The neural bypass works using a microelectrode array implanted in
Burkhart’s brain. The implant picks up activity in a specific area of
his left motor cortex, which researchers had analyzed prior to placing
the implant. Using functional magnetic resonance imaging (fMRI), which
tracks brain activity based on blood flow, the researchers pinpointed
the hand-controlling area of Burkhart’s brain while he repeatedly
thought about moving his hand.

In the clinic, the implanted electrode hooks into a custom-built
“neural bypass system.” The system picks up the signals from Burkhart’s
brain activity, then, using machine learning algorithms, translates
those signals to control a flexible arm sleeve, outfitted with 130
muscle-stimulating electrodes.

To get it to work, Burkhart attended three weekly sessions for 15
months. He mastered controlling his thoughts and could pull off six hand
and wrist movements, including the ability to move individual fingers.

“The ability to move individual fingers—we were not sure if this
would be possible,” first author Chad Bouton, of Feinstein Institute for
Medical Research, said. “This result really exceeded our expectations
because not only were we able to find those signals in the brain and
decipher those signals for that individual finger movement, but we were
able to link those signals to Ian’s muscles and allow that kind of
movement to be regained.”

After that, Burkhart went on to learn more complex tasks, like playing Guitar Hero and putting a cup to his mouth.

Using synthetic nervous system, paralyzed man is first to move again