December 4, 2023


Brain-computer interfaces (BCIs) powered by artificial intelligence (AI) offer hope to the paralyzed; a person can now use their thoughts to control robotic limbs that assist movement. New research published in Science shows how a brain-computer interface endowed with both vision and touch, coupled with an AI decoder improved the ability of a paralyzed person to operate a prosthetic arm.

“The potential benefits of a bidirectional BCI—a system in which tactile sensations are evoked through cortical stimulation while neural recordings during attempted movement are decoded to control a robotic prosthesis—have remained unexplored in humans,” the study authors said in their report. It showed that bidirectional BCI could improve performance on functional tasks substantially.

The study was conducted by the University of Pittsburgh research team of Robert Gaunt, Jennifer Collinger, Michael Boninger, Angelica Herrera, Christopher Hughes, Jeffrey Weiss, John Downey, and Sharlene Flesher, along with Elizabeth Tyler-Kabara at the University of Texas at Austin.

“We supplemented vision with tactile percepts evoked using a bidirectional brain-computer interface that records neural activity from the motor cortex and generates tactile sensations through intracortical microstimulation of the somatosensory cortex,” the researchers noted. A person with tetraplegia could improve their performance with their robotic limb. In addition, the researchers found that trial times on a clinical upper-limb assessment were reduced by half, from a median time of 20.9 to 10.2 seconds.

A quadriplegic male with a spinal cord injury from an automobile accident a decade prior to the study was implanted with two sets of Blackrock’s NeuroPort Array, also known as the Utah array. The paralyzed man was 28 years old when he was implanted with the microelectrode arrays.

“Faster times were primarily due to less time spent attempting to grasp objects, revealing that mimicking known biological control principles results in task performance that is closer to able-bodied human abilities,” the researchers reported.

To gather data to decode the paralyzed man’s intended movement, one set of microelectrode arrays with 88 wired electrodes was implanted in the brain area of the motor cortex that controls hand and arm movement.

A second set of microelectrode arrays equipped with 32 wired electrodes were implanted in the somatosensory cortex area of the brain to produce sensations in the fingers of the right hand with intracortical microstimulation (ICMS).

In neuroscience, intracortical microstimulation is commonly used to spot a causal relationship between a specific brain function and the activity of cortical neurons. Electrodes stimulate and activate nearby neuronal populations by evoking action potentials in neurons. Action potentials in neurons produce nerve impulses, and muscle cells cause contraction needed for movement.

This engineered approach that mimics sensorimotor circuits will impact future research in this area.

Copyright © 2023 Cami Rosso All rights reserved.