“Mental reading” technology allows the paralyzed man to send text messages quickly

0
203


By Amy Norton
HealthDay Reporter

WEDNESDAY, May 12, 2021 (HealthDay News) – A microchip implanted in the brain has allowed a paralyzed man to communicate via text, at speeds approaching the typical smartphone user.

The achievement is the latest breakthrough in “brain-computer interface” (BCI) systems.

Scientists have been studying BCI technology for years, with the goal of giving people a day off paralysis or amputations of more independent limbs in their daily lives.

It basically works like this: small chips are implanted in the areas of the brain related to movement, where they take advantage of the electrical activity of the cells. When a person imagines himself performing a movement, the relevant brain cells begin to shoot. These electrical signals are transmitted by cables to a computer, where they are “decoded” by sophisticated algorithms and translated into actions, allowing people to control assistive devices with his own mental power.

Researchers at some universities have used BCI to allow a small number of patients to mentally control robotic limbs or move computer cursors to “write” text.

Continued

In the new study, researchers at Stanford University managed to accelerate the latter ability in a man with full-body paralysis. Instead of mentally moving the cursor from a computer, the researchers asked him to imagine handwriting.

The approach allowed him to finish the text at a speed of about 18 words per minute, or double what he had achieved with the mental writing tactic.

The researchers said the man’s advanced performance is almost at the same level as the typical smartphone user.

“We think it’s pretty remarkable,” said co-senior researcher Dra. Jaimie Henderson, professor of neurosurgery at Stanford University in California.

Henderson stressed, however, that the technology is limited to the research lab for now. It still requires equipment, cables and technical experience that are unrealistic for home use.

Krishna Shenoy, a professor of electrical engineering at Stanford and the other lead author of the study, said, “We can’t predict when there will be devices that can be used clinically.”

Both investigations said the findings represent progress in the field.

“We’re very excited about the future,” Henderson said.

Continued

The study participant, known as T5, lost almost all of his movement below the neck after suffering a spinal cord injury in 2007. Nearly a decade later, Henderson implanted two microchips into the motor cortex. ‘man, an area of ​​the outermost layer of the brain that governs the will movement.

Each chip is the size of a baby aspirin and contains electrodes that pick up signals from neurons involved in hand movement.

In a 2017 study, T5 and two people with paralysis learned to mentally move a cursor around a keyboard displayed on the computer screen, simulating typing. T5 was able to extract 40 characters (or about eight words) per minute.

This time, the researchers tried a new approach, where computer algorithms decoded mental writing.

First, T5 pictured himself writing individual letters, using a pen on a legal block. (“It was very specific about that,” Henderson noted.) Through repetition, the software “learned” to recognize the brain signals associated with the T5 effort to write a given letter.

Continued

He then graduated by writing sentences mentally and, over time, the algorithms improved by reading his neural trait patterns, until he managed to get 90 characters, or 18 words, per minute.

It turns out that the handwriting display, with its curves and speed changes, provides a “rich signal” that is easier to decode than the straight-line movement of a cursor, Shenoy explained.

Jennifer Collinger is an associate professor at the University of Pittsburgh who develops BCI technology.

He said the new discoveries were a major scientific breakthrough, but warned that much work remains to be done before BCI moves into the real world.

“These systems need to be wireless, reliable and work when you need them,” Collinger said.

The hardware itself, he added, will have to last many years.

Collinger was able to see how different developing BCI systems could be put together: a mind-controlled robotic member could have many daily uses, but, Collinger said, it might not be a great tool for sending text messages.

The research, published May 12 in the journal Nature,it was funded by government and private grants. Stanford University has applied for a patent on intellectual property associated with the work.

Continued

More information

The Christopher and Dana Reeve Foundation has more information living with paralysis.

SOURCES: Jaimie Henderson, MD, Professor of Neurosurgery, Stanford University Medical Center, Stanford, California; Krishna Shenoy, Ph.D., professor of electrical engineering, Stanford University; Jennifer Collinger, PhD, Associate Professor of Physical Medicine and Rehabilitation, University of Pittsburg; Nature, May 12, 2021, online



Source link