Brain implant decodes finger moves so paralyzed patients can type
Brain-computer interface aims to foster independence
Written by |
- A brain implant helps paralyzed patients type on a computer by decoding attempted finger movements.
- The device enables rapid, accurate communication, reaching speeds up to 22 words per minute.
- Researchers aim to integrate typing with text-to-speech and digital interactions.
A brain implant to detect attempted finger movements can enable people paralyzed by conditions such as amyotrophic lateral sclerosis (ALS) to type on a computer, a study showed.
The findings build on a rapidly growing field of research into so-called implantable brain-computer interfaces (iBCIs), in which electrodes are implanted into the brain to detect brain activity. This activity is then interpreted by a computer, allowing people who are paralyzed to better communicate and interact with the outside world.
“This typing neuroprosthesis has the potential to provide a rapid, highly accurate and intuitive means of communication for people with paralysis,” researchers wrote in the study, “Restoring rapid natural bimanual typing with a neuroprosthesis after paralysis,” published in Nature Neuroscience. The work was funded by the National Institutes of Health (NIH) and the U.S. Department of Veterans Affairs, among others.
ALS is marked by the dysfunction and death of specialized nerve cells that control movement, leading to gradually worsening muscle weakness. As the disease progresses, people with ALS lose the ability to move and speak, making it extremely difficult to communicate.
“For many people with paralysis, when losing use of both the hands and the muscles of speech, communication can become difficult or impossible. Often, people with severe speech and motor impairments end up relying on things like eye-gaze technology—spelling words out one letter at a time by using an eye movement tracking system,” Daniel Rubin, MD, PhD, co-author of the study and a neurologist at Mass General Brigham Neuroscience Institute, said in an institute press release. “Those systems take far too long for many users. Patients often find this and other types of Augmentative and Alternative Communication systems frustrating to use. BCIs are on track to become an important new alternative to what’s currently offered.”
For patients, an alternative to ‘frustrating’ communication systems
Previous studies have used iBCIs to detect a person’s attempted speech or attempted handwriting, decoding the brain activity of attempted mouth or arm movements into words. Here, the scientists used an iBCI setup to detect the attempted finger movements when people tried to type on a standard keyboard.
At a neurological level, this typing approach may offer some advantages: The brain activity that controls the movement of each finger is relatively well characterized, and because standard keyboards use the same layout, this approach doesn’t have as much variability as attempting to decode individualized handwriting.
And in an era when many people communicate online, typing may feel more natural to some than speaking or writing longhand.
The researchers tested their approach in two people who were paralyzed, one due to ALS and one from a spinal cord injury. Both patients received the iBCIs as part of an ongoing clinical trial called BrainGate2 (NCT00912041), which is recruiting people with ALS and other paralyzing conditions at five U.S. sites.
The trial is being conducted by the Braingate consortium, a group of scientists, engineers, and physicians from several leading institutions dedicated to advancing iBCI technology.
“Since 2004, our BrainGate team has been advancing and testing the feasibility and efficacy of implantable brain computer interfaces to restore communication and independence for people with paralysis,” said study co-author Leigh Hochberg, MD, PhD, director of the Center for Neurotechnology and Neurorecovery at Mass General Brigham Neuroscience Institute and leader of the clinical trial.
The effort “demonstrates the strength of academic and university-based researchers working together, thinking about what’s possible, and then advancing the frontiers of restorative neurotechnology,” Hochberg said. “And by doing so, we make it that much easier for industry to create the final form of implantable medical devices for our patients.”
Study participants had sensors implanted into the motor cortex, a region of the brain that controls movement, and were shown a QWERTY keyboard with each letter mapped onto fingers and finger positions.
After calibrating the devices with as few as 30 sentences, both people who received the typing-based iBCIs were able to communicate quickly and accurately with the setup and use it at home.
One participant reached a maximum typing speed of 22 words per minute, with a word error rate of 1.6%. That’s on par with the typing accuracy of able-bodied people, and faster than the rates reported for some previous iBCI systems based on attempted handwriting.
The researchers hope to expand on these findings and integrate the typing-based approach into broader communication systems, allowing typed text to be either spoken aloud using text-to-speech tools or used directly for digital interactions such as email and messaging.
The team also noted plans to refine the system to enable users to switch between different sets of keys, such as numbers or special characters, potentially through attempted wrist gestures.
“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,” said Justin Jude, PhD, a postdoctoral researcher at Mass General Brigham and co-author of the study. “And there’s also room to make this communication tool better—like implementing a stenography or otherwise personalized keyboard to make typing even faster. Our BCI is a great example of how modern neuroscience and artificial intelligence technology can combine to create something capable of restoring communication and independence for people with paralysis.”
