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 observe the effect of high-frequency repetitive transcranial magnetic stimulation (rTMS) at different frequencies on cognitive impairment due to high-altitude hypoxia.Methods:Sixty officers and soldiers displaying cognitive impairment in a hypoxic high-altitude environment were randomly divided into 15Hz, 20Hz and 25Hz groups, each of 20. They were given rTMS at those frequencies for 30 days. Before the stimulation and after 15 and 30 days, event-related potentials, latencies of mismatched negativity (MMN) and P300 signals were recorded. The participants′ cognition was also evaluated using the Montreal Cognitive Assessment Scale (MoCA). Correlation between the electrophysiological indexes and the MoCA scores was computed.Results:After 15 days, all had shorter MMN latencies, higher total MoCA scores and better memory scores. The only significant difference among the three groups was in the average memory scores. After 15 days, MMN latency was significantly negatively correlated with the memory scores in all three groups ( r=0.44 to -0.54). Conclusions:rTMS at frequencies above 15Hz can effectively relieve cognitive impairment, especially memory dysfunction, resulting from high-altitude hypoxia.

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.

Transcranial temporal interference stimulation (tTIS) is a novel non-invasive neuromodulation technique with the potential to precisely target deep brain structures. This study explores the neural and behavioral effects of tTIS on the superior colliculus (SC), a region involved in eye movement control, in mice. Computational modeling revealed that tTIS delivers more focused stimulation to the SC than traditional transcranial alternating current stimulation. In vivo experiments, including Ca²⁺ signal recordings and eye movement tracking, showed that tTIS effectively modulates SC neural activity and induces eye movements. A significant correlation was found between stimulation frequency and saccade frequency, suggesting direct tTIS-induced modulation of SC activity. These results demonstrate the precision of tTIS in targeting deep brain regions and regulating eye movements, highlighting its potential for neuroscientific research and therapeutic applications.
Animals ; Superior Colliculi/physiology* ; Transcranial Direct Current Stimulation/methods* ; Eye Movements/physiology* ; Male ; Mice ; Mice, Inbred C57BL

Aim To explore the effect of hydroxysafflor yellow A(HSYA)on lipocalin 2(LCN2)-induced fer-roptosis in HT22 cells and the related mechanism.Methods Thirty male Sprague-Dawley(SD)rats were used to establish the middle cerebral artery occlu-sion/reperfusion(MCAO/R)model by the suture method.The rats were randomly divided into the Sham group,the MCAO/R group,and the MCAO/R+HSYA group.The infarct area was measured by TTC staining,and the degree of neurological deficit was evaluated by the Z-Longa scoring method.The expressions of LCN2 and 24P3R in brain tissues were detected by Western blot.LCN2 protein was added to HT-22 cells,and the cells were divided into the normal group,the LCN2 group,and the LCN2+HSYA group.The optimal con-centration of LCN2-induced neuronal ferroptosis was screened by LDH assay and Western blot,and the ex-pression levels of ferritin,FPN1,GPX4,SLC7A11,COX2,and 24P3R were detected.LCN2 was knocked down by siRNA transfection,and the expressions of GPX4 and ferritin were detected.The contents of glu-tathione(GSH),malondialdehyde(MDA),GPX4,and Fe2+were determined by colorimetry,and the expres-sion of GPX4 was detected by immunofluorescence.The binding force between HSYA and LCN2 was ana-lyzed by molecular docking technology.Results Ani-mal experiments showed that HSYA could reduce the cerebral infarction area and decrease the neurological function score of MCAO/R rats.Compared with the sham group,the levels of LCN2 and 24P3R increased in the MCAO/R group,while HSYA inhibited their ex-pressions.Cell experiments showed that the optimal concentration of LCN2 to induce ferroptosis in HT22 cells was 2 μmol·L-1.After knocking down LCN2 by siRNA transfection,compared with the LCN2 group,the expression levels of GPX4 and ferritin in the siLCN2 group increased significantly.Compared with the nor-mal group,the expressions of SLC7A11,GPX4,FPN1,ferritin,and GSH in the LCN2 group decreased signifi-cantly,while the concentration of Fe2+,and the expres-sions of MDA,COX2,and 24P3R increased.HSYA could increase the expressions of SLC7A11,GPX4,FPN1,ferritin,and GSH,reduce the contents of Fe2+and MDA,and inhibit the expressions of COX2 and 24P3R.Molecular docking showed that the binding en-ergy between HSYA and LCN2 was-8.0 kJ·mol-1.Conclusion HSYA can inhibit LCN2-induced ferrop-tosis in HT22 cells through the SLC7A11/GPX4 signa-ling pathway.

Aim To explore the effect of hydroxysafflor yellow A(HSYA)on lipocalin 2(LCN2)-induced fer-roptosis in HT22 cells and the related mechanism.Methods Thirty male Sprague-Dawley(SD)rats were used to establish the middle cerebral artery occlu-sion/reperfusion(MCAO/R)model by the suture method.The rats were randomly divided into the Sham group,the MCAO/R group,and the MCAO/R+HSYA group.The infarct area was measured by TTC staining,and the degree of neurological deficit was evaluated by the Z-Longa scoring method.The expressions of LCN2 and 24P3R in brain tissues were detected by Western blot.LCN2 protein was added to HT-22 cells,and the cells were divided into the normal group,the LCN2 group,and the LCN2+HSYA group.The optimal con-centration of LCN2-induced neuronal ferroptosis was screened by LDH assay and Western blot,and the ex-pression levels of ferritin,FPN1,GPX4,SLC7A11,COX2,and 24P3R were detected.LCN2 was knocked down by siRNA transfection,and the expressions of GPX4 and ferritin were detected.The contents of glu-tathione(GSH),malondialdehyde(MDA),GPX4,and Fe2+were determined by colorimetry,and the expres-sion of GPX4 was detected by immunofluorescence.The binding force between HSYA and LCN2 was ana-lyzed by molecular docking technology.Results Ani-mal experiments showed that HSYA could reduce the cerebral infarction area and decrease the neurological function score of MCAO/R rats.Compared with the sham group,the levels of LCN2 and 24P3R increased in the MCAO/R group,while HSYA inhibited their ex-pressions.Cell experiments showed that the optimal concentration of LCN2 to induce ferroptosis in HT22 cells was 2 μmol·L-1.After knocking down LCN2 by siRNA transfection,compared with the LCN2 group,the expression levels of GPX4 and ferritin in the siLCN2 group increased significantly.Compared with the nor-mal group,the expressions of SLC7A11,GPX4,FPN1,ferritin,and GSH in the LCN2 group decreased signifi-cantly,while the concentration of Fe2+,and the expres-sions of MDA,COX2,and 24P3R increased.HSYA could increase the expressions of SLC7A11,GPX4,FPN1,ferritin,and GSH,reduce the contents of Fe2+and MDA,and inhibit the expressions of COX2 and 24P3R.Molecular docking showed that the binding en-ergy between HSYA and LCN2 was-8.0 kJ·mol-1.Conclusion HSYA can inhibit LCN2-induced ferrop-tosis in HT22 cells through the SLC7A11/GPX4 signa-ling pathway.

Objective:To observe the effect of high-frequency repetitive transcranial magnetic stimulation (rTMS) at different frequencies on cognitive impairment due to high-altitude hypoxia.Methods:Sixty officers and soldiers displaying cognitive impairment in a hypoxic high-altitude environment were randomly divided into 15Hz, 20Hz and 25Hz groups, each of 20. They were given rTMS at those frequencies for 30 days. Before the stimulation and after 15 and 30 days, event-related potentials, latencies of mismatched negativity (MMN) and P300 signals were recorded. The participants′ cognition was also evaluated using the Montreal Cognitive Assessment Scale (MoCA). Correlation between the electrophysiological indexes and the MoCA scores was computed.Results:After 15 days, all had shorter MMN latencies, higher total MoCA scores and better memory scores. The only significant difference among the three groups was in the average memory scores. After 15 days, MMN latency was significantly negatively correlated with the memory scores in all three groups ( r=0.44 to -0.54). Conclusions:rTMS at frequencies above 15Hz can effectively relieve cognitive impairment, especially memory dysfunction, resulting from high-altitude hypoxia.