New breakthrough in brain-computer interface: Paralyzed patients can write with their mind, with 99% accuracy

The research team combined artificial intelligence software with a brain-computer interface device and worked with a paralyzed patient who had the device implanted in his brain to let the patient imagine that he was holding a pen and "trying" to write on a piece of lined paper, as if his hand was not paralyzed. And quickly converted the man's handwriting intention into text on the computer screen. "This brain-computer interface is designed for people with 'Locked-in Syndrome', who have paralyzed almost all of their voluntary muscles and cannot speak or communicate." Dr. Francis R. Willett, the corresponding author and first author of the study, said, "Imagine if you can only move your eyes up and down but can't move. Such a device can allow you to enter your thoughts at a speed comparable to normal handwriting or typing on a smartphone."

Willett is a research scientist at the Stanford University Neurorestoration Translational Laboratory, appointed by the Howard Hughes Medical Institute. His research focuses on improving brain-computer interfaces and understanding how the brain expresses and controls movement. In addition to Willett, the research is mainly directed by Stanford neurosurgeon Henderson and Krishna Shenoy, a researcher at the Howard Hughes Medical Institute at Stanford University. Willett is a member of Shenoy's team. Shenoy and Henderson have been collaborating on brain-computer interface research since 2005.

Nature also published a perspective article on the study by two researchers, Pavithra Rajeswaran and Amy Orsborn, from the University of Washington. "Although there is still a lot of work to be done, the study by Willett and his colleagues is a milestone that broadens the horizons of invasive brain-computer interface applications." They commented that the method in this study "brings neural interfaces that allow rapid communication closer to reality."

The brain-computer interface used in this study is for research purposes only and has not been approved for commercial use. Stanford’s Office of Technology Licensing has applied for patents on intellectual property related to the work of Willett, Henderson and Shenoy.