Researchers at UC San Francisco (UCSF) have created a device that allowed a paralyzed man to control a robotic arm through his thoughts.
The study, which was funded by the National Institute of Health and published in the scientific journal Cell on March 6, states that the man — who had a stroke years earlier and cannot speak or move — was able to hold, move and drop objects just by imagining himself doing so.
The study potentially has major implications for people with paralysis, as it means they could do simple but critical tasks, such as feeding themselves or getting a drink of water, entirely independently.
According to an update on the university’s website, the new device is a type of brain-computer interface (BCI). Until now, such devices have only worked for up to a day or two at a time without needing outside adjustment from an engineer.
However, the device from the UCSF study reportedly worked up to seven months without requiring an adjustment. This is because this specific device uses artificial intelligence (AI) to adjust to small changes in the brain that occur over time, leading to more refined gestures and less need for external oversight.
Never miss a story — sign up for PEOPLE’s free daily newsletter to stay up-to-date on the best of what PEOPLE has to offer, from celebrity news to compelling human interest stories.
And how does the new BCI work in practice?
Per the university, the man had tiny sensors implanted on the surface of his brain. These sensors picked up brain activity when he imagined certain tasks, like opening his hand or moving his fingers.
The PEOPLE Puzzler crossword is here! How quickly can you solve it? Play now!
The researchers say that while the brain activity associated with these movements largely remained the same over time, their location within the brain could shift slightly from day to day — and this is why AI, which can automatically adjust for these minor changes — proved key.
“This blending of learning between humans and AI is the next phase for these brain-computer interfaces,” said UCSF researcher Karunesh Ganguly, MD, PhD, before noting that he plans to do continued testing on the device in home environments to better refine it.
“I’m very confident that we’ve learned how to build the system now, and that we can make this work,” Ganguly said.
Read the full article here