Electroencephalography (EEG) is a non-invasive neurophysiological monitoring technique. It records the electrical activity of the cerebral cortex using electrodes placed on the scalp surface. Owing to its high safety, portability, and millisecond-level temporal resolution, EEG has been widely utilized in a variety of fields, including clinical diagnosis, brain-computer interfaces (BCIs), and cognitive neuroscience research. However, due to its microvolt-level amplitude, EEG is highly susceptible to various artifacts, including electrooculographic (EOG), electrocardiographic (ECG), electromyographic (EMG), and power line interference (PLI). These artifacts can obscure genuine neural activity and introduce spurious electrophysiological features. Consequently, they may compromise EEG signal quality, thereby reducing the reliability of downstream analyses. To address this issue, numerous EEG artifact removal methods have been developed, including both traditional denoising techniques and deep learning-based approaches. Traditional EEG denoising methods have long served as the primary solutions for artifact removal. Representative approaches include filtering, regression, and blind source separation. Although these methods have demonstrated effectiveness in specific scenarios, they suffer from several inherent limitations. Filtering assumes that artifacts and EEG signals can be separated in the frequency domain, but many artifacts, such as EOG and EMG, overlap with EEG spectra, which may lead to the loss of valuable neural information. Regression methods require high-quality artifact references to estimate and subtract contaminations, limiting their effectiveness in reference-free scenarios. Blind source separation can remove artifacts without external references, but it typically requires the number of EEG channels to exceed the number of sources, restricting its application in single- or low-channel EEG recordings. Deep learning-based EEG denoising methods address these limitations effectively. First, they learn the nonlinear mapping between contaminated and clean EEG directly from data in an end-to-end manner. This approach does not rely on assumptions about spectral separability, thereby preserving neural activity more completely. Second, the reference information is incorporated during the training phase, allowing the trained model to perform artifact removal independently without external references. Third, deep learning models can be flexibly designed to accommodate various recording setups, achieving robust denoising for both high-density and single-channel EEG. Collectively, these advantages enable deep learning-based methods to overcome the main challenges of traditional approaches, providing more accurate and reliable EEG signal recovery. The superior denoising performance of deep learning-based EEG denoising methods has attracted increasing attention in EEG artifact removal research. As a result, many deep learning-based denoising methods have been developed and successfully applied in neural engineering areas. However, a systematic review of the techniques and applications in this field is still lacking. To address this gap, this paper reviews recent advances in deep learning-based EEG denoising from four perspectives: technical principle, benchmark dataset, denoising model, and evaluation method. Representative applications in neural signal analysis and BCI decoding are also summarized. Furthermore, the advantage, existing challenge, and future research direction of deep learning-based EEG denoising are discussed. This review aims to provide valuable theoretical insights and technical guidance for researchers. It is also expected to promote further advances and broader applications of deep learning-based EEG denoising techniques.

Background: and Purpose Symptomatic intracranial hemorrhage (sICH) following endovascular thrombectomy (EVT) is a severe complication associated with adverse functional outcomes and increased mortality rates. Currently, a reliable predictive model for sICH risk after EVT is lacking. Methods: This study used data from patients aged ≥20 years who underwent EVT for anterior circulation stroke from the nationwide Taiwan Registry of Endovascular Thrombectomy for Acute Ischemic Stroke (TREAT-AIS). A predictive model including factors associated with an increased risk of sICH after EVT was developed to differentiate between patients with and without sICH. This model was compared existing predictive models using nationwide registry data to evaluate its relative performance. Results: Of the 2,507 identified patients, 158 developed sICH after EVT. Factors such as diastolic blood pressure, Alberta Stroke Program Early CT Score, platelet count, glucose level, collateral score, and successful reperfusion were associated with the risk of sICH after EVT. The TREAT-AIS score demonstrated acceptable predictive accuracy (area under the curve [AUC]=0.694), with higher scores being associated with an increased risk of sICH (odds ratio=2.01 per score increase, 95% confidence interval=1.64–2.45, P<0.001). The discriminatory capacity of the score was similar in patients with symptom onset beyond 6 hours (AUC=0.705). Compared to existing models, the TREAT-AIS score consistently exhibited superior predictive accuracy, although this difference was marginal. Conclusions The TREAT-AIS score outperformed existing models, and demonstrated an acceptable discriminatory capacity for distinguishing patients according to sICH risk levels. However, the differences between models were only marginal. Further research incorporating periprocedural and postprocedural factors is required to improve the predictive accuracy.

Objective To investigate the effect and mechanism of actin gamma1(ACTG1)downregulation on apoptosis in gastric cancer cells line HGC-27.Methods Stable ACTG1 knockdown HGC-27 cell line was constructed by CRISPR/Cas9,ACTG1 knockdown was verified by DNA sequencing and Western blot,apoptosis rate was detected by flow cytometry,Western blot detected the expression level of apoptosis-related proteins Bcl2-associated X protein(Bax),B cell lymphoma 2 family protein(Bcl2)and PI3K/AKT signal pathway-related proteins AKT and p-AKT.Results HGC-27 cell lines with stable knockdown of ACTG1 were constructed,and the ACTG1 protein levels were decreased in the sgACTG1-1 and sgACTG1-2 groups compared with the Control group.Compared with the apoptosis rate in the Control group(6.54%±0.67%),cell apoptosis rate in the sgACTG1-1 and sgACTG1-2 groups(10.11%±0.46%,14.67%±0.17%)were significantly increased,the differences were statistically significant(t=-7.58,-20.28,all P<0.01).Compared the Control group,the Bax protein levels in the sgACTG1-1 and sgACTG1-2 groups(0.89±0.02,1.00±0.08 vs 0.71±0.03)were significantly increased(t=-8.14,-5.87),the level of Bcl2 protein(0.49±0.06,0.39±0.06 vs 0.65±0.07)were significantly decreased(t=3.09,5.35),the differences were statistically significant(all P<0.05).Compared with the Control group,the AKT protein levels in the sgACTG1-1 and sgACTG1-2 groups(0.95±0.10,0.43±0.09 vs 1.17±0.06)and the P-AKT protein level(0.38±0.08,0.28±0.12 vs 0.70±0.14)were significantly decreased,the differences were statistically significant(t=3.20,12.13;3.44,3.85,all P<0.05).Conclusion Downregulation of ACTG1 inhibits the expression of PI3K/Akt signaling pathway related proteins AKT,p-AKT and promotes gastric cancer cells line HGC-27 apoptosis.

Aim To investigate the protective effect of Shengmai Yin on myocardial ischemia/reperfusion in-jury(MI/RI)in vitro and in vivo and to unravel the underlying mechanism.Methods SD rats were divid-ed into the sham group,model group,and Shengmai Yin group(SM).Rat MI/RI model was established.Cardiac function,infarct area,pathological changes,cardiomyocyte apoptosis,macrophage infiltration,and serum cTnT and CK-MB levels were measured.The mRNA and protein expressions of Calpain-1 and Cal-pain-2 were assessed.The hypoxia/reoxygenation(H/R)model was constructed in H9c2 cells.The active ingredients of Shengmai Yin were screened using net-work pharmacology and verified by CCK-8.In the car-diomyocytes H/R model,Fluo-4 AM staining was used to detect the changes of Ca2+levels.Results Com-pared with model group,LVEF and LVFS of Shengmai Yin-treated rats increased,myocardial infarction area was reduced,while myocardial tissue injury was allevi-ated.Myocardial apoptosis rate and the number of macrophages were reduced.Similarly,cTnT and CK-MB levels decreased.In addition,the expression lev-els of Calpain-1 and Calpain-2 mRNA and protein de-creased in the SM treatment group.Under the H/R model,all the active ingredients of Shengmai decoction had protective effects on cardiomyocytes,and the treat-ment could reduce the level of Ca2+in cardiomyocytes.Conclusions Shengmai Yin has protective effects on MI/RI in rats.This effect may be related to the de-crease in Ca2+levels,as well as Calpain-1 and Calap-in-2 mRNA and protein expression.

Objective To investigate the characteristics of changes in pain-anxiety-depression-fatigue symptom clusters and their possible associated factors in adolescents with acute lymphoblastic leukemia(ALL)during early chemotherapy.Methods A prospective longitudinal study was conducted from Nov 2019 to Oct 2021,enrolling newly diagnosed adolescent ALL patients from 5 tertiary or pediatric specialty hospitals in Shanghai,Zhejiang Province,Sichuan Province,Anhui Province and Guangdong Province.Patient-reported pain,anxiety,depression,and fatigue were collected at five time points within the first nine weeks of chemotherapy using the PROMIS Pediatric-25 instrument.Latent profile analysis(LPA)and latent transition analysis(LTA)were applied to explore the latent classes of symptom clusters,their transition probabilities over time,and possible risk or protective factors associated with class membership.Results A total of 134 ALL cases were enrolled,and symptom clusters at all the 5 time points(T1-T5)were consistently classified into three groups of mild,moderate and severe symptoms.The severe symptoms group accounted for the largest proportion at each time point(54.5%,59.7%,66.4%,49.3%,and 47.0%,respectively),while the mild and moderate symptoms groups showed an initial decline followed by an increase.Among participants,40.2%maintained the same symptom status,and 77.4%experienced at least one episode of severe symptom status during the trajectory.Religious affiliation(T5)and family monthly income>5 000 Yuan(T2,T4 and T5)served as protective factors against severe symptoms.Higher baseline fatigue(T1)was associated with membership in the severe symptoms group at subsequent time points.Conclusion Pain-anxiety-depression-fatigue symptoms in adolescents with ALL during early chemotherapy can be categorized into mild,moderate and severe symptoms with dynamic transitions over time.Higher baseline fatigue was associated with increased risk of severe symptoms,whereas higher family income and religious affiliation appeared protective effects.

Objective:To investigate the sex difference and symptom correlation of pituitary-thyroid axis and pituitary-adrenal axis function in patients with remitted schizophrenia.Methods:Using cross-sectional study method,243 patients with remitted schizophrenia at Changning District Mental Health Center of Shanghai from January 2019 to September 2021(schizophrenia group)were selected,and healthy individuals who underwent physical examinations during the same period(healthy control group)were also selected.The demographic data and HPT axis,HPA axis neuroendocrine indicators[serum thyroid stimulating hormone(TSH),free triiodothyronine(FT3),free thyroid hormone(FT4),triiodothyronine(TT3),thyroid hormone(TT4),adrenocorticotropic hormone(ACTH),and cortisol(COR)]between healthy control group and schizophrenia group were compared.Gender differences in HPT axis and HPA axis in schizophrenia patients were compared.The correlation between neuroendocrine indicators and gender,disease duration,positive and negative symptom scale(PANSS)scores in patients with schizophrenia were analyzed by linear regression method.Using stratified multiple linear regression,laboratory measured variables and age were included as predictive factors in the model to construct a regression prediction model for hormone levels between schizophrenia and healthy control group,as well as subgroups of schizophrenia gender.Generate receiver operating characteristic(ROC)curves based on the probability values of predictive factors,and determine the predictive value of the logistic regression model using the area under the curve(AUC).Results:TT3,TSH,TT4 in schizophrenia group were lower than those in the healthy control group(P＜0.05),while ACTH and COR were higher than those in the healthy control group(P＜0.05).There was a statistically significant difference in the negative symptom scores,TSH,TT3,FT3,ACTH,and COR levels between the female schizophrenia group and male schizophrenia group(P＜0.05).PANSS,total score of general psychopathology score were positively correlated with COR level,negative symptom score was negatively correlated with FT3 levels(all P＜0.05),but there was no linear relationship among the three(absolute value of r＜0.3).ROC curve results showed that,the schizophrenia hormone level model had good discrimination accuracy,with AUC=0.872(95％confidence interval 0.841-0.904),the optimal threshold(Yoden index)=0.651.ROC curve shows that the male and female subgroups of schizophrenia models also have good discrimination accuracy,with AUC=0.794(95％confidence interval 0.737-0.850)and the optimal cutoff value(Yoden index)=0.495.Conclusion:The changes of active T4 in schizophrenia patients may be one of the possible causes of the chronic pathological changes of schizophrenia.The level of high-functioning T3 hormone is significantly lower in female patients than that in male patients.The hierarchical regression model provides good identification accuracy for remitted schizophrenia and gender subgroups.

Objective To investigate the association of endometrial thickness(EMT)with obstetric and neonatal outcomes of monoparous pregnancy in fresh cleavage embryos transfer.Methods A total of 1 845 patients of monoparous pregnancy after fresh cleavage embryos transfer cycles from Jan 2016 to Mar 2022 at Shanghai First Maternity and Infant Hospital,Tongji Universtiy were analyzed retrospectively.Patients were categorized into three groups by EMT on transferation day:≤8 mm(group A),8-14 mm(group B)and≥14 mm(group C).The primary outcomes were preterm birth(PTB),birth weight and birth weight z-score,small-for-gestation age,large-for-gestation age,very low birth weight,low birth weight and macrosomia.The second outcomes were pregnancy and perinatal complications.The relationship between EMT and adverse neonatal outcomes was estimated by Logistic regression analysis.Results The rate of ectopic pregnancy was increased significantly in group A.No significant differences were found among the three groups in gestation age,birth weight,birth weight z-score,PTB,small for gestation age,large for gestation age,low birth weight,very low birth weight and macrosomia.Compared with group B,the odds of adverse neonatal outcomes did not show significant differences before and after adjustment in both group A and group C by Logistic regression analysis.Conclusion Thinner EMT in fresh cleavage embryos transfer is associated with higher rate of ectopic pregnancy,while it is not independently associated with adverse perinatal outcomes.

Objective To investigate the association of endometrial thickness(EMT)with obstetric and neonatal outcomes of monoparous pregnancy in fresh cleavage embryos transfer.Methods A total of 1 845 patients of monoparous pregnancy after fresh cleavage embryos transfer cycles from Jan 2016 to Mar 2022 at Shanghai First Maternity and Infant Hospital,Tongji Universtiy were analyzed retrospectively.Patients were categorized into three groups by EMT on transferation day:≤8 mm(group A),8-14 mm(group B)and≥14 mm(group C).The primary outcomes were preterm birth(PTB),birth weight and birth weight z-score,small-for-gestation age,large-for-gestation age,very low birth weight,low birth weight and macrosomia.The second outcomes were pregnancy and perinatal complications.The relationship between EMT and adverse neonatal outcomes was estimated by Logistic regression analysis.Results The rate of ectopic pregnancy was increased significantly in group A.No significant differences were found among the three groups in gestation age,birth weight,birth weight z-score,PTB,small for gestation age,large for gestation age,low birth weight,very low birth weight and macrosomia.Compared with group B,the odds of adverse neonatal outcomes did not show significant differences before and after adjustment in both group A and group C by Logistic regression analysis.Conclusion Thinner EMT in fresh cleavage embryos transfer is associated with higher rate of ectopic pregnancy,while it is not independently associated with adverse perinatal outcomes.

Objective:To investigate the sex difference and symptom correlation of pituitary-thyroid axis and pituitary-adrenal axis function in patients with remitted schizophrenia.Methods:Using cross-sectional study method,243 patients with remitted schizophrenia at Changning District Mental Health Center of Shanghai from January 2019 to September 2021(schizophrenia group)were selected,and healthy individuals who underwent physical examinations during the same period(healthy control group)were also selected.The demographic data and HPT axis,HPA axis neuroendocrine indicators[serum thyroid stimulating hormone(TSH),free triiodothyronine(FT3),free thyroid hormone(FT4),triiodothyronine(TT3),thyroid hormone(TT4),adrenocorticotropic hormone(ACTH),and cortisol(COR)]between healthy control group and schizophrenia group were compared.Gender differences in HPT axis and HPA axis in schizophrenia patients were compared.The correlation between neuroendocrine indicators and gender,disease duration,positive and negative symptom scale(PANSS)scores in patients with schizophrenia were analyzed by linear regression method.Using stratified multiple linear regression,laboratory measured variables and age were included as predictive factors in the model to construct a regression prediction model for hormone levels between schizophrenia and healthy control group,as well as subgroups of schizophrenia gender.Generate receiver operating characteristic(ROC)curves based on the probability values of predictive factors,and determine the predictive value of the logistic regression model using the area under the curve(AUC).Results:TT3,TSH,TT4 in schizophrenia group were lower than those in the healthy control group(P＜0.05),while ACTH and COR were higher than those in the healthy control group(P＜0.05).There was a statistically significant difference in the negative symptom scores,TSH,TT3,FT3,ACTH,and COR levels between the female schizophrenia group and male schizophrenia group(P＜0.05).PANSS,total score of general psychopathology score were positively correlated with COR level,negative symptom score was negatively correlated with FT3 levels(all P＜0.05),but there was no linear relationship among the three(absolute value of r＜0.3).ROC curve results showed that,the schizophrenia hormone level model had good discrimination accuracy,with AUC=0.872(95％confidence interval 0.841-0.904),the optimal threshold(Yoden index)=0.651.ROC curve shows that the male and female subgroups of schizophrenia models also have good discrimination accuracy,with AUC=0.794(95％confidence interval 0.737-0.850)and the optimal cutoff value(Yoden index)=0.495.Conclusion:The changes of active T4 in schizophrenia patients may be one of the possible causes of the chronic pathological changes of schizophrenia.The level of high-functioning T3 hormone is significantly lower in female patients than that in male patients.The hierarchical regression model provides good identification accuracy for remitted schizophrenia and gender subgroups.

Background: and Purpose Symptomatic intracranial hemorrhage (sICH) following endovascular thrombectomy (EVT) is a severe complication associated with adverse functional outcomes and increased mortality rates. Currently, a reliable predictive model for sICH risk after EVT is lacking. Methods: This study used data from patients aged ≥20 years who underwent EVT for anterior circulation stroke from the nationwide Taiwan Registry of Endovascular Thrombectomy for Acute Ischemic Stroke (TREAT-AIS). A predictive model including factors associated with an increased risk of sICH after EVT was developed to differentiate between patients with and without sICH. This model was compared existing predictive models using nationwide registry data to evaluate its relative performance. Results: Of the 2,507 identified patients, 158 developed sICH after EVT. Factors such as diastolic blood pressure, Alberta Stroke Program Early CT Score, platelet count, glucose level, collateral score, and successful reperfusion were associated with the risk of sICH after EVT. The TREAT-AIS score demonstrated acceptable predictive accuracy (area under the curve [AUC]=0.694), with higher scores being associated with an increased risk of sICH (odds ratio=2.01 per score increase, 95% confidence interval=1.64–2.45, P<0.001). The discriminatory capacity of the score was similar in patients with symptom onset beyond 6 hours (AUC=0.705). Compared to existing models, the TREAT-AIS score consistently exhibited superior predictive accuracy, although this difference was marginal. Conclusions The TREAT-AIS score outperformed existing models, and demonstrated an acceptable discriminatory capacity for distinguishing patients according to sICH risk levels. However, the differences between models were only marginal. Further research incorporating periprocedural and postprocedural factors is required to improve the predictive accuracy.