Machine-learning assisted swallowing assessment: a deep learning-based quality improvement tool to screen for post-stroke dysphagia.

Introduction: Post-stroke dysphagia is common and associated with significant morbidity and mortality, rendering bedside screening of significant clinical importance. Using voice as a biomarker coupled with deep learning has the potential to improve patient access to screening and mitigate the subjectivity associated with detecting voice change, a component of several validated screening protocols. Methods: In this single-center study, we developed a proof-of-concept model for automated dysphagia screening and evaluated the performance of this model on training and testing cohorts. Patients were admitted to a comprehensive stroke center, where primary English speakers could follow commands without significant aphasia and participated on a rolling basis. The primary outcome was classification either as a pass or fail equivalent using a dysphagia screening test as a label. Voice data was recorded from patients who spoke a standardized set of vowels, words, and sentences from the National Institute of Health Stroke Scale. Seventy patients were recruited and 68 were included in the analysis, with 40 in training and 28 in testing cohorts, respectively. Speech from patients was segmented into 1,579 audio clips, from which 6,655 Mel-spectrogram images were computed and used as inputs for deep-learning models (DenseNet and ConvNext, separately and together). Clip-level and participant-level swallowing status predictions were obtained through a voting method. Results: The models demonstrated clip-level dysphagia screening sensitivity of 71% and specificity of 77% (F1 = 0.73, AUC = 0.80 [95% CI: 0.78-0.82]). At the participant level, the sensitivity and specificity were 89 and 79%, respectively (F1 = 0.81, AUC = 0.91 [95% CI: 0.77-1.05]). Discussion: This study is the first to demonstrate the feasibility of applying deep learning to classify vocalizations to detect post-stroke dysphagia. Our findings suggest potential for enhancing dysphagia screening in clinical settings. https://github.com/UofTNeurology/masa-open-source.

Brain-Computer Interfaces for Children With Complex Communication Needs and Limited Mobility: A Systematic Review.

Brain-computer interfaces (BCIs) represent a new frontier in the effort to maximize the ability of individuals with profound motor impairments to interact and communicate. While much literature points to BCIs' promise as an alternative access pathway, there have historically been few applications involving children and young adults with severe physical disabilities. As research is emerging in this sphere, this article aims to evaluate the current state of translating BCIs to the pediatric population. A systematic review was conducted using the Scopus, PubMed, and Ovid Medline databases. Studies of children and adolescents that reported BCI performance published in English in peer-reviewed journals between 2008 and May 2020 were included. Twelve publications were identified, providing strong evidence for continued research in pediatric BCIs. Research evidence was generally at multiple case study or exploratory study level, with modest sample sizes. Seven studies focused on BCIs for communication and five on mobility. Articles were categorized and grouped based on type of measurement (i.e., non-invasive and invasive), and the type of brain signal (i.e., sensory evoked potentials or movement-related potentials). Strengths and limitations of studies were identified and used to provide requirements for clinical translation of pediatric BCIs. This systematic review presents the state-of-the-art of pediatric BCIs focused on developing advanced technology to support children and youth with communication disabilities or limited manual ability. Despite a few research studies addressing the application of BCIs for communication and mobility in children, results are encouraging and future works should focus on customizable pediatric access technologies based on brain activity.

Novel hybrid brain-computer interface system based on motor imagery and P300.

Motor imagery (MI) is a mental representation of motor behavior and has been widely used in electroencephalogram based brain-computer interfaces (BCIs). Several studies have demonstrated the efficacy of MI-based BCI-feedback training in post-stroke rehabilitation. However, in the earliest stage of the training, calibration data typically contain insufficient discriminability, resulting in unreliable feedback, which may decrease subjects' motivation and even hinder their training. To improve the performance in the early stages of MI training, a novel hybrid BCI paradigm based on MI and P300 is proposed in this study. In this paradigm, subjects are instructed to imagine writing the Chinese character following the flash order of the desired Chinese character displayed on the screen. The event-related desynchronization/synchronization (ERD/ERS) phenomenon is produced with writing based on one's imagination. Simultaneously, the P300 potential is evoked by the flash of each stroke. Moreover, a fusion method of P300 and MI classification is proposed, in which unreliable P300 classifications are corrected by reliable MI classifications. Twelve healthy naïve MI subjects participated in this study. Results demonstrated that the proposed hybrid BCI paradigm yielded significantly better performance than the single-modality BCI paradigm. The recognition accuracy of the fusion method is significantly higher than that of P300 (p < 0.05) and MI (p < 0.01). Moreover, the training data size can be reduced through fusion of these two modalities.

Category-based attentional capture can be influenced by color- and shape-dimensions independently in the conjunction search task.

Attention can be involuntarily attracted by a distractor that matches the current attentional control settings (ACSs). However, it remains unclear whether two category-specific ACSs can operate independently. By defining a target as a combination of two prototype-based categories, the present event-related potential (ERP) study investigated how color-category and shape-category ACSs operate within a search task paradigm and the effects of temporal task demands on these ACSs. The matching level between target and distractor was manipulated to separate the effects of each ACS. The relative position between target and distractor was employed to isolate the attentional processing of the distractor from the target. Furthermore, two display durations were used to manipulate the temporal task demands, including a short fixed window (800 ms) and a dynamic window extended until the user responded. Our results support a two-stage selection scenario. In early stage, the color- and shape-ACS independently guided attention to task-relevant property (N2pc components) and suppressed attention toward task-irrelevant properties (PD components). In late stage, these two independent ACSs were integrated into a holistic ACS to interfere with the consolidation (contralateral delay activity components) and behavioral performance (accuracy and RTs) of target identification. Moreover, an early N1/P1 component might reflect a preattentive enhancement of relevant information or a preattentive suppression of irrelevant objects. These two category-specific ACSs weights differently in varied temporal task demands. These findings support the idea that independent early processing is followed by integrated late processing, which can be applied to category-based attentional capture with different temporal task demands.

A Dynamic Window Recognition Algorithm for SSVEP-Based Brain-Computer Interfaces Using a Spatio-Temporal Equalizer.

The past decade has witnessed rapid development in the field of brain-computer interfaces (BCIs). While the performance is no longer the biggest bottleneck in the BCI application, the tedious training process and the poor ease-of-use have become the most significant challenges. In this study, a spatio-temporal equalization dynamic window (STE-DW) recognition algorithm is proposed for steady-state visual evoked potential (SSVEP)-based BCIs. The algorithm can adaptively control the stimulus time while maintaining the recognition accuracy, which significantly improves the information transfer rate (ITR) and enhances the adaptability of the system to different subjects. Specifically, a spatio-temporal equalization algorithm is used to reduce the adverse effects of spatial and temporal correlation of background noise. Based on the theory of multiple hypotheses testing, a stimulus termination criterion is used to adaptively control the dynamic window. The offline analysis which used a benchmark dataset and an offline dataset collected from 16 subjects demonstrated that the STE-DW algorithm is superior to the filter bank canonical correlation analysis (FBCCA), canonical variates with autoregressive spectral analysis (CVARS), canonical correlation analysis (CCA) and CCA reducing variation (CCA-RV) algorithms in terms of accuracy and ITR. The results show that in the benchmark dataset, the STE-DW algorithm achieved an average ITR of 134 bits/min, which exceeds the FBCCA, CVARS, CCA and CCA-RV. In off-line experiments, the STE-DW algorithm also achieved an average ITR of 116 bits/min. In addition, the online experiment also showed that the STE-DW algorithm can effectively expand the number of applicable users of the SSVEP-based BCI system. We suggest that the STE-DW algorithm can be used as a reliable identification algorithm for training-free SSVEP-based BCIs, because of the good balance between ease of use, recognition accuracy, ITR and user applicability.

Time course of influence on the allocation of attentional resources caused by unconscious fearful faces.

Emotionally affective stimuli have priority in our visual processing even in the absence of conscious processing. However, the influence of unconscious emotional stimuli on our attentional resources remains unclear. Using the continuous flash suppression (CFS) paradigm, we concurrently recorded and analyzed visual event-related potential (ERP) components evoked by the images of suppressed fearful and neutral faces, and the steady-state visual evoked potential (SSVEP) elicited by dynamic Mondrian pictures. Fearful faces, relative to neutral faces, elicited larger late ERP components on parietal electrodes, indicating emotional expression processing without consciousness. More importantly, the presentation of a suppressed fearful face in the CFS resulted in a significantly greater decrease in SSVEP amplitude which started about 1-1.2 s after the face images first appeared. This suggests that the time course of the attentional bias occurs at about 1 s after the appearance of the fearful face and demonstrates that unconscious fearful faces may influence attentional resource allocation. Moreover, we proposed a new method that could eliminate the interaction of ERPs and SSVEPs when recorded concurrently.

Towards correlation-based time window selection method for motor imagery BCIs.

The start of the cue is often used to initiate the feature window used to control motor imagery (MI)-based brain-computer interface (BCI) systems. However, the time latency during an MI period varies between trials for each participant. Fixing the starting time point of MI features can lead to decreased system performance in MI-based BCI systems. To address this issue, we propose a novel correlation-based time window selection (CTWS) algorithm for MI-based BCIs. Specifically, the optimized reference signals for each class were selected based on correlation analysis and performance evaluation. Furthermore, the starting points of time windows for both training and testing samples were adjusted using correlation analysis. Finally, the feature extraction and classification algorithms were used to calculate the classification accuracy. With two datasets, the results demonstrate that the CTWS algorithm significantly improved the system performance when compared to directly using feature extraction approaches. Importantly, the average improvement in accuracy of the CTWS algorithm on the datasets of healthy participants and stroke patients was 16.72% and 5.24%, respectively when compared to traditional common spatial pattern (CSP) algorithm. In addition, the average accuracy increased 7.36% and 9.29%, respectively when the CTWS was used in conjunction with Sub-Alpha-Beta Log-Det Divergences (Sub-ABLD) algorithm. These findings suggest that the proposed CTWS algorithm holds promise as a general feature extraction approach for MI-based BCIs.

An Auditory-Tactile Visual Saccade-Independent P300 Brain-Computer Interface.

Most P300 event-related potential (ERP)-based brain-computer interface (BCI) studies focus on gaze shift-dependent BCIs, which cannot be used by people who have lost voluntary eye movement. However, the performance of visual saccade-independent P300 BCIs is generally poor. To improve saccade-independent BCI performance, we propose a bimodal P300 BCI approach that simultaneously employs auditory and tactile stimuli. The proposed P300 BCI is a vision-independent system because no visual interaction is required of the user. Specifically, we designed a direction-congruent bimodal paradigm by randomly and simultaneously presenting auditory and tactile stimuli from the same direction. Furthermore, the channels and number of trials were tailored to each user to improve online performance. With 12 participants, the average online information transfer rate (ITR) of the bimodal approach improved by 45.43% and 51.05% over that attained, respectively, with the auditory and tactile approaches individually. Importantly, the average online ITR of the bimodal approach, including the break time between selections, reached 10.77 bits/min. These findings suggest that the proposed bimodal system holds promise as a practical visual saccade-independent P300 BCI.

A Hybrid Brain-Computer Interface Based on the Fusion of P300 and SSVEP Scores.

The present study proposes a hybrid brain-computer interface (BCI) with 64 selectable items based on the fusion of P300 and steady-state visually evoked potential (SSVEP) brain signals. With this approach, row/column (RC) P300 and two-step SSVEP paradigms were integrated to create two hybrid paradigms, which we denote as the double RC (DRC) and 4-D spellers. In each hybrid paradigm, the target is simultaneously detected based on both P300 and SSVEP potentials as measured by the electroencephalogram. We further proposed a maximum-probability estimation (MPE) fusion approach to combine the P300 and SSVEP on a score level and compared this approach to other approaches based on linear discriminant analysis, a naïve Bayes classifier, and support vector machines. The experimental results obtained from thirteen participants indicated that the 4-D hybrid paradigm outperformed the DRC paradigm and that the MPE fusion achieved higher accuracy compared with the other approaches. Importantly, 12 of the 13 participants, using the 4-D paradigm achieved an accuracy of over 90% and the average accuracy was 95.18%. These promising results suggest that the proposed hybrid BCI system could be used in the design of a high-performance BCI-based keyboard.