L4-L5,ROM in spinal canal reconstruction group was similar to that in normal group(＜5％differ-ence),while ROM in laminectomy group was significantly higher than that in normal group and spinal canal reconstruction group(＞5％difference).In the overall maximum ROM of L3-L5,spinal canal reconstruction group was only slightly higher than normal group under the condition of posterior extension(＞5％difference),while laminectomy was significantly higher than normal group and spinal canal reconstruction group under the condition of anterior flexion,posterior extension,left and right rotation(＞5％difference).The changes of each segment ROM and overall ROM of L3-L5 showed laminectomy group＞spinal canal reconstruction group＞normal group.Conclusion Laminectomy could seriously affect biomechanical stability of the spine,but application of spinal canal reconstruction and internal fixation could effectively reduce ROM displacement of the responsi-ble segment of spine and maintain its biomechanical stability.