中 / EN

BCIwiki — Brain-computer interface news, research and industry database

Latest

October 2026
10-23 · Laboratory for Neuro- and Psychophysiology +2 more ChinaBelgium Papers Foundations & Methods

West China Hospital Collaboration Improves Gesture Decoding in Glioma Patients

A collaboration involving West China Hospital of Sichuan University combined healthy neural recordings with biophysical constraints to decode motor signals affected by pathology. In a gesture classification task using high-density electrocorticography from patients with gliomas infiltrating the motor cortex, the study reported improved classification accuracy. Correlation between motor-command representations and healthy canonical representations increased from r = 0.66 to r = 0.94. The authors interpret the model's behavior as an "inverse weighting" strategy that downweights high-power pathological noise and redirects spatial attention toward functional compensatory regions. This is a proof of concept for decoding in compromised networks, not evidence of restored motor function.
Why it matters Higher signal power does not necessarily make a signal more useful for decoding. The authors' model analysis points to downweighting pathological noise and using information from compensatory regions as a possible explanation for the classification gains.
View details →
10-23 Papers Foundations & Methods

Japan’s University of Electro-Communications Raises Visual BCI Transfer Rate by Up to 11.30 Bit/Min

A study from The University of Electro-Communications in Japan proposes enhancing brain signals without model training. The method repeatedly samples and pastes EEG signals to strengthen steady-state visual evoked potential components, which visual brain-computer interfaces use to identify target commands. In experiments with synthesized signals and open benchmark datasets, it outperformed conventional methods at every tested signal length, improving information transfer rate by up to 11.30 bit/min. The approach addresses the training-data requirements and upfront costs of learning-based methods; the reported gains come from signal and dataset experiments.
Why it matters The study focuses on enhancing signals rather than training a more complex recognition model. Its comparisons across signal lengths also examine whether the training-free approach maintains an advantage with different amounts of recorded EEG.
View details →
10-23 Papers Rehabilitation & Assistance

Columbia Collaboration Finds BCI Control in 13 of 41 Clinically Unresponsive Patients

A prospective single-centre study involving Columbia University Medical Center found that 13 of 41 clinically unresponsive, critically ill patients with acute brain injury (32%) could control a brain-computer interface. The system analyzed EEG in real time and translated attempted movement into changes in sound. Clinical consciousness returned by discharge in 4/13 patients with BCI control versus 1/28 without it. At 12 months, 6/13 versus 2/28 met the study's definition of functional independence. BCI control was associated with subsequent recovery, but the findings do not show that device use caused recovery. The tested interface was one-way; bidirectional communication remains a future possibility.
Why it matters A lack of observable clinical responses did not rule out BCI task performance. Longer signal delays in clinically unresponsive patients also highlight response timing as a practical consideration when assessing their ability to interact.
View details →
10-23 · Synchron +1 more AustraliaUnited States Papers Communication & Language

Melbourne Team Tests Endovascular BCI Handwriting Classification in One Participant

University of Melbourne researchers studied one participant implanted with a Stentrode endovascular brain-computer interface who attempted to handwrite English characters. They classified the attempts offline and online using neural signal trajectories over time. Across four online sessions, each containing 20-30 trials per character and 80-180 rest trials, the best-performing 3-class model achieved a mean rest recall of 87%, character recall of 65%, and character precision of 59%. Adjusting all trials to the same duration significantly improved classification compared with raw trials. The findings support further investigation of temporal information for motor decoding, but come from one participant and a small number of classes.
Why it matters By summing high-gamma power across all channels into one trajectory, the study isolated the contribution of temporal information. This design helps distinguish the value of where a signal is recorded from how it changes over time.
View details →
10-23 Papers Foundations & Methods

Nanchang Collaboration Reports 80.21%–97.32% Motor Imagery Accuracy Across Three EEG Datasets

A collaboration involving Nanchang University proposed a deep learning network to classify motor imagery tasks from EEG signals. Across three public BCI datasets, it achieved average accuracies of 80.21% for Dataset 1's 4-class tasks, 90.19% for Dataset 2's 2-class tasks, and 97.32% for Dataset 3's 4-class tasks, exceeding the strongest comparison network on each dataset. The approach combines multiscale processing with temporal and channel attention, while augmenting training data through segmentation and reconstruction. These results reflect classification under the tested dataset and training conditions, not demonstrated real-time BCI or clinical performance.
Why it matters The datasets contain different numbers of task classes, so their accuracy figures are not directly comparable. The more informative comparison is against the strongest baseline within each dataset, rather than the highest accuracy alone.
View details →
10-23 Policy & Regulation Regulatory Approval

Shanghai Ninth People's Hospital Leads Trial of Auditory Brainstem Implant That Receives Approval in China

According to Sanbo Brain Hospital, China's National Medical Products Administration has approved the registration of an auditory brainstem implant. Professor Wu Hao of Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, led the device trial, with a team from Sanbo Brain Hospital, Capital Medical University, participating as site investigators. Intended for hearing reconstruction, the device is indicated for prelingually deaf patients aged 2-6 years, excluding those aged 6, with non-tumor-related, non-syndromic deafness and specified severe inner ear malformations or an absent cochlear nerve that prevent cochlear implantation. It stimulates the cochlear nucleus at the brainstem surface, bypassing the cochlea and auditory nerve, and works with a cochlear implant speech processor.
Why it matters The implant targets the cochlear nucleus at the brainstem surface rather than the cochlea. This distinction helps explain its indication for selected patients who cannot receive a cochlear implant, rather than for everyone with deafness.
View details →
10-22 · University at Buffalo, State University of New York United States Papers Rehabilitation & Assistance

University at Buffalo Combines BCI and Eye Tracking for Faster AAC Selection

A University at Buffalo author evaluated an assistive communication interface combining a BCI with eye tracking. Gaze narrows the target area and brain signals confirm selection. The study reports faster selection than BCI alone, better control than eye tracking alone, and fewer selection errors and corrections.
Why it matters Measuring correction time, workload and preferences alongside selection speed broadens the assessment of the hybrid interface.
View details →
10-22 · Nanyang Technological University Singapore Papers Foundations & Methods

Nanyang Technological University Reaches 89.2% in Cross-User EEG–EMG Gesture Tests

A Nanyang Technological University researcher combined EEG and EMG timing information in a gesture-recognition network, reaching 87.6% and 89.2% accuracy on datasets with 12 and 20 participants. The results exceeded the strongest baselines by 9.4 and 9.1 percentage points; adaptation required no labelled target-user data. Participants were healthy young adults.
Why it matters Separate tests of cross-user transfer, cross-day use and simulated electrode displacement help assess how the method handles changes in recording conditions.
View details →
10-22 Papers Rehabilitation & Assistance

UCSF and UC Berkeley Authors Examine Learning to Control Human-Machine Interfaces

Authors at the University of California, San Francisco and UC Berkeley discuss how continuous closed-loop reinforcement interacts with sensory feedback when people learn to control human-machine interfaces. The Neuron commentary covers BCIs, augmented reality devices and hand prostheses.
Why it matters The commentary directs attention to feedback and user learning as factors in interface control.
View details →
10-21 · University of Essex United Kingdom Papers Foundations & Methods

University of Essex EEG Tests Reach 73.4% in Pairwise Semantic Classification

University of Essex researchers recorded EEG from 14 participants retrieving concepts from verbal clues. Mean accuracies in three pairwise comparisons of food, musical instruments and body parts were 73.4%, 70.7% and 68.2%. The model learned representations from other participants before calibration with each test participant’s own labelled data.
Why it matters Aligning EEG to participants’ reported retrieval times provides a window into semantic processing, while retaining a need for individual calibration.
View details →

© 2026 BCIwiki.com Digest Topics Tips Subscribe Revisions About