Researchers at Mass General Brigham Neuroscience Institute and Brown University report in Nature Neuroscience that an implantable intracortical brain–computer interface allowed two participants in the BrainGate clinical trial to type rapidly and accurately.
One participant had advanced amyotrophic lateral sclerosis (ALS) and the other had a cervical spinal cord injury. The system uses microelectrode sensors placed in motor cortex to record neural signals produced when users attempt individual finger movements. Those signals are decoded into letters on a QWERTY keyboard and passed through a predictive language model to produce text.
Both participants calibrated the system with as few as 30 sentences. One reached a peak speed of 110 characters — about 22 words — per minute with a 1.6% word error rate, comparable to able-bodied typing accuracy reported in the study. Both used the device from their homes, demonstrating feasibility of at‑home use.
“For many people with paralysis, when losing use of both the hands and the muscles of speech, communication can become difficult or impossible,” said Dr. Daniel Rubin, senior author and critical care neurologist at Mass General Brigham. He said current augmentative systems such as eye‑gaze can be too slow for many users.
Dr. Leigh Hochberg, a co‑author and leader of the BrainGate clinical trial, said the work builds on the consortium’s long‑running research program and helps create a pathway for implantable medical devices aimed at restoring communication and independence.
First author Justin Jude called decoding attempted finger movements a step toward restoring complex reach and grasp for people with upper‑extremity paralysis and noted the potential to further speed typing with personalized keyboards or stenography.
The paper lists multiple institutional authors and funding sources and appears in Nature Neuroscience. The reporting and quotes come from a Brown University release summarizing the study.
Photo credit: www.technology.org
Tags: intracortical BCI, BrainGate, ALS, spinal cord injury, motor cortex
Topics: Brain–computer interfaces, Neuroprosthetics & neural implants, Neuroscience & neuroplasticity