Hybrid asynchronous brain-computer interface for yes/no communication in patients with disorders of consciousness

Brain-computer interfaces and human factors: the role of language and cultural differences-Still a missing gap?

Brain-computer interfaces (BCIs) aim at the non-invasive investigation of brain activity for supporting communication and interaction of the users with their environment by means of brain-machine assisted technologies. Despite technological progress and promising research aimed at understanding the influence of human factors on BCI effectiveness, some topics still remain unexplored. The aim of this article is to discuss why it is important to consider the language of the user, its embodied grounding in perception, action and emotions, and its interaction with cultural differences in information processing in future BCI research. Based on evidence from recent studies, it is proposed that detection of language abilities and language training are two main topics of enquiry of future BCI studies to extend communication among vulnerable and healthy BCI users from bench to bedside and real world applications. In addition, cultural differences shape perception, actions, cognition, language and emotions subjectively, behaviorally as well as neuronally. Therefore, BCI applications should consider cultural differences in information processing to develop culture- and language-sensitive BCI applications for different user groups and BCIs, and investigate the linguistic and cultural contexts in which the BCI will be used.

Classification Algorithm for Electroencephalogram-based Motor Imagery Using Hybrid Neural Network with Spatio-temporal Convolution and Multi-head Attention Mechanism

Motor imagery (MI) is a brain-computer interface (BCI) technique in which specific brain regions are activated when people imagine their limbs (or muscles) moving, even without actual movement. The technology converts electroencephalogram (EEG) signals generated by the brain into computer-readable commands by measuring neural activity. Classification of motor imagery is one of the tasks in BCI. Researchers have done a lot of work on motor imagery classification, and the existing literature has relatively mature decoding methods for two-class motor tasks. However, as the categories of EEG-based motor imagery tasks increase, further exploration is needed for decoding research on four-class motor imagery tasks. In this study, we designed a hybrid neural network that combines spatiotemporal convolution and attention mechanisms. Specifically, the data is first processed by spatiotemporal convolution to extract features and then processed by a Multi-branch Convolution block. Finally, the processed data is input into the encoder layer of the Transformer for a self-attention calculation to obtain the classification results. Our approach was tested on the well-known MI datasets BCI Competition IV 2a and 2b, and the results show that the 2a dataset has a global average classification accuracy of 83.3% and a kappa value of 0.78. Experimental results show that the proposed method outperforms most of the existing methods.

Assessing Consciousness through Neurofeedback and Neuromodulation: Possibilities and Challenges

Neurofeedback is a non-invasive therapeutic approach that has gained traction in recent years, showing promising results for various neurological and psychiatric conditions. It involves real-time monitoring of brain activity, allowing individuals to gain control over their own brainwaves and improve cognitive performance or alleviate symptoms. The use of electroencephalography (EEG), such as brain-computer interface (BCI), transcranial direct current stimulation (tDCS), and transcranial magnetic stimulation (TMS), has been instrumental in developing neurofeedback techniques. However, the application of these tools in patients with disorders of consciousness (DoC) presents unique challenges. In this narrative review, we explore the use of neurofeedback in treating patients with DoC. More specifically, we discuss the advantages and challenges of using tools such as EEG neurofeedback, tDCS, TMS, and BCI for these conditions. Ultimately, we hope to provide the neuroscientific community with a comprehensive overview of neurofeedback and emphasize its potential therapeutic applications in severe cases of impaired consciousness levels.

A cross-subject decoding algorithm for patients with disorder of consciousness based on P300 brain computer interface

Background

Brain computer interface (BCI) technology may provide a new way of communication for some patients with disorder of consciousness (DOC), which can directly connect the brain and external devices. However, the DOC patients' EEG differ significantly from that of the normal person and are difficult to collected, the decoding algorithm currently only is trained based on a small amount of the patient's own data and performs poorly.

Methods

In this study, a decoding algorithm called WD-ADSTCN based on domain adaptation is proposed to improve the DOC patients' P300 signal detection. We used the Wasserstein distance to filter the normal population data to increase the training data. Furthermore, an adversarial approach is adopted to resolve the differences between the normal and patient data.

Results

The results showed that in the cross-subject P300 detection of DOC patients, 7 of 11 patients achieved an average accuracy of over 70%. Furthermore, their clinical diagnosis changed and CRS-R scores improved three months after the experiment.

Conclusion

These results demonstrated that the proposed method could be employed in the P300 BCI system for the DOC patients, which has important implications for the clinical diagnosis and prognosis of these patients.

Advances in P300 brain-computer interface spellers: toward paradigm design and performance evaluation

A brain-computer interface (BCI) is a non-muscular communication technology that provides an information exchange channel for our brains and external devices. During the decades, BCI has made noticeable progress and has been applied in many fields. One of the most traditional BCI applications is the BCI speller. This article primarily discusses the progress of research into P300 BCI spellers and reviews four types of P300 spellers: single-modal P300 spellers, P300 spellers based on multiple brain patterns, P300 spellers with multisensory stimuli, and P300 spellers with multiple intelligent techniques. For each type of P300 speller, we further review several representative P300 spellers, including their design principles, paradigms, algorithms, experimental performance, and corresponding advantages. We particularly emphasized the paradigm design ideas, including the overall layout, individual symbol shapes and stimulus forms. Furthermore, several important issues and research guidance for the P300 speller were identified. We hope that this review can assist researchers in learning the new ideas of these novel P300 spellers and enhance their practical application capability.

EEG-based Brain-Computer Interfaces for people with Disorders of Consciousness: Features and applications. A systematic review

Background

Disorders of Consciousness (DoC) are clinical conditions following a severe acquired brain injury (ABI) characterized by absent or reduced awareness, known as coma, Vegetative State (VS)/Unresponsive Wakefulness Syndrome (VS/UWS), and Minimally Conscious State (MCS). Misdiagnosis rate between VS/UWS and MCS is attested around 40% due to the clinical and behavioral fluctuations of the patients during bedside consciousness assessments. Given the large body of evidence that some patients with DoC possess "covert" awareness, revealed by neuroimaging and neurophysiological techniques, they are candidates for intervention with brain-computer interfaces (BCIs).

Objectives

The aims of the present work are (i) to describe the characteristics of BCI systems based on electroencephalography (EEG) performed on DoC patients, in terms of control signals adopted to control the system, characteristics of the paradigm implemented, classification algorithms and applications (ii) to evaluate the performance of DoC patients with BCI.

Methods

The search was conducted on Pubmed, Web of Science, Scopus and Google Scholar. The PRISMA guidelines were followed in order to collect papers published in english, testing a BCI and including at least one DoC patient.

Results

Among the 527 papers identified with the first run of the search, 27 papers were included in the systematic review. Characteristics of the sample of participants, behavioral assessment, control signals employed to control the BCI, the classification algorithms, the characteristics of the paradigm, the applications and performance of BCI were the data extracted from the study. Control signals employed to operate the BCI were: P300 (N = 19), P300 and Steady-State Visual Evoked Potentials (SSVEP; hybrid system, N = 4), sensorimotor rhythms (SMRs; N = 5) and brain rhythms elicited by an emotional task (N = 1), while assessment, communication, prognosis, and rehabilitation were the possible applications of BCI in DoC patients.

Conclusion

Despite the BCI is a promising tool in the management of DoC patients, supporting diagnosis and prognosis evaluation, results are still preliminary, and no definitive conclusions may be drawn; even though neurophysiological methods, such as BCI, are more sensitive to covert cognition, it is suggested to adopt a multimodal approach and a repeated assessment strategy.

Pain assessment during physiotherapy and noxious stimuli in patients with disorders of consciousness: A preliminary study

Objectives

The primary purpose of this study is to determine whether patients with disorders of consciousness (DOC) (unresponsive wakefulness syndrome, UWS; minimally conscious state, MCS) experience pain during physiotherapy and noxious stimuli in a larger patient population.

Materials and methods

The patients’ level of consciousness was measured with the Coma Recovery Scale-Revised (CRS-R). Additionally, the Nociception Coma Scale-revised (NCS-R) was used to assess their pain response. The NCS-R total scores between UWS and MCS at baseline, physiotherapy and noxious stimulus were compared using the Mann-Whitney U test (Wilcoxon rank-sum test) and the Kruskal-Wallis H test with Bonferroni correction.

Results

The study enrolled 93 participants. There was a statistically significant difference in NCS-R total scores between the three conditions (H = 215.25, p < 0.001). At baseline, there was no statistically significant difference between MCS and UWS (U = 378, z = –1.35, p = 0.178). While there was a statistically significant difference between MCS and UWS during physiotherapy (U = 1,362, z = –3.06, p < 0.01) and under noxious stimuli (U = 5142.5, z = –11.22, p < 0.001).

Conclusion

Physiotherapy improved the activity responsiveness of DOC patients, and patients experienced less potential pain. However, some DOC patients, especially MCS patients, perceived pain under the noxious stimuli.

SincNet-based Hybrid Neural Network for Motor Imagery EEG Decoding

It is difficult to identify optimal cut-off frequencies for filters used with the common spatial pattern (CSP) method in motor imagery (MI)-based brain-computer interfaces (BCIs). Most current studies choose filter cut-frequencies based on experience or intuition, resulting in sub-optimal use of MI-related spectral information in the electroencephalography (EEG). To improve information utilization, we propose a SincNet-based hybrid neural network (SHNN) for MI-based BCIs. First, raw EEG is segmented into different time windows and mapped into the CSP feature space. Then, SincNets are used as filter bank band-pass filters to automatically filter the data. Next, we used squeeze-and-excitation modules to learn a sparse representation of the filtered data. The resulting sparse data were fed into convolutional neural networks to learn deep feature representations. Finally, these deep features were fed into a gated recurrent unit module to seek sequential relations, and a fully connected layer was used for classification. We used the BCI competition IV datasets 2a and 2b to verify the effectiveness of our SHNN method. The mean classification accuracies (kappa values) of our SHNN method are 0.7426 (0.6648) on dataset 2a and 0.8349 (0.6697) on dataset 2b, respectively. The statistical test results demonstrate that our SHNN can significantly outperform other state-of-the-art methods on these datasets.

A Systematic Review of Sleep in Patients with Disorders of Consciousness: From Diagnosis to Prognosis

With the development of intensive care technology, the number of patients who survive acute severe brain injury has increased significantly. At present, it is difficult to diagnose the patients with disorders of consciousness (DOCs) because motor responses in these patients may be very limited and inconsistent. Electrophysiological criteria, such as event-related potentials or motor imagery, have also been studied to establish a diagnosis and prognosis based on command-following or active paradigms. However, the use of such task-based techniques in DOC patients is methodologically complex and requires careful analysis and interpretation. The present paper focuses on the analysis of sleep patterns for the evaluation of DOC and its relationships with diagnosis and prognosis outcomes. We discuss the concepts of sleep patterns in patients suffering from DOC, identification of this challenging population, and the prognostic value of sleep. The available literature on individuals in an unresponsive wakefulness syndrome (UWS) or minimally conscious state (MCS) following traumatic or nontraumatic severe brain injury is reviewed. We can distinguish patients with different levels of consciousness by studying sleep patients with DOC. Most MCS patients have sleep and wake alternations, sleep spindles and rapid eye movement (REM) sleep, while UWS patients have few EEG changes. A large number of sleep spindles and organized sleep-wake patterns predict better clinical outcomes. It is expected that this review will promote our understanding of sleep EEG in DOC.