Many patients with locked-in syndrome (LIS) or complete locked-in syndrome (CLIS) also need brain-computer interface (BCI) platforms that do not rely on visual stimuli and are easy to use. We investigate command following and communication functions of mindBEAGLE with 9 LIS, 3 CLIS patients and three healthy controls. This tests were done with vibro-tactile stimulation with 2 or 3 stimulators (VT2 and VT3 mode) and with motor imagery (MI) paradigms. In VT2 the stimulators are fixed on the left and right wrist and the participant has the task to count the stimuli on the target hand in order to elicit a P300 response. In VT3 mode an additional stimulator is placed as a distractor on the shoulder and the participant is counting stimuli either on the right or left hand. In motor imagery mode the participant is instructed to imagine left or right hand movement. VT3 and MI also allow the participant to answer yes and no questions. Healthy controls achieved a mean assessment accuracy of 100% in VT2, 93% in VT3, and 73% in MI modes. They were able to communicate with VT3 (86.7%) and MI (83.3%) after 2 training runs. The patients achieved a mean accuracy of 76.6% in VT2, 63.1% in VT3, and 58.2% in MI modes after 1-2 training runs. 9 out of 12 LIS patients could communicate by using the vibro-tactile P300 paradigms (answered on average 8 out of 10 questions correctly) and 3 out of 12 could communicate with the motor imagery paradigm (answered correctly 4,7 out of 5 questions). 2 out of the 3 CLIS patients could use the system to communicate with VT3 (90 and 70% accuracy). The results show that paradigms based on non-visual evoked potentials and motor imagery can be effective for these users. It is also the first study that showed EEG-based BCI communication with CLIS patients and was able to bring 9 out of 12 patients to communicate with higher accuracies than reported before. More importantly this was achieved within less than 15-20 min.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5418541 | PMC |
| http://dx.doi.org/10.3389/fnins.2017.00251 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
The complementary strengths of electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) have driven extensive research into integrating these two noninvasive modalities to better understand the neural mechanisms underlying cognitive, sensory, and motor functions. However, the precise neural patterns associated with motor functions, especially imagined movements, remain unclear. Specifically, the correlations between electrophysiological responses and hemodynamic activations during executed and imagined movements have not been fully elucidated at a whole-brain level.
View Article and Find Full Text PDFJoint disentangled representation and domain adversarial training for EEG-based cross-session biometric recognition in single-task protocols.
Cogn Neurodyn
December 2025
School of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018 Zhejiang China.
The increasing adoption of wearable technologies highlights the potential of electroencephalogram (EEG) signals for biometric recognition. However, the intrinsic variability in cross-session EEG data presents substantial challenges in maintaining model stability and reliability. Moreover, the diversity within single-task protocols complicates achieving consistent and generalized model performance.
View Article and Find Full Text PDFA Synergy of Convolutional Neural Networks for Sensor-Based EEG Brain-Computer Interfaces to Enhance Motor Imagery Classification.
Sensors (Basel)
January 2025
Department of Mechanical Engineering, College of Engineering, Imam Mohammad Ibn Saud Islamic University, Riyadh 11432, Saudi Arabia.
Enhancing motor disability assessment and its imagery classification is a significant concern in contemporary medical practice, necessitating reliable solutions to improve patient outcomes. One promising avenue is the use of brain-computer interfaces (BCIs), which establish a direct communication pathway between users and machines. This technology holds the potential to revolutionize human-machine interaction, especially for individuals diagnosed with motor disabilities.
View Article and Find Full Text PDFA cross-domain-based channel selection method for motor imagery.
Med Biol Eng Comput
January 2025
State Key Laboratory of Power Transmission Equipment Technology, School of Electrical Engineering, Chongqing, University, Chongqing, 400044, People's Republic of China.
Selecting channels for motor imagery (MI)-based brain-computer interface (BCI) systems can not only enhance the portability of the systems, but also improve the decoding performance. Hence, we propose a cross-domain-based channel selection (CDCS) approach, which effectively minimizes the number of EEG channels used while maintaining high accuracy in MI recognition. The EEG source imaging (ESI) technique is employed to map scalp EEG into the cortical source domain.
View Article and Find Full Text PDFA Lightweight Network with Domain Adaptation for Motor Imagery Recognition.
Entropy (Basel)
December 2024
Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300384, China.
Brain-computer interfaces (BCI) are an effective tool for recognizing motor imagery and have been widely applied in the motor control and assistive operation domains. However, traditional intention-recognition methods face several challenges, such as prolonged training times and limited cross-subject adaptability, which restrict their practical application. This paper proposes an innovative method that combines a lightweight convolutional neural network (CNN) with domain adaptation.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!