Unsupervised heterogeneous domain adaptation for EEG classification.

Objective.Domain adaptation has been recognized as a potent solution to the challenge of limited training data for electroencephalography (EEG) classification tasks. Existing studies primarily focus on homogeneous environments, however, the heterogeneous properties of EEG data arising from device diversity cannot be overlooked. This motivates the development of heterogeneous domain adaptation methods that can fully exploit the knowledge from an auxiliary heterogeneous domain for EEG classification.Approach.In this article, we propose a novel model named informative representation fusion (IRF) to tackle the problem of unsupervised heterogeneous domain adaptation in the context of EEG data. In IRF, we consider different perspectives of data, i.e. independent identically distributed (iid) and non-iid, to learn different representations. Specifically, from the non-iid perspective, IRF models high-order correlations among data by hypergraphs and develops hypergraph encoders to obtain data representations of each domain. From the non-iid perspective, by applying multi-layer perceptron networks to the source and target domain data, we achieve another type of representation for both domains. Subsequently, an attention mechanism is used to fuse these two types of representations to yield informative features. To learn transferable representations, the maximum mean discrepancy is utilized to align the distributions of the source and target domains based on the fused features.Main results.Experimental results on several real-world datasets demonstrate the effectiveness of the proposed model.Significance.This article handles an EEG classification situation where the source and target EEG data lie in different spaces, and what's more, under an unsupervised learning setting. This situation is practical in the real world but barely studied in the literature. The proposed model achieves high classification accuracy, and this study is important for the commercial applications of EEG-based BCIs.

VSSI-GGD: A Variation Sparse EEG Source Imaging Approach Based on Generalized Gaussian Distribution.

Electroencephalographic (EEG) source imaging (ESI) is a powerful method for studying brain functions and surgical resection of epileptic foci. However, accurately estimating the location and extent of brain sources remains challenging due to noise and background interference in EEG signals. To reconstruct extended brain sources, we propose a new ESI method called Variation Sparse Source Imaging based on Generalized Gaussian Distribution (VSSI-GGD). VSSI-GGD uses the generalized Gaussian prior as a sparse constraint on the spatial variation domain and embeds it into the Bayesian framework for source estimation. Using a variational technique, we approximate the intractable true posterior with a Gaussian density. Through convex analysis, the Bayesian inference problem is transformed entirely into a series of regularized L2p -norm ( ) optimization problems, which are efficiently solved with the ADMM algorithm. Imaging results of numerical simulations and human experimental dataset analysis reveal the superior performance of VSSI-GGD, which provides higher spatial resolution with clear boundaries compared to benchmark algorithms. VSSI-GGD can potentially serve as an effective and robust spatiotemporal EEG source imaging method. The source code of VSSI-GGD is available at https://github.com/Mashirops/VSSI-GGD.git.

A Multi-Domain Convolutional Neural Network for EEG-Based Motor Imagery Decoding.

Motor imagery (MI) decoding plays a crucial role in the advancement of electroencephalography (EEG)-based brain-computer interface (BCI) technology. Currently, most researches focus on complex deep learning structures for MI decoding. The growing complexity of networks may result in overfitting and lead to inaccurate decoding outcomes due to the redundant information. To address this limitation and make full use of the multi-domain EEG features, a multi-domain temporal-spatial-frequency convolutional neural network (TSFCNet) is proposed for MI decoding. The proposed network provides a novel mechanism that utilize the spatial and temporal EEG features combined with frequency and time-frequency characteristics. This network enables powerful feature extraction without complicated network structure. Specifically, the TSFCNet first employs the MixConv-Residual block to extract multiscale temporal features from multi-band filtered EEG data. Next, the temporal-spatial-frequency convolution block implements three shallow, parallel and independent convolutional operations in spatial, frequency and time-frequency domain, and captures high discriminative representations from these domains respectively. Finally, these features are effectively aggregated by average pooling layers and variance layers, and the network is trained with the joint supervision of the cross-entropy and the center loss. Our experimental results show that the TSFCNet outperforms the state-of-the-art models with superior classification accuracy and kappa values (82.72% and 0.7695 for dataset BCI competition IV 2a, 86.39% and 0.7324 for dataset BCI competition IV 2b). These competitive results demonstrate that the proposed network is promising for enhancing the decoding performance of MI BCIs.

SincMSNet: a Sinc filter convolutional neural network for EEG motor imagery classification.

Objective.Motor imagery (MI) is widely used in brain-computer interfaces (BCIs). However, the decode of MI-EEG using convolutional neural networks (CNNs) remains a challenge due to individual variability.Approach.We propose a fully end-to-end CNN called SincMSNet to address this issue. SincMSNet employs the Sinc filter to extract subject-specific frequency band information and utilizes mixed-depth convolution to extract multi-scale temporal information for each band. It then applies a spatial convolutional block to extract spatial features and uses a temporal log-variance block to obtain classification features. The model of SincMSNet is trained under the joint supervision of cross-entropy and center loss to achieve inter-class separable and intra-class compact representations of EEG signals.Main results.We evaluated the performance of SincMSNet on the BCIC-IV-2a (four-class) and OpenBMI (two-class) datasets. SincMSNet achieves impressive results, surpassing benchmark methods. In four-class and two-class inter-session analysis, it achieves average accuracies of 80.70% and 71.50% respectively. In four-class and two-class single-session analysis, it achieves average accuracies of 84.69% and 76.99% respectively. Additionally, visualizations of the learned band-pass filter bands by Sinc filters demonstrate the network's ability to extract subject-specific frequency band information from EEG.Significance.This study highlights the potential of SincMSNet in improving the performance of MI-EEG decoding and designing more robust MI-BCIs. The source code for SincMSNet can be found at:https://github.com/Want2Vanish/SincMSNet.

Sparse Bayesian Learning for End-to-End EEG Decoding.

Decoding brain activity from non-invasive electroencephalography (EEG) is crucial for brain-computer interfaces (BCIs) and the study of brain disorders. Notably, end-to-end EEG decoding has gained widespread popularity in recent years owing to the remarkable advances in deep learning research. However, many EEG studies suffer from limited sample sizes, making it difficult for existing deep learning models to effectively generalize to highly noisy EEG data. To address this fundamental limitation, this paper proposes a novel end-to-end EEG decoding algorithm that utilizes a low-rank weight matrix to encode both spatio-temporal filters and the classifier, all optimized under a principled sparse Bayesian learning (SBL) framework. Importantly, this SBL framework also enables us to learn hyperparameters that optimally penalize the model in a Bayesian fashion. The proposed decoding algorithm is systematically benchmarked on five motor imagery BCI EEG datasets ( N=192) and an emotion recognition EEG dataset ( N=45), in comparison with several contemporary algorithms, including end-to-end deep-learning-based EEG decoding algorithms. The classification results demonstrate that our algorithm significantly outperforms the competing algorithms while yielding neurophysiologically meaningful spatio-temporal patterns. Our algorithm therefore advances the state-of-the-art by providing a novel EEG-tailored machine learning tool for decoding brain activity.

Bayesian Uncertainty Modeling for P300-Based Brain-Computer Interface.

P300 potential is important to cognitive neuroscience research, and has also been widely applied in brain-computer interfaces (BCIs). To detect P300, many neural network models, including convolutional neural networks (CNNs), have achieved outstanding results. However, EEG signals are usually high-dimensional. Moreover, since collecting EEG signals is time-consuming and expensive, EEG datasets are typically small. Therefore, data-sparse regions usually exist within EEG dataset. However, most existing models compute predictions based on point-estimate. They cannot evaluate prediction uncertainty and tend to make overconfident decisions on samples located in data-sparse regions. Hence, their predictions are unreliable. To solve this problem, we propose a Bayesian convolutional neural network (BCNN) for P300 detection. The network places probability distributions over weights to capture model uncertainty. In prediction phase, a set of neural networks can be obtained by Monte Carlo sampling. Integrating the predictions of these networks implies ensembling. Therefore, the reliability of prediction can be improved. Experimental results demonstrate that BCNN can achieve better P300 detection performance than point-estimate networks. In addition, placing a prior distribution over the weight acts as a regularization technique. Experimental results show that it improves the robustness of BCNN to overfitting on small dataset. More importantly, with BCNN, both weight uncertainty and prediction uncertainty can be obtained. The weight uncertainty is then used to optimize the network through pruning, and the prediction uncertainty is applied to reject unreliable decisions so as to reduce detection error. Therefore, uncertainty modeling provides important information to further improve BCI systems.

Robust Bayesian Estimation of EEG-Based Brain Causality Networks.

OBJECTIVE: The multivariate autoregression (MVAR) model is an effective model to construct brain causality networks. However, the accuracy of MVAR parameter estimation is considerably affected by outliers such as head movements and eye blinks contained in EEG signals, especially in short time windows. METHODS: We proposed a robust MVAR parameter estimation method based on a Bayesian probabilistic framework and Laplace fitting error known as Lap-SBL. With the Bayesian inference framework, we can accurately estimate the MVAR parameters under short time windows. Additionally, to alleviate the influence of outliers, we model the fitting error using the Laplace distribution instead of the typical Gaussian distribution. We employ convex analysis to model the inference task by approximating the Laplace noise prior with a maximum over Gaussian functions with varying scales. The variational inference approach was used to efficiently estimate the MVAR parameters. RESULTS: The numerical results suggest that the proposed method obtains less parameter estimation bias and more consistent linkages than existing benchmark methods, i.e., LS, LASSO, LAPPS and SBL. The motor imagery experimental data analysis shows that Lap-SBL can better describe the lateralization characteristics of brain network. This lateralization is less apparent in a subject with poor MI classification accuracy. CONCLUSION AND SIGNIFICANCE: Lap-SBL effectively suppresses the influence of outliers and recovers reliable networks in the presence of outliers and short time windows.

WRA-MTSI: A Robust Extended Source Imaging Algorithm Based on Multi-Trial EEG.

OBJECTIVE: Reconstructing brain activities from electroencephalography (EEG) signals is crucial for studying brain functions and their abnormalities. However, since EEG signals are nonstationary and vulnerable to noise, brain activities reconstructed from single-trial EEG data are often unstable, and significant variability may occur across different EEG trials even for the same cognitive task. METHODS: In an effort to leverage the shared information across the EEG data of multiple trials, this paper proposes a multi-trial EEG source imaging method based on Wasserstein regularization, termed WRA-MTSI. In WRA-MTSI, Wasserstein regularization is employed to perform multi-trial source distribution similarity learning, and the structured sparsity constraint is enforced to enable accurate estimation of the source extents, locations and time series. The resulting optimization problem is solved by a computationally efficient algorithm based on the alternating direction method of multipliers (ADMM). RESULTS: Both numerical simulations and real EEG data analysis demonstrate that WRA-MTSI outperforms existing single-trial ESI methods (e.g., wMNE, LORETA, SISSY, and SBL) in mitigating the influence of artifacts in EEG data. Moreover, WRA-MTSI yields superior performance compared to other state-of-the-art multi-trial ESI methods (e.g., group lasso, the dirty model, and MTW) in estimating source extents. CONCLUSION AND SIGNIFICANCE: WRA-MTSI may serve as an effective robust EEG source imaging method in the presence of multi-trial noisy EEG data.

FBMSNet: A Filter-Bank Multi-Scale Convolutional Neural Network for EEG-Based Motor Imagery Decoding.

OBJECT: Motor imagery (MI) is a mental process widely utilized as the experimental paradigm for brain-computer interfaces (BCIs) across a broad range of basic science and clinical studies. However, decoding intentions from MI remains challenging due to the inherent complexity of brain patterns relative to the small sample size available for machine learning. APPROACH: This paper proposes an end-to-end Filter-Bank Multiscale Convolutional Neural Network (FBMSNet) for MI classification. A filter bank is first employed to derive a multiview spectral representation of the EEG data. Mixed depthwise convolution is then applied to extract temporal features at multiple scales, followed by spatial filtering to mitigate volume conduction. Finally, with the joint supervision of cross-entropy and center loss, FBMSNet obtains features that maximize interclass dispersion and intraclass compactness. MAIN RESULTS: We compare FBMSNet with several state-of-the-art EEG decoding methods on two MI datasets: the BCI Competition IV 2a dataset and the OpenBMI dataset. FBMSNet significantly outperforms the benchmark methods by achieving 79.17% and 70.05% for four-class and two-class hold-out classification accuracy, respectively. SIGNIFICANCE: These results demonstrate the efficacy of FBMSNet in improving EEG decoding performance toward more robust BCI applications. The FBMSNet source code is available at https://github.com/Want2Vanish/FBMSNet.

Intermediate Sensory Feedback Assisted Multi-Step Neural Decoding for Reinforcement Learning Based Brain-Machine Interfaces.

Reinforcement-learning (RL)-based brain-machine interfaces (BMIs) interpret dynamic neural activity into movement intention without patients' real limb movements, which is promising for clinical applications. A movement task generally requires the subjects to reach the target within one step and rewards the subjects instantaneously. However, a real BMI scenario involves tasks that require multiple steps, during which sensory feedback is provided to indicate the status of the prosthesis, and the reward is only given at the end of the trial. Actually, subjects internally evaluate the sensory feedback to adjust motor activity. Existing RL-BMI tasks have not fully utilized the internal evaluation from the brain upon the sensory feedback to guide the decoder training, and there lacks an effective tool to assign credit for the multi-step decoding task. We propose first to extract intermediate guidance from the medial prefrontal cortex (mPFC) to assist the learning of multi-step decoding in an RL framework. To effectively explore the neural-action mapping in a large state-action space, a temporal difference (TD) method is incorporated into quantized attention-gated kernel reinforcement learning (QAGKRL) to assign the credit over the temporal sequence of movement, but also discriminate spatially in the Reproducing Kernel Hilbert Space (RKHS). We test our approach on the data collected from the primary motor cortex (M1) and the mPFC of rats when they brain control the cursor to reach the target within multiple steps. Compared with the models which only utilize the final reward, the intermediate evaluation interpreted from the mPFC can help improve the prediction accuracy by 10.9% on average across subjects, with faster convergence and more stability. Moreover, our proposed algorithm further increases 18.2% decoding accuracy compared with existing TD-RL methods. The results reveal the possibility of achieving better multi-step decoding performance for more complicated BMI tasks.

SPD-CNN: A plain CNN-based model using the symmetric positive definite matrices for cross-subject EEG classification with meta-transfer-learning.

The electroencephalography (EEG) signals are easily contaminated by various artifacts and noise, which induces a domain shift in each subject and significant pattern variability among different subjects. Therefore, it hinders the improvement of EEG classification accuracy in the cross-subject learning scenario. Convolutional neural networks (CNNs) have been extensively applied to EEG-based Brain-Computer Interfaces (BCIs) by virtue of the capability of performing automatic feature extraction and classification. However, they have been mainly applied to the within-subject classification which would consume lots of time for training and calibration. Thus, it limits the further applications of CNNs in BCIs. In order to build a robust classification algorithm for a calibration-less BCI system, we propose an end-to-end model that transforms the EEG signals into symmetric positive definite (SPD) matrices and captures the features of SPD matrices by using a CNN. To avoid the time-consuming calibration and ensure the application of the proposed model, we use the meta-transfer-learning (MTL) method to learn the essential features from different subjects. We validate our model by making extensive experiments on three public motor-imagery datasets. The experimental results demonstrate the effectiveness of our proposed method in the cross-subject learning scenario.

Exploiting Data Uncertainty for Improving the Performance of a Quantitative Analysis Model for Laser-Induced Breakdown Spectroscopy.

The accuracy and precision of laser-induced breakdown spectroscopy (LIBS) quantitative analysis are significantly limited by the spectral noise. Normalization and ensemble averaging of multiple spectra were often used to preprocess spectra. However, these methods cannot completely remove the spectral noise. Data uncertainty due to the irremovable spectral noise will affect LIBS quantitative analysis. Therefore, this paper proposes a method using data uncertainty to improve the performance of LIBS quantitative analysis. The proposed method uses several spectra to characterize each sample to preserve some data uncertainty in the calibration data matrix. Thus, the data uncertainty is used to optimize the calibration model for improving the toleration to the spectral signal variation. As a result, the optimized calibration model had better accuracy and robustness than the calibration model trained by conventional method. The best root mean square error of prediction (RMSEP) of the ash content of coal was 1.152% for the optimized calibration model, while that for the conventional calibration model was 1.718%. The optimized calibration model also showed a lower relative standard deviation (RSD) value of repeated predictions. Moreover, the calibration model for predicting the ash content in biomass was also optimized by the proposed method. The optimized calibration model outperformed the conventional calibration model again, which demonstrated the extensive applicability of the proposed method.

Toward Assessment of Sound Localization in Disorders of Consciousness Using a Hybrid Audiovisual Brain-Computer Interface.

Behavioral assessment of sound localization in the Coma Recovery Scale-Revised (CRS-R) poses a significant challenge due to motor disability in patients with disorders of consciousness (DOC). Brain-computer interfaces (BCIs), which can directly detect brain activities related to external stimuli, may thus provide an approach to assess DOC patients without the need for any physical behavior. In this study, a novel audiovisual BCI system was developed to simulate sound localization evaluation in CRS-R. Specifically, there were two alternatively flashed buttons on the left and right sides of the graphical user interface, one of which was randomly chosen as the target. The auditory stimuli of bell sounds were simultaneously presented by the ipsilateral loudspeaker during the flashing of the target button, which prompted patients to selectively attend to the target button. The recorded electroencephalography data were analyzed in real time to detect event-related potentials evoked by the target and further to determine whether the target was attended to or not. A significant BCI accuracy for a patient implied that he/she had sound localization. Among eighteen patients, eleven and four showed sound localization in the BCI and CRS-R, respectively. Furthermore, all patients showing sound localization in the CRS-R were among those detected by our BCI. The other seven patients who had no sound localization behavior in CRS-R were identified by the BCI assessment, and three of them showed improvements in the second CRS-R assessment after the BCI experiment. Thus, the proposed BCI system is promising for assisting the assessment of sound localization and improving the clinical diagnosis of DOC patients.

Representation Learning for Dynamic Functional Connectivities via Variational Dynamic Graph Latent Variable Models.

Latent variable models (LVMs) for neural population spikes have revealed informative low-dimensional dynamics about the neural data and have become powerful tools for analyzing and interpreting neural activity. However, these approaches are unable to determine the neurophysiological meaning of the inferred latent dynamics. On the other hand, emerging evidence suggests that dynamic functional connectivities (DFC) may be responsible for neural activity patterns underlying cognition or behavior. We are interested in studying how DFC are associated with the low-dimensional structure of neural activities. Most existing LVMs are based on a point process and fail to model evolving relationships. In this work, we introduce a dynamic graph as the latent variable and develop a Variational Dynamic Graph Latent Variable Model (VDGLVM), a representation learning model based on the variational information bottleneck framework. VDGLVM utilizes a graph generative model and a graph neural network to capture dynamic communication between nodes that one has no access to from the observed data. The proposed computational model provides guaranteed behavior-decoding performance and improves LVMs by associating the inferred latent dynamics with probable DFC.

Validation and Diagnostic Performance of a CFD-Based Non-invasive Method for the Diagnosis of Aortic Coarctation.

Purpose: The clinical diagnosis of aorta coarctation (CoA) constitutes a challenge, which is usually tackled by applying the peak systolic pressure gradient (PSPG) method. Recent advances in computational fluid dynamics (CFD) have suggested that multi-detector computed tomography angiography (MDCTA)-based CFD can serve as a non-invasive PSPG measurement. The aim of this study was to validate a new CFD method that does not require any medical examination data other than MDCTA images for the diagnosis of CoA. Materials and methods: Our study included 65 pediatric patients (38 with CoA, and 27 without CoA). All patients underwent cardiac catheterization to confirm if they were suffering from CoA or any other congenital heart disease (CHD). A series of boundary conditions were specified and the simulated results were combined to obtain a stenosis pressure-flow curve. Subsequently, we built a prediction model and evaluated its predictive performance by considering the AUC of the ROC by 5-fold cross-validation. Results: The proposed MDCTA-based CFD method exhibited a good predictive performance in both the training and test sets (average AUC: 0.948 vs. 0.958; average accuracies: 0.881 vs. 0.877). It also had a higher predictive accuracy compared with the non-invasive criteria presented in the European Society of Cardiology (ESC) guidelines (average accuracies: 0.877 vs. 0.539). Conclusion: The new non-invasive CFD-based method presented in this work is a promising approach for the accurate diagnosis of CoA, and will likely benefit clinical decision-making.

Deep Temporal-Spatial Feature Learning for Motor Imagery-Based Brain-Computer Interfaces.

Motor imagery (MI) decoding is an important part of brain-computer interface (BCI) research, which translates the subject's intentions into commands that external devices can execute. The traditional methods for discriminative feature extraction, such as common spatial pattern (CSP) and filter bank common spatial pattern (FBCSP), have only focused on the energy features of the electroencephalography (EEG) and thus ignored the further exploration of temporal information. However, the temporal information of spatially filtered EEG may be critical to the performance improvement of MI decoding. In this paper, we proposed a deep learning approach termed filter-bank spatial filtering and temporal-spatial convolutional neural network (FBSF-TSCNN) for MI decoding, where the FBSF block transforms the raw EEG signals into an appropriate intermediate EEG presentation, and then the TSCNN block decodes the intermediate EEG signals. Moreover, a novel stage-wise training strategy is proposed to mitigate the difficult optimization problem of the TSCNN block in the case of insufficient training samples. Firstly, the feature extraction layers are trained by optimization of the triplet loss. Then, the classification layers are trained by optimization of the cross-entropy loss. Finally, the entire network (TSCNN) is fine-tuned by the back-propagation (BP) algorithm. Experimental evaluations on the BCI IV 2a and SMR-BCI datasets reveal that the proposed stage-wise training strategy yields significant performance improvement compared with the conventional end-to-end training strategy, and the proposed approach is comparable with the state-of-the-art method.

Novel Convolutional Neural Network with Variational Information Bottleneck for P300 Detection.

In the area of brain-computer interfaces (BCI), the detection of P300 is a very important technique and has a lot of applications. Although this problem has been studied for decades, it is still a tough problem in electroencephalography (EEG) signal processing owing to its high dimension features and low signal-to-noise ratio (SNR). Recently, neural networks, like conventional neural networks (CNN), has shown excellent performance on many applications. However, standard convolutional neural networks suffer from performance degradation on dealing with noisy data or data with too many redundant information. In this paper, we proposed a novel convolutional neural network with variational information bottleneck for P300 detection. Wiht the CNN architecture and information bottleneck, the proposed network termed P300-VIB-Net could remove the redundant information in data effectively. The experimental results on BCI competition data sets show that P300-VIB-Net achieves cutting-edge character recognition performance. Furthermore, the proposed model is capable of restricting the flow of irrelevant information adaptively in the network from perspective of information theory. The experimental results show that P300-VIB-Net is a promising tool for P300 detection.

A Robust Direction of Arrival Estimation Method for Uniform Circular Array.

Estimating the Direction of Arrival (DOA) is a basic and crucial problem in array signal processing. The existing DOA methods fail to obtain reliable and accurate results when noise and reverberation occur in real applications. In this paper, an accurate and robust estimation method for estimating the DOA of sources signal is proposed. Incorporating the Estimating Signal Parameters via Rotational Invariance Techniques (ESPRIT) algorithm with the RANdom SAmple Consensus (RANSAC) algorithm gives rise to the RAN-ESPRIT method, which removes outliers automatically in noise-corrupted environments. In this work, a uniform circular array (UCA) is converted into a virtual uniform linear array (ULA) to begin with. Then, the covariance matrix of the received signals of the virtual linear array is reconstructed, and the ESPRIT algorithm is deployed to estimate initial DOA of the source signal. Finally, the modified RANSAC method with automatically selected thresholds is used to fit the source signal to obtain accurate DOA. The proposed method can remove the unreliable DOA feature data and leads to more accuracy of DOA estimation of source signals in reverberation environments. Experimental results demonstrate that the proposed method is more robust and efficient compared to the traditional methods (i.e., ESPRIT, TLS-ESPRIT).

Using machine learning to predict one-year cardiovascular events in patients with severe dilated cardiomyopathy.

PURPOSE: Dilated cardiomyopathy (DCM) is a common form of cardiomyopathy and it is associated with poor outcomes. A poor prognosis of DCM patients with low ejection fraction has been noted in the short-term follow-up. Machine learning (ML) could aid clinicians in risk stratification and patient management after considering the correlation between numerous features and the outcomes. The present study aimed to predict the 1-year cardiovascular events in patients with severe DCM using ML, and aid clinicians in risk stratification and patient management. MATERIALS AND METHODS: The dataset used to establish the ML model was obtained from 98 patients with severe DCM (LVEF < 35%) from two centres. Totally 32 features from clinical data were input to the ML algorithm, and the significant features highly relevant to the cardiovascular events were selected by Information gain (IG). A naive Bayes classifier was built, and its predictive performance was evaluated using the area under the curve (AUC) of the receiver operating characteristics by 10-fold cross-validation. RESULTS: During the 1-year follow-up, a total of 22 patients met the criterion of the study end-point. The top features with IG > 0.01 were selected for ML model, including left atrial size (IG = 0.240), QRS duration (IG = 0.200), and systolic blood pressure (IG = 0.151). ML performed well in predicting cardiovascular events in patients with severe DCM (AUC, 0.887 [95% confidence interval, 0.813-0.961]). CONCLUSIONS: ML effectively predicted risk in patients with severe DCM in 1-year follow-up, and this may direct risk stratification and patient management in the future.

A Brain-Computer Interface Based on Three-Dimensional Stereo Stimuli for Assisting Clinical Object Recognition Assessment in Patients With Disorders of Consciousness.

The coma recovery scale-revised (CRS-R) behavioral scale is commonly used for the clinical evaluation of patients with disorders of consciousness (DOC). However, since DOC patients generally cannot supply stable and efficient behavioral responses to external stimulation, evaluation results based on behavioral scales are not sufficiently accurate. In this paper, we proposed a novel brain-computer interface (BCI) based on 3D stereo audiovisual stimuli to supplement object recognition evaluation in the CRS-R. During the experiment, subjects needed to follow the instructions and to focus on the target object on the screen, whereas EEG data were recorded and analyzed in real time to determine the object of focus, and the detection result was output as feedback. Thirteen DOC patients participated in the object recognition assessments using the 3D audiovisual BCI and CRS-R. None of the patients showed object recognition function in the CRS-R assessment before the BCI experiment. However, six of these DOC patients achieved accuracies that were significantly higher than the chance level in the BCI-based assessment, indicating the successful detection of object recognition function in these six patients using our 3D audiovisual BCI system. These results suggest that the BCI method may provide a more sensitive object recognition evaluation compared with CRS-R and may be used to assist clinical CRS-R for DOC patients.