Abstract Objective. Electroencephalogram (EEG) features are important objective markers for diagnostic and prognostic evaluation of prolonged disorders of consciousness (DOC). However, task-based EEG paradigms are limited by mismatches between task demands and patients' residual awareness, as well as the limited individual assessment capacity of machine-learning-based detection frameworks. Approach. In this study, we proposed a lowdemand DOC detection strategy by decoding expectations of global regularities in sequence auditory stimulation using a modified local-global paradigm. Three single-trial classification frameworks using canonical correlation analysis, principal component analysis, and xDAWN for feature extraction were developed for individualized detection of global-regularity expectations. We further established awareness evaluation criteria based on single-trial classification outcomes and evaluated their diagnostic and prognostic effectiveness in a DOC experiment. Main results. Experiments in healthy participants demonstrated that the principal components of event-related potentials associated with global regularities were preserved under the proposed detection strategy. Compared with the original local-global paradigm, this strategy significantly improved single-trial classification performance for global effects by up to 15%. Electrophysiological analyses indicated that this improvement was driven by larger EEG response differences for global effects and more stable trial-to-trial neural states. In a cohort of 20 DOC patients, the proposed evaluation criteria achieved an individual diagnostic balanced accuracy of 68.8% (sensitivity = 50%; specificity = 87.5%), and a prognostic balanced accuracy of 60.5% (sensitivity = 50%; specificity = 71%). Significance. These findings demonstrate that decoding sequential auditory expectations enables effective low-
Abstract Objective. Stroke represents one of the leading causes of long-term motor dysfunction on a global scale. Existing motor imagery (MI) brain-computer interface (BCI) rehabilitation training systems face critical challenges of suboptimal patient engagement and limited electroencephalography (EEG) feature decoding capacity. To overcome these challenges, this study presents two primary original contributions: an independently designed wearable augmented reality (AR) MI training paradigm and a novel Euclidean Alignment-based Dynamic Graph Convolutional Neural Network (EA-DGCNN) end-to-end decoding architecture. Approach. The immersive AR-MI paradigm heightens patient engagement and enhances MI performance. The EA-DGCNN model incorporates Euclidean alignment to minimize inter-subject variability in EEG distributions. The model extracts multi-dimensional spatiotemporal features via convolutional block attention, dynamic graph attention, and multi-scale convolutions, incorporating a Broad Learning System to achieve precise classification results. Main results. Experimental results demonstrate that the model achieves an accuracy of 85.13 ± 10.53% on the public BCI Competition IV 2a dataset. On a custom clinical dataset of 20 stroke patients, the AR paradigm yields a classification accuracy of 71.9 ± 8.9%, outperforming the 68.9 ± 8.0% of the traditional 2D paradigm. Furthermore, evaluations on the 64-channel PhysioNet benchmark demonstrate robust cross-subject transferability with a superior grand-average accuracy of 83.67 ± 8.52%. Neurophysiological feature analysis indicates that the AR paradigm elicits more pronounced event-related desynchronisation and event-related synchronisation responses. The t-SNE visualisation demonstrates that the AR paradigm, coupled with the proposed model, produces highly discriminative feature clustering patterns. Significance. This study delivers a more effective paradigm and a robust decoding solution for clinical BCI rehabilitation.
Non-invasive multimodal neuromodulation is often limited by cross-modal temporal misalignment caused by modality-specific conduction delays. To address this challenge, we developed a microcontroller-based multiphysics stimulation platform integrating transcranial alternating current stimulation (tACS) with visual and auditory rhythmic inputs. A feedforward delaycompensation strategy using individualized ERP latencies (visual P1 and auditory N1) was implemented to reduce intermodal timing discrepancies.The system was evaluated in a randomized, sham-controlled crossover study with 15 participants providing complete EEG datasets. Compared with sensory-only stimulation, the phase-coordinated multiphysics condition increased resting-state frontoparietal theta power and enhanced functional connectivity (wPLI). During a subsequent high-load cognitive task, it was also associated with reduced accumulation of fatigue-related parietal alpha power.Exploratory analysis revealed a moderate association between parietal alpha stability and behavioral performance (r = 0.577, p = 0.024). These findings suggest that temporally coordinated cross-modal stimulation may support more stable large-scale neural dynamics and improved cognitive performance under sustained load, providing a technical framework for precision multimodal neuromodulation.
Abstract Objective. Physiological artifacts degrade electroencephalographic (EEG) recordings and can affect downstream brain–computer interface (BCI) analysis. This study develops a compact single-channel framework for ocular, muscular, cardiac, and mixed-artifact removal. Approach. The Diffusion-Guided Artifact Denoising Network (Diff-ADN) employs a two-stage framework comprising severity-conditioned Stage-I reconstruction followed by diffusion-guided Stage-II residual refinement. During training, forward noising and velocity prediction supervise the Stage-II encoder, whereas inference requires only a single deterministic residual correction, without iterative reverse-diffusion sampling. The framework was evaluated under contamination levels ranging from − 7 to + 2 dB, using independently recorded artifact sources and motor-imagery decoding across four public EEG datasets. Main results. Diff-ADN achieved mean Pearson correlations of 0.936, 0.839, 0.886, and 0.844 for electrooculographic (EOG),electromyographic (EMG), electrocardiographic (ECG), and mixed EOG+EMG artifacts, respectively. When tested with independently recorded artifact sources, performance varied by artifact type: larger reductions were observed for EOG and EMG, while PTB and INCART ECG differed from the MIT–BIH reference by 0.026 and 0.014, respectively. Across the four motor-imagery datasets, ECG denoising recovered 4.88–5.59 percentage points (pp) in decoding accuracy compared with artifact-corrupted EEG. The largest recovery was 21.90 pp for PTB ECG artifacts on BCI IV-2a at − 6 dB. Significance. The proposed framework combines artifact-aware EEG reconstruction with efficient deterministic inference, processing 2 s segments in 12.52–17.08 ms on the tested CPU. Results across independent artifact sources and multiple motor-imagery datasets further show that improvements in waveform reconstruction do not necessarily translate into uniform recovery of BCI decoding accuracy.
