Cathal Harte of NeuroRestore develops software with the goal of interpreting the brain’s intentions to restore motor function.
Researchers in Switzerland are working on groundbreaking studies that could give people with paralysis the ability to walk again by sending electrical impulses to targeted nerves.
NeuroRestore is a research, innovation and treatment center focused on “Electroceuticals” – a type of neurotherapy that uses electrical stimulation to support neurological function. There are various possible applications for this, for example to improve motor skills in people with a stroke or Parkinson’s disease.
However, an important area of research is the restoration of motor function for people with chronic spinal cord injuries. NeuroRestore researchers have been working on a proof-of-concept clinical study called Stimo, which has shown very positive results in experimental treatments that help people with complete paralysis walk.
One of the people working on this technology is Cathal Harte, an Irish software engineer who joined NeuroRestore in 2020. He leads the development efforts behind the center’s clinical software.
The NeuroRestore center was founded by the Defitech Foundation, the University Hospital of Lausanne, the Faculty of Biology and Medicine of the University of Lausanne and the Swiss Federal Institute of Technology (EPFL).
Some members of the team behind NeuroRestore made headlines in 2018 after using continuous electrical stimulation and a pacemaker-like implant to help David Mzee, a man who lost his legs after a spinal cord injury, walk again.
“I was tasked with bringing next-generation software that really opened the door to ways to do things automatically,” Harte told SiliconRepublic.com.
Harte and the team at NeuroRestore aim to have this software eventually interpret the brain’s motor intentions and translate them into targeted epidural spinal stimulation that can restore movement to people with paralysis.
development of the software
Harte said the first generation of NeuroRestore software was simpler. It allowed users to make “eye-based assessments” of the electrical stimulations with a separate app.
An important part of developing the software is testing different stimulation settings on different nerves. The team can examine this electromyography or EMG data to see which muscles are activated by stimulating specific nerves.
“The data is an essential part of the mapping process, serving the patient right in front of you,” Harte said.
This data is then used to understand exactly how the nerves are stimulated to produce a specific movement, e.g. B. a walking motion. Because everything is built into the latest version of the software, Harte says it’s possible to incorporate machine learning.
“We know exactly what configuration we’re sending, we know exactly how long we’re stimulating,” he explained. “We can tag all muscle signals with this information, send it all to a machine learning program, and then it can make the calls.”
Harte explained that machine learning is an important step in bringing this type of technology to product maturity.
“If you’re a dedicated research team, you have a patient about every six months, then you can do that with a bunch of very smart people in the room looking at the data manually,” Harte said. “But if you’re going to bring that to hundreds of thousands of people, you need to automate things like that.”
One participant in the Stimo study is Michel Roccati, an Italian who became paralyzed after a motorcycle accident.
Harte said previous patients in STIMO studies had some ability to move their legs, so the focus was on aiding the rehabilitation process and giving them “the missing parts of their walking patterns.” Roccati couldn’t move his legs at all, but Harte said the results had been “amazingly successful” and the man was able to walk again.
“First of all, it’s just his attitude. He’s an incredibly dedicated guy. He’s really motivated to do this,” Harte said.
After inserting a surgical implant into his spinal cord, the NeuroRestore team attached two remote controls to Roccati’s walker.
These controls were connected wirelessly via a tablet, which relayed the signals to a pacemaker in his abdomen, which then relayed the signals to the implant, which stimulates specific neurons.
“That triggers a step to the left or a step to the right. And if it doesn’t trigger a left separate step, it’s standing stimulation. So essentially this gives him autonomy when walking.”
According to NeuroRestore, the three patients involved in this study followed a stimulation program-based exercise regimen and were able to regain muscle mass, move more independently, and participate in social activities such as drinking while standing at a bar.
Some of the products that could result from these studies will be demonstrated by Onward Medical, a medtech company that has a research partnership with NeuroRestore and was involved in the STIMO study.
Onward is developing two technology platforms based on targeted nerve stimulation to attempt to solve multiple medical problems.
For example, the company’s ArcEx platform aims to improve physical movement of hand and arm function for people with spinal cord injuries. This is an external device that contains a wearable stimulator and a wireless programmer.
The other device, ArcIm, is an implantable pulse generator and lead that is placed near the spinal cord. This device was used in the Stimo study, but Onward believes it may help in other areas as well, such as improved sexual function, bladder and bowel control.
One study Harte is excited about is NeuroRestore’s Brain Spine Interface study, which aims to create a digital bridge between the brain and spinal cord to restore motor control to paralyzed limbs.
According to the center, using various brain recording techniques such as electroencephalography, electrocorticography and intracortical recordings, it is possible to decode motor intentions and convert them into targeted stimulations.
“There’s an implanted brain decoder, you remove parts of the skull and replace it with a sensor,” Harte explained. “Then you train pattern recognition algorithms to say, OK, remember to move your left leg, remember to move your toe, think about different things, and it learns these brain states.
“And so it’s able to match what it’s perceiving with intentions, and then we convert those intentions into spinal cord stimulation.”
10 Things You Need to Know, straight to your inbox every weekday. Sign up for the Daily shortSilicon Republic’s Digest of Essential Sci-Tech News.