Think, and it shall be written.

That’s one way to summarize the outcome of a recent study by researchers at Stanford University, who developed an AI-driven Brain-Computer Interface (BCI) device that enable a man with full-body paralysis to communicate by text at a rate of 18 words per minute.

“With this BCI, our study participant, whose hand was paralysed from spinal cord injury, achieved typing speeds of 90 characters per minute with 94.1% raw accuracy online, and greater than 99% accuracy offline with a general-purpose autocorrect,” the researchers said in their report published in Nature.  

For context, able-bodied people can type approximately 23 words per minute on a smartphone, the study reported. 

For the study, two BCI chips were placed on the left side of the participant’s brain, picking up neural signals firing in a specific part of the motor cortex that dictates hand movement. The AI interprets the signals and then displays the subject’s hand motions on a computer screen.   

“We’ve learned that the brain retains its ability to prescribe fine movements a full decade after the body has lost its ability to execute those movements,” said lead author and research scientist at the Howard Hughes Medical Institute, Frank Willett, PhD, in a press release accompanying the report. “And we’ve learned that complicated intended motions involving changing speeds and curved trajectories, like handwriting, can be interpreted more easily and more rapidly by the artificial-intelligence algorithms we’re using than can simpler intended motions like moving a cursor in a straight path at a steady speed. Alphabetical letters are different from one another, so they’re easier to tell apart.” 

The algorithms were designed in Stanford’s Neural Prosthetics Translational Lab, co-directed by Jaimie Henderson, MD, professor of neurosurgery, and Krishna Shenoy, PhD, professor of electrical engineering and the Hong Seh and Vivian W. M. Lim Professor of Engineering.

According to Henderson, the findings could lead to further advances benefiting hundreds of thousands of Americans – and millions globally – who’ve lost the use of their upper limbs or their ability to speak due to spinal-cord injuries, strokes or amyotrophic lateral sclerosis, also known as Lou Gehrig’s disease.

In a 2017 study by the same researchers, the same participant was able to produce approximately 40 characters per minute. The 2021 study asked the participant, referred to as “T5,” to hand-write letters on an imaginary piece of paper.  

In repeating each letter of the alphabet 10 times, the software was able to learn to associate the participant’s effort to write particular letters with corresponding neural signals.   

“In further sessions, T5 was instructed to copy sentences the algorithms had never been exposed to. He was eventually able to generate 90 characters, or about 18 words, per minute,” the press release said. 

Photo by wigglestick/Getty Images