The effect of PFAS exposure on glucolipid metabolism in children and adolescents: a meta-analysis.

Background: Previous studies showed that per- and polyfluoroalkyl substances (PFAS), which are widely found in the environment, can disrupt endocrine homeostasis when they enter the human body. This meta-analysis aimed to evaluate current human epidemiological evidence on the relationship between PFAS exposure and glucolipid metabolism in childhood and adolescence. Methods: We searched PubMed, Web of Science, Embase, and Cochrane Library databases, and identified population-based epidemiological studies related to PFAS and glucolipid metabolism indexes that were published before 30 December 2022. The heterogeneity of the included literature was assessed using the I-square (I2) test and statistics Q. Random-effects and fixed-effects models were used to combine the effect size. Subgroup analysis based on age and sex of the study participants was performed. A sensitivity analysis was used to evaluate the robustness and reliability of the combined results. Egger's and Begg's tests were used to analyze publication bias. Results: A total of 12 studies were included in this analysis. There was a positive association between PFAS and TC (ß = 1.110, 95% CI: 0.601, 1.610) and LDL (ß = 1.900, 95% CI: 1.030, 2.770), and a negative association between PFAS and HOMA-IR in children and adolescents (ß = -0.130, 95% CI: -0. 200, -0.059). PFOS was significant positive associated with TC (ß = 8.22, 95% CI: 3.93, 12.51), LDL (ß = (12.04, 95% CI: 5.08, 18.99), and HOMA-IR (ß = -0.165, 95% CI: -0.292, -0.038). Subgroup analysis showed that exposure to PFAS in the adolescent group was positively associated with TC and LDL levels, and the relationship was stronger in females. Conclusion: PFAS exposure is associated with glucolipid metabolism in children and adolescents. Among them, PFOS may play an important role. Recognition of environmental PFAS exposure is critical for stabilizing the glycolipid metabolism relationship during the growth and development of children and adolescents.

Association between Dietary Consumption of Vitamin B1 and Advanced Age-Related Macular Degeneration: A Cross-Sectional Observational Study in NHANES 2005-2008.

INTRODUCTION: One of the most common conditions that causes permanent blindness globally is age-related macular degeneration (AMD). The purpose of the present study was to determine the association between vitamin B1 consumption and the prevalence of late AMD in a representative US sample. METHODS: Data from the National Health and Nutrition Examination Survey (NHANES) between 2005 and 2008 were utilized for this cross-sectional analysis. The logistic regression model was used to evaluate the association between vitamin B1 consumption levels and late AMD. RESULTS: Our study included 5,107 people aged 40 years old and above. Vitamin B1 intake levels were inversely associated with the prevalence of late AMD, with OR being 0.40 (95% CI: 0.26-0.62), 0.53 (95% CI: 0.29-0.94), 0.55 (95% CI: 0.31-0.99) for the crude model 1, adjusted model 2, and fully adjusted model 3, respectively. CONCLUSION: Our study found that vitamin B1 intake levels were inversely associated with the prevalence of late AMD in the USA. Further randomized clinical trials among multiple centers are still warranted to investigate the longitudinal and causal relationship between vitamin B1 intake and late AMD.

Memory-based unsupervised video clinical quality assessment with multi-modality data in fetal ultrasound.

In obstetric sonography, the quality of acquisition of ultrasound scan video is crucial for accurate (manual or automated) biometric measurement and fetal health assessment. However, the nature of fetal ultrasound involves free-hand probe manipulation and this can make it challenging to capture high-quality videos for fetal biometry, especially for the less-experienced sonographer. Manually checking the quality of acquired videos would be time-consuming, subjective and requires a comprehensive understanding of fetal anatomy. Thus, it would be advantageous to develop an automatic quality assessment method to support video standardization and improve diagnostic accuracy of video-based analysis. In this paper, we propose a general and purely data-driven video-based quality assessment framework which directly learns a distinguishable feature representation from high-quality ultrasound videos alone, without anatomical annotations. Our solution effectively utilizes both spatial and temporal information of ultrasound videos. The spatio-temporal representation is learned by a bi-directional reconstruction between the video space and the feature space, enhanced by a key-query memory module proposed in the feature space. To further improve performance, two additional modalities are introduced in training which are the sonographer gaze and optical flow derived from the video. Two different clinical quality assessment tasks in fetal ultrasound are considered in our experiments, i.e., measurement of the fetal head circumference and cerebellar diameter; in both of these, low-quality videos are detected by the large reconstruction error in the feature space. Extensive experimental evaluation demonstrates the merits of our approach.

Corneal remodeling after SMILE for moderate and high myopia: short-term assessment of spatial changes in corneal volume and thickness.

PURPOSE: To evaluate the early corneal remodeling and its influencing factors after Small incision lenticule extraction (SMILE) for moderate and high myopia. METHODS: This was a retrospective study. Pre- and post-operative (1 week and 1, 3, 6 months) corneal volume (CV), mean keratometry (Km), and corneal thickness (CT) were measured by Scheimpflug tomography. CT at the central, thinnest point, and on concentric circles of 2, 4, and 6 mm diameter was recorded to assess corneal thickness spatial profile (CTSP) and percentage of thickness increase (PTI) in the moderate and high myopia groups, and to explore possible influencing factors. RESULTS: After SMILE, the peripheral CT decreased in the moderate myopia group and central corneal thickness (CCT) increased in the high myopia group at 1 month compared to 1 week (all P < 0.05). The CV, Km and CT were significantly increased at 3 months compared to 1 month (all P < 0.05), but there was no significant change at 6 months compared to 3 months for both groups (all P > 0.05). Patients with high myopia showed greater corneal thickness changes (△CT) and higher PTI than moderate myopia (all P < 0.05). Regression analysis revealed that in addition to refraction, peripheral PTI was negatively correlated with CCT in the moderate myopia group (4 mm: ß = -0.023, P = 0.001; 6 mm: ß = -0.050, P < 0.001), as well as in the high myopia group (4 mm: ß = -0.038, P < 0.001; 6 mm: ß = -0.094, P < 0.001). Moreover, peripheral PTI in the moderate myopia group was negatively correlated with age (4 mm: ß = -0.071, P = 0.003; 6 mm: ß = -0.162, P < 0.001). CONCLUSIONS: After SMILE, the CV, Km, and CTSP showed dynamic changes in the early stage, which stabilized after 3 months. Compared to the moderate myopia group, the high myopia group experienced slower corneal stabilization. The change in PTI at 6 months after SMILE may be related to higher preoperative refraction, thinner CCT and younger age.

The link between obesity and insulin resistance among children: Effects of key metabolites.

BACKGROUND: Childhood obesity became a severe public health challenge, and insulin resistance (IR) was one of the common complications. Both obesity and IR were considered as the basis of metabolic disorders. However, it is unclear which common key metabolites are associated with childhood obesity and IR. METHODS: The children were divided into normal weight and overweight/obese groups. Fasting blood glucose and fasting insulin were measured, and homeostasis model assessment of insulin resistance was calculated. Liquid chromatography-tandem mass spectrometry was applied for metabonomic analysis. Multiple linear regression analysis and correlation analysis explored the relationships between obesity, IR, and metabolites. Random forests were used to rank the importance of differential metabolites, and relative operating characteristic curves were used for prediction. RESULTS: A total of 88 normal-weight children and 171 obese/overweight children participated in the study. There was a significant difference between the two groups in 30 metabolites. Childhood obesity was significantly associated with 10 amino acid metabolites and 20 fatty acid metabolites. There were 12 metabolites significantly correlated with IR. The ranking of metabolites in random forest showed that glutamine, tyrosine, and alanine were important in amino acids, and pyruvic-ox-2, ethylmalonic-2, and phenyllactic-2 were important in fatty acids. The area under the curve of body mass index standard deviation  score (BMI-SDS) combined with key amino acid metabolites and fatty acid metabolites for predicting IR was 80.0% and 76.6%, respectively. CONCLUSIONS: There are common key metabolites related to IR and obese children, and these key metabolites combined with BMI-SDS could effectively predict the risk of IR.

Global Adaptive Transformer for Cross-Subject Enhanced EEG Classification.

Due to the individual difference, EEG signals from other subjects (source) can hardly be used to decode the mental intentions of the target subject. Although transfer learning methods have shown promising results, they still suffer from poor feature representation or neglect long-range dependencies. In light of these limitations, we propose Global Adaptive Transformer (GAT), an domain adaptation method to utilize source data for cross-subject enhancement. Our method uses parallel convolution to capture temporal and spatial features first. Then, we employ a novel attention-based adaptor that implicitly transfers source features to the target domain, emphasizing the global correlation of EEG features. We also use a discriminator to explicitly drive the reduction of marginal distribution discrepancy by learning against the feature extractor and the adaptor. Besides, an adaptive center loss is designed to align the conditional distribution. With the aligned source and target features, a classifier can be optimized to decode EEG signals. Experiments on two widely used EEG datasets demonstrate that our method outperforms state-of-the-art methods, primarily due to the effectiveness of the adaptor. These results indicate that GAT has good potential to enhance the practicality of BCI.

Concentrations and association between exposure to mixed perfluoroalkyl and polyfluoroalkyl substances and glycometabolism among adolescents.

BACKGROUND: Perfluoroalkyl and polyfluoroalkyl substances (PFASs) are widely used for industrial and commercial purposes and have received increasing attention due to their adverse effects on health. OBJECTIVE: To examine the relationship of serum PFAS and glycometabolism among adolescents based on the US National Health and Nutrition Examination Survey. METHODS: General linear regression models were applied to estimate the relationship between exposure to single PFAS and glycometabolism. Weighted quantile sum (WQS) regression models and Bayesian kernel machine regressions (BKMR) were used to assess the associations between multiple PFASs mixture exposure and glycometabolism. RESULTS: A total of 757 adolescents were enrolled. Multivariable regression model showed that Me-PFOSA-AcOH exposure was negatively associated with fasting blood glucose. WQS index showed that there was marginal negative correlation between multiple PFASs joint exposure and the homeostasis model of assessment for insulin resistance index (HOMA-IR) (ß = -0.26, p < .068), and PFHxS had the largest weight. BKMR models showed that PFASs mixture exposure were associated with decreased INS and HOMA-IR, and the exposure-response relationship had curvilinear shape. CONCLUSIONS: The increase in serum PFASs were associated with a decrease in HOMA-IR among adolescents. Mixed exposure models could more accurately and effectively reveal true exposure.Key MessagesThe detection rates of different PFAS contents in adolescent serum remained diverse.Adolescent serum PFASs had negative curvilinear correlation with INS and HOMA-IR levels.PFHxS had the highest weight in the associations between multiple PFASs and adolescent glycometabolism.

Automatic differentiation of ruptured and unruptured intracranial aneurysms on computed tomography angiography based on deep learning and radiomics.

OBJECTIVES: Rupture of intracranial aneurysm is very dangerous, often leading to death and disability. In this study, deep learning and radiomics techniques were used to automatically detect and differentiate ruptured and unruptured intracranial aneurysms. MATERIALS AND METHODS: 363 ruptured aneurysms and 535 unruptured aneurysms from Hospital 1 were included in the training set. 63 ruptured aneurysms and 190 unruptured aneurysms from Hospital 2 were used for independent external testing. Aneurysm detection, segmentation and morphological features extraction were automatically performed with a 3-dimensional convolutional neural network (CNN). Radiomic features were additionally computed via pyradiomics package. After dimensionality reduction, three classification models including support vector machines (SVM), random forests (RF), and multi-layer perceptron (MLP) were established and evaluated via area under the curve (AUC) of receiver operating characteristics. Delong tests were used for the comparison of different models. RESULTS: The 3-dimensional CNN automatically detected, segmented aneurysms and calculated 21 morphological features for each aneurysm. The pyradiomics provided 14 radiomics features. After dimensionality reduction, 13 features were found associated with aneurysm rupture. The AUCs of SVM, RF and MLP on the training dataset and external testing dataset were 0.86, 0.85, 0.90 and 0.85, 0.88, 0.86, respectively, for the discrimination of ruptured and unruptured intracranial aneurysms. Delong tests showed that there was no significant difference among the three models. CONCLUSIONS: In this study, three classification models were established to distinguish ruptured and unruptured aneurysms accurately. The aneurysms segmentation and morphological measurements were performed automatically, which greatly improved the clinical efficiency. CLINICAL RELEVANCE STATEMENT: Our fully automatic models could rapidly process the CTA data and evaluate the status of aneurysms in one minute.

Association between axial length and HDL in children: a hospital-based cross-sectional study.

BACKGROUND: To analyze the relationship between axial length and levels of high-density lipoprotein (HDL) cholesterol in children. METHODS: A retrospective, hospital-based cross-sectional research with 69 right eyes from 69 children who underwent health examination by Zhejiang Provincial People's Hospital was carried out. The participants were split into three groups: Group A (axial length < = 23 mm), Group B (axial length 23-24 mm), and Group C (axial length > 24 mm). Demographic epidemiological information, blood biochemical parameters and ophthalmic characteristics including refractive status and ocular geometric parameters were obtained and analyzed. RESULTS: 69 right eyes from 69 patients (25 males and 44 females) with a median age of 10.00 years old (IQR: 8.00-11.00 years) were included in the study. Within Group A, there were a total of 17 individuals; Group B consisted of 22 individuals; Group C included 30 individuals. The mean axial length of three groups was 22.148(0.360), 23.503(0.342) and 24.770(0.556) mm, respectively (p < 0.0001). The mean HDL levels were significantly different in three groups are 1.824(0.307), 1.485(0.253) and 1.507 (0.265) mmol/L, respectively. By applying a Pearson Coefficient, we evaluated the association between axial length and HDL and discovered that there was a statistically significant (p = 0.00025) and adverse (R = -0.43) association between axial length and HDL. CONCLUSIONS: We concluded from our study that there was a significantly inverse relationship between axial length and the levels of HDL in children.

Comparison of Aurolab Aqueous Drainage Implant with Ahmed Glaucoma Valve for Refractory Glaucoma: A Meta-Analysis.

BACKGROUND: Ahmed glaucoma valve (AGV) is a common surgical method for the treatment of refractory glaucoma.Aurolab aqueous drainage implant (AADI) is a novel surgical method which has been applied in clinical practice in recent years. OBJECTIVE: The purpose of this study was to compare the efficacy and safety of the AADI and the AGV for the treatment of refractory glaucoma. METHODS: We comprehensively searched four databases, including PubMed, Embase, Web of Science, and the Cochrane Library databases, selecting the relevant studies. The continuous variables, namely, intraocular pressure reduction (IOPR) and a reduction in antiglaucoma medication (AGMR), were pooled by the weighted mean differences (WMDs), and the dichotomous outcomes, including success rates and complications, were pooled by the odds ratio (OR). RESULTS: A total of 825 eyes from 820 patients from six studies were included. The WMDs of the IOPR between the AADI and the AGV implant were 0.58 (95% CI: 0.07-1.09) at 3 months, 0.44 (95% CI: 0.11-0.77) at 6 months, 2.20 (95% CI: 0.63-3.77) at 12 months, and 3.24 (95% CI: 1.73-4.75) at follow-up endpoint. Significant difference was detected between the two groups at any point in time. The WMDs of the AGMR between the AADI and the AGV implant were 0.87 (95% CI: 0.61-1.13) at 6 months, 1.04 (95% CI: 0.66-1.42) at 12 months, and 0.93 (95% CI: 0.52-1.34) at the follow-up endpoint; the differences reached statistical significance at any point in time. The pooled ORs comparing the AADI with the AGV were 3.64 (95% CI: 2.44-5.45) for the complete success rate and 1.72 (95% CI: 1.24-2.39) for qualified success rate; significant difference was detected between the two groups. There were no significant differences between the AADI and the AGV implant on the rates of adverse events. CONCLUSIONS: The AADI is more effective in both its surgical success rate and reducing IOP and AGM. And the two implants may have comparable incidences of adverse events.

A Promising Insight: The Potential Influence and Therapeutic Value of the Gut Microbiota in GI GVHD.

Allogeneic hematopoietic cell transplantation (allo-HSCT) is a reconstruction process of hematopoietic and immune functions that can be curative in patients with hematologic malignancies, but it carries risks of graft-versus-host disease (GVHD), thrombotic microangiopathy (TMA), Epstein-Barr virus (EBV) infection, cytomegalovirus infection, secondary hemophagocytic lymphohistiocytosis (sHLH), macrophage activation syndrome (MAS), bronchiolitis obliterans, and posterior reversible encephalopathy syndrome (PRES). Gastrointestinal graft-versus-host disease (GI GVHD), a common complication of allo-HSCT, is one of the leading causes of transplant-related death because of its high treatment difficulty, which is affected by preimplantation, antibiotic use, dietary changes, and intestinal inflammation. At present, human trials and animal studies have proven that a decrease in intestinal bacterial diversity is associated with the occurrence of GI GVHD. Metabolites produced by intestinal bacteria, such as lipopolysaccharides, short-chain fatty acids, and secondary bile acids, can affect the development of GVHD through direct or indirect interactions with immune cells. The targeted damage of GVHD on intestinal stem cells (ISCs) and Paneth cells results in intestinal dysbiosis or dysbacteriosis. Based on the effect of microbiota metabolites on the gastrointestinal tract, the clinical treatment of GI GVHD can be further optimized. In this review, we describe the mechanisms of GI GVHD and the damage it causes to intestinal cells and we summarize recent studies on the relationship between intestinal microbiota and GVHD in the gastrointestinal tract, highlighting the role of intestinal microbiota metabolites in GI GVHD. We hope to elucidate strategies for immunomodulatory combined microbiota targeting in the clinical treatment of GI GVHD.

Towards Unsupervised Ultrasound Video Clinical Quality Assessment with Multi-modality Data.

Video quality assurance is an important topic in obstetric ultrasound imaging to ensure that captured videos are suitable for biometry and fetal health assessment. Previously, one successful objective approach to automated ultrasound image quality assurance has considered it as a supervised learning task of detecting anatomical structures defined by a clinical protocol. In this paper, we propose an alternative and purely data-driven approach that makes effective use of both spatial and temporal information and the model learns from high-quality videos without any anatomy-specific annotations. This makes it attractive for potentially scalable generalisation. In the proposed model, a 3D encoder and decoder pair bi-directionally learns a spatio-temporal representation between the video space and the feature space. A zoom-in module is introduced to encourage the model to focus on the main object in a frame. A further design novelty is the introduction of two additional modalities in model training (sonographer gaze and optical flow derived from the video). Finally, our approach is applied to identify high-quality videos for fetal head circumference measurement in freehand second-trimester ultrasound scans. Extensive experiments are conducted, and the results demonstrate the effectiveness of our approach with an AUC of 0.911.

EEG Conformer: Convolutional Transformer for EEG Decoding and Visualization.

Due to the limited perceptual field, convolutional neural networks (CNN) only extract local temporal features and may fail to capture long-term dependencies for EEG decoding. In this paper, we propose a compact Convolutional Transformer, named EEG Conformer, to encapsulate local and global features in a unified EEG classification framework. Specifically, the convolution module learns the low-level local features throughout the one-dimensional temporal and spatial convolution layers. The self-attention module is straightforwardly connected to extract the global correlation within the local temporal features. Subsequently, the simple classifier module based on fully-connected layers is followed to predict the categories for EEG signals. To enhance interpretability, we also devise a visualization strategy to project the class activation mapping onto the brain topography. Finally, we have conducted extensive experiments to evaluate our method on three public datasets in EEG-based motor imagery and emotion recognition paradigms. The experimental results show that our method achieves state-of-the-art performance and has great potential to be a new baseline for general EEG decoding. The code has been released in https://github.com/eeyhsong/EEG-Conformer.

IL-10 -1082 A/G polymorphism is related with the risk and clinical characteristics of acute kidney injury: a case-control study.

BACKGROUND: Interleukin-10 (IL-10), a kind of anti-inflammation cytokine, has a key role in the development of acute kidney injury (AKI). Recently, several studies addressed the link between the risk of AKI and the IL-10 -1082 A/G polymorphism with conflicting findings. METHODS: To identify the effects of the IL-10 -1082 A/G polymorphism on the risk of AKI, we designed this case-control study. This study recruited 320 AKI patients and 408 ICU patients without AKI. The association between the AKI risk and this polymorphism was analyzed using the logistic regression analysis adjusted for confounding factors. RESULTS: The IL-10 -1082 A/G polymorphism enhanced the risk of AKI. After stratified analysis, this polymorphism increased the risk of AKI among the males, smokers, those aged exceeding 60 years old, and overweight individuals (BMI ≥ 25). Moreover, -1082 A/G polymorphism was remarkably related with APACHE II score and eGFR. CONCLUSIONS: Collectively, the IL-10 -1082 A/G polymorphism is linked with an elevated risk of AKI. Further studies in China need be performed to verify these results.

Repositioning of the Severe Prolapsed Silicone Tubes after Bicanalicular Nasal Intubation: A Novel Technique.

BACKGROUND: Bicanalicular nasal intubation is widely used in lacrimal drainage system surgery. Its common complication is lateral displacement or spontaneous prolapse. When the distal part of the silicone tubes cannot be seen in the nose endoscopically, either repositioning or removal could be a challenge. We developed a simple technique to reposition the severe prolapsed silicone tubes. METHOD: This retrospective study included 6 patients with severe prolapsed silicone tubes who had undergone bicanalicular nasal intubation between January 2017 and December 2019. We used a memory wire probe to pull a nylon suture through the lacrimal passage retrograde. Then, the nylon suture was cut into two lines. One line was coiled to the prolapsed tube and tied to another line. This nylon turned into a "lasso" to capture the silicone tube and then lock its knot. By pulling the nylon suture, the severe prolapsed silicone tube was repositioned to the nasal cavity. RESULTS: Using this technique, we successfully repositioned severe prolapsed silicone tubes without any complication in 6 cases. CONCLUSIONS: Silicone tube reposition guiding by using a memory wire probe is an optional technique in the treatment of prolapse of silicone tubes, particularly if the distal part of the silicon tube was embedded in the lacrimal sac and cannot be seen in the nose by endoscopy. It is a feasible, minimally invasive, safe, and effective method, avoiding premature tube removal.

Dynamic Joint Domain Adaptation Network for Motor Imagery Classification.

Electroencephalogram (EEG) has been widely used in brain computer interface (BCI) due to its convenience and reliability. The EEG-based BCI applications are majorly limited by the time-consuming calibration procedure for discriminative feature representation and classification. Existing EEG classification methods either heavily depend on the handcrafted features or require adequate annotated samples at each session for calibration. To address these issues, we propose a novel dynamic joint domain adaptation network based on adversarial learning strategy to learn domain-invariant feature representation, and thus improve EEG classification performance in the target domain by leveraging useful information from the source session. Specifically, we explore the global discriminator to align the marginal distribution across domains, and the local discriminator to reduce the conditional distribution discrepancy between sub-domains via conditioning on deep representation as well as the predicted labels from the classifier. In addition, we further investigate a dynamic adversarial factor to adaptively estimate the relative importance of alignment between the marginal and conditional distributions. To evaluate the efficacy of our method, extensive experiments are conducted on two public EEG datasets, namely, Datasets IIa and IIb of BCI Competition IV. The experimental results demonstrate that the proposed method achieves superior performance compared with the state-of-the-art methods.

Multitask Feature Learning Meets Robust Tensor Decomposition for EEG Classification.

In this article, we study a tensor-based multitask learning (MTL) method for classification. Taking into account the fact that in many real-world applications, the given training samples are limited and can be inherently arranged into multidimensional arrays (tensors), we are motivated by the advantages of MTL, where the shared structural information among related tasks can be leveraged to produce better generalization performance. We propose a regularized tensor-based MTL method for joint feature selection and classification. For feature selection, we employ the Fisher discriminant criterion to both select discriminative features and control the within-class nonstationarity. For classification, we take both shared and task-specific structural information into consideration. We decompose the regression tensor for each task into a linear combination of a shared tensor and a task-specific tensor and propose a composite tensor norm. Specifically, we use the scaled latent trace norm for regularizing the shared tensor and the l1 -norm for task-specific tensor. Further, we give a computationally efficient optimization algorithm based on the alternating direction method of multipliers (ADMMs) to tackle the joint learning of discriminative features and multitask classification. The experimental results on real electroencephalography (EEG) datasets demonstrate the superiority of our method over the state-of-the-art techniques.

Deep Representation-Based Domain Adaptation for Nonstationary EEG Classification.

In the context of motor imagery, electroencephalography (EEG) data vary from subject to subject such that the performance of a classifier trained on data of multiple subjects from a specific domain typically degrades when applied to a different subject. While collecting enough samples from each subject would address this issue, it is often too time-consuming and impractical. To tackle this problem, we propose a novel end-to-end deep domain adaptation method to improve the classification performance on a single subject (target domain) by taking the useful information from multiple subjects (source domain) into consideration. Especially, the proposed method jointly optimizes three modules, including a feature extractor, a classifier, and a domain discriminator. The feature extractor learns the discriminative latent features by mapping the raw EEG signals into a deep representation space. A center loss is further employed to constrain an invariant feature space and reduce the intrasubject nonstationarity. Furthermore, the domain discriminator matches the feature distribution shift between source and target domains by an adversarial learning strategy. Finally, based on the consistent deep features from both domains, the classifier is able to leverage the information from the source domain and accurately predict the label in the target domain at the test time. To evaluate our method, we have conducted extensive experiments on two real public EEG data sets, data set IIa, and data set IIb of brain-computer interface (BCI) Competition IV. The experimental results validate the efficacy of our method. Therefore, our method is promising to reduce the calibration time for the use of BCI and promote the development of BCI.