An Experimental Brain Implant Allows People With Paralysis to Type Their Thoughts With Their Minds
One of the two participants wrote words up to a speed similar to an able-bodied person texting on a smartphone
People with paralysis affecting their speech and hands can struggle to communicate, and the loss is often cited as one of the most devastating symptoms of their condition. Existing devices to aid them, like technology that tracks eye movements to spell out words, can be slow and frustrating to use.
Over the last several years, however, a different type of technology called implantable brain-computer interfaces, or BCIs, has been gaining momentum as a possible alternative. Now, a study published March 16 in the journal Nature Neuroscience reports that an experimental BCI helped two people with paralysis type on a virtual keyboard with their minds—and one participant did it as fast as an able-bodied smartphone user can text.
“This is an important technical advance that brings brain-computer typing much closer to practical communication speeds for people with paralysis,” says Edward Chang, a neurosurgeon at the University of California, San Francisco, who was not involved in the study, to Tanya Lewis at Scientific American. “At about 22 words per minute, this is among the fastest motor-cortex typing BCIs yet and dramatically faster than most earlier neural spellers.”
The device relies on artificial intelligence to decode brain activity that corresponds with attempting different movements, even if a person is not actually moving. In the study, microelectrode sensors were placed in each participant’s motor cortex, the region responsible for movement. Then, the brain implant users were instructed to try performing 30 unique finger motions, and a computer translated the brain activity associated with each attempted movement into a distinct keystroke on a virtual QWERTY keyboard.
After tuning neural activity with the motions, the two participants used their minds to type various sentences. One of them, who was paralyzed from the neck down, wrote at speeds up to 47 characters per minute with 81 percent accuracy. The other individual, who had the progressive neurodegenerative disease amyotrophic lateral sclerosis (ALS), typed up to 110 characters, or 22 words, per minute with 95 percent accuracy—almost as fast as the average able-bodied person their age can text, about 27 words per minute.
The performance differences might partially stem from the number of implanted sensors and where they were located in the BCI users’ brains, study co-author Justin Jude, a computer scientist at Brown University, tells STAT’s O. Rose Broderick. The speedier typer had 384 motor electrodes, while the slower person had 128. The differences could also come from how their distinct conditions affect their brains.
The top measured speed is 20 characters per minute faster than that recorded with the past record-holding communication device, a BCI that decodes attempted handwriting movements, the researchers write in the paper. Picking up the communication pace matters “because being part of a conversation matters,” study co-author Daniel Rubin, a critical care neurologist at Massachusetts General Hospital, tells Scientific American.
Did you know? The world’s first commercial brain implant
Earlier this month, China became the first country to approve an implantable BCI for commercial use. It’s intended to help restore hand movement in people ages 18 to 60 years old with paralysis caused by a spinal cord injury.
Still, the work has limitations. The sample size included only two people, and the device implantation procedure is invasive.
But “decoding these finger movements is also a big step toward being able to restore complex reach and grasp movements for people with upper extremity paralysis,” Jude says in a statement. “And there’s also room to make this communication tool better—like implementing a stenography or otherwise personalized keyboard to make typing even faster.”
Nevertheless, the experimental device is “a great example of how modern neuroscience and artificial intelligence technology can combine to create something capable of restoring communication and independence,” Jude says.