Research collaboration hopes to help the paralysed walk again

Spinal cord injuries can be severely debilitating, if not fatal. Recovery is painful and difficult; patients generally regain the majority of function within the first six months after the injury but any loss that lingers after a year will likely be permanent.

Recent figures reported by the National Spinal Cord Injury Statistical Center (NSCISC) show an annual incidence rate of about 54 cases per one million people across the US. 

This translates to 17,700 new cases per year, with 30 percent of spinal cord injuries resulting in either partial or complete paralysis. 

But an industry-academia research collaboration is exploring innovative ways to reduce that percentage by using artificial intelligence (AI) technologies to restore movement in paralysed limbs.

Engineers and neurosurgeons at Brown University, Rhode Island Hospital, Intel and Micro-Leads Medical will be spending the next two years designing and building an “Intelligent Spine Interface” (ISI), which will record motor and sensory signals from spinal cord neurons in order to learn how to stimulate them using AI.

Surgeons will implant electrodes on both ends of the injury or spinal lesion to create an “intelligent bypass”, through which signals are passed and decoded via Intel tools to (hopefully) communicate motor commands to the damaged nerves and bring back movement to the affected limb.

What researchers are essentially looking to do is try and fix a paralysis by reconnecting the brain with the damaged spinal nerves.

“We know that circuits around a spinal lesion often remain active and functional,” project lead David Borton, an assistant professor at Brown’s School of Engineering and a researcher at the University’s Carney Institute for Brain Science, said in an article on the project by Brown University

“The hope is that by using information from either side of a lesion in a bidirectional way, we could make a significant impact on the treatment of spinal cord injuries.

“This exploratory study aims to build the toolset — the mix of hardware, software, and functional understanding of the spinal cord — to make such a system possible.”

For the project, the group has received a US$6.3 million grant from the US Defense Advanced Research Projects Agency (DARPA). 

They will use AI and machine learning tools supplied by Intel which will help decode signals sent from the brain to the spine, in addition to the necessary hardware, software and expertise. Micro-Leads will provide its expertise and spinal cord simulation technology for the research effort.

The work implanting the electrodes will be carried out by Rhode Island Hospital surgeons. The team will recruit volunteers with spinal cord injuries to carry out the project. The volunteers will participate in physical therapy while being implanted with the interface for up to 29 days.

The initial focus will be on signals related to leg control as well as bladder control, a major area of concern for patients with spinal cord injuries.

“What’s new in this project is taking information from the spinal cord itself and to use that to drive stimulation to another part of the spinal cord,” Borton continued. 

“In this way, we’re taking advantage of as much intact tissue as we can, which we think could lead open the door to wider therapeutic application of spinal cord stimulation, for example, bladder control.”

For the first phase of the project, an external computer will be used to decode the spinal signals. Using their findings from here, the team intends to later develop a fully implantable device capable of decoding signals in real-time.