Researchers at University of Utah have reported early success in using microelectrodes implanted over speech centers in the brain to translate brain signals into words. According Bradley Greger, an assistant professor of bioengineering, the initial success in decoding spoken words may eventually lead to a device for paralyzed patients who suffer from locked-in syndrome. Greger’s “proof of concept" study of this approach is due to appear in Journal of Neural Engineering's September issue.
The research team put grids of microelectrodes over speech centers in the brain, using a volunteer with severe epileptic seizures who’d already had a craniotomy. The study used microECoGs, a new kind of nonpenetrating microelectrode that sits on the brain without poking into it. Microelectrode grids were placed over the facial motor cortex and Wernicke's area, and brain signals were recorded as the patient repeated 10 simple words. When researchers compared brain signals, they were able to distinguish at rates above chance, but accuracy was not yet sufficient for a device to translate a paralyzed person's thoughts into words spoken by a computer. The researchers were 85 percent accurate in distinguishing brain signals for one word from another when they used signals recorded from the facial motor cortex rather than Wernicke's area.
“The obvious next step,” Greger said, is “to make the grid bigger, have more electrodes and get a tremendous amount of data out of the brain, which probably means more words and better accuracy."
More information is available at The University of Utah News Center.
Ms. Graham is a writer and editor with a current focus on health and wellness. To read more of her articles, please visit her columnist page.Edited by
Erin Monda