A team at UC Davis and UC Davis Health has demonstrated that brain-computer interfaces (BCIs) designed for translating brain signals into speech can also allow users to control a computer cursor. The research, published in the Journal of Neuroengineering, was supported by the National Science Foundation and the National Institutes of Health.
The study is a collaborative effort among engineers, neuroscientists, and neurosurgeons. Tyler Singer-Clark, a biomedical engineering Ph.D. student and first author, said, “Future steps in multimodal BCIs could include gesture decoding for all sorts of different things, enriching the types of interactions someone with paralysis can have with their environment beyond speech.”
Singer-Clark is part of the UC Davis Neuroprosthetics Lab, which is co-directed by neuroscientist Sergey Stavisky and neurosurgeon David Brandman. The lab previously developed what they describe as the most accurate BCI for speech. The new project builds on this earlier work.
The team’s BCI is implanted in the speech motor cortex and interprets electrical activity from thought into words displayed on a computer. They observed that this area of the brain could also support cursor control, a function typically associated with a different region.
Singer-Clark developed software for cursor control based on prior research and existing code from the lab’s speech BCI. He said, “We didn’t have to reinvent the pre-processing of the neural data. For cursor control, it’s actually the same pre-processing steps the speech BCI uses to get the neural features that are going to be useful for decoding the intention of the participant.”
The team individualized the decoding architecture by working with a participant from the original speech BCI research as part of the BrainGate clinical trial. The participant has amyotrophic lateral sclerosis (ALS), a disease that causes gradual loss of movement.
During testing, Singer-Clark had the participant watch a cursor move and select targets on a screen while monitoring neural activity. This data was mapped to the cursor control software. Once enabled, the participant adapted to controlling the cursor with his thoughts in less than 40 seconds. He was able to move the cursor, click on applications, and open links.
Singer-Clark noted that the BCI does not translate abstract thoughts into movement but relies on a sense of intuition. “That’s his word, intuition,” Singer-Clark said. “I’ll say, ‘What motor imagery are you using?’ And he says, ‘Intuition.’”
Brandman said, “Singer-Clark’s work is incredibly important for the field. His work has not only empowered our BrainGate2 participant to use a computer cursor with his thoughts but has also led the way for multiple companies in this space to design their clinical trials.”
Singer-Clark emphasized both the scientific and personal impact of the project. He said it supports a growing view that different body parts and movements are represented across multiple areas of the motor cortex. He also highlighted its significance for individuals: “There’s a man with ALS who can control his computer independently without someone else helping him for hours and hours every day. It’s like this great event, and we might not have tried if we didn’t have that prior research encouraging us to do that.”
The research points toward future developments in BCIs that could restore greater autonomy for people with paralysis.
