Non -invasive decoders could help restore the movement after a spinal cord injury

If a person violates a violation of the spinal cord, normal communication between the brain and the spine circuit is interrupted below the injury, which leads to paralysis. Since the brain works normally, like the spinal cord below the injury, researchers have worked to restore communication in order to enable rehabilitation and possibly restore the movement.

Ismael Seáñez, assistant professor for biomedical engineering at the McKelvey School of Engineering at Washington University in St. Louis and neurosurgery in the Washu Medicine, and members of his laboratory, including Carolyn Atkinson, a doctoral student, have developed a kind of decoder to restore this communication. Through experiments in their laboratory with 17 human subjects without spinal cord injury, they were able to address the movement in the lower leg with a transcutaneous spinal cord stimulation or non -invasive external electrical impulses.

The results of the research were published online on April 25, 2025 on April 25, 2025 Journal of Neuroengineering and Rehabilitation.

The team used a special cap with non -invasive electrodes that measure brain activity through electroencephalography (EEG). Volunteers were asked to extend their legs on the knee while wearing the hat, and then only to think about expanding their leg – while it stays still – so that the researchers could record the brain waves in both exercises.

The team provided neural activity to the decoder or the algorithm, so that under both circumstances it could learn how the brain waves work. They found that the actual movement and the imaginary movement used similar neuronal strategies.

After we have given the decoder this data, it learns to predict on the basis of neuronal activities when there is movement or movement. We show that we can predict if someone thinks about moving his leg, even if his leg doesn't really move. “

Ismael Seáñez, assistant professor of biomedical engineering at the McKelvey School of Engineering at Washington University in St. Louis and neurosurgery in Washu Medicine

The team used controls to ensure that the volunteers really imagined a movement and did not actually move.

“If people move, this can introduce the noise noise and we want to make sure that the noise noise is not what we learn to predict,” said Seáñez. “It is an intention to move or the brain activity that we want to predict. So we have the people to imagine that they expand their leg and use the same algorithm who was trained in people who move to predict whether they are imagining or not.”

Seáñez said this reveals two things.

“First of all, it is more likely that we decode the intention to move and not an artifact or sound and secondly, if we use this in people with spinal cord injuries that do not have this ability to move your legs for us to mark the data.

Seáñez said that the Proof-of-Concept study is a first step in the development of a non-invasive interface between brain economy that uses real-time predictions in order to provide transcutaneous spinal cord stimulation in order to strengthen the voluntary movement in a single joint in rehabilitation in patients with a spinal cord injury.

In the future, the team plans to test a generalized decoder that has been trained on data from all participants who can determine whether a universal decoder is practically a personalized implementation and simplifies its use in clinical environments.