Sep 25, 2018   SOURCE: BusinessWire

Battelle Shows NeuroLife System’s Machine Learning Prowess in Nature Medicine

During the past four years, Battelle scientists and their colleagues at The Ohio State University Wexner Medical Center (OSU) have shown the world that patients with spinal cord injuries can regain movement in their paralyzed limb using the Battelle NeuroLife® system. In a new paper published in the prestigious international journal Nature Medicine they are demonstrating how their advances might help the NeuroLife system emerge from the laboratory and enter the homes of users.

Battelle’s brain-computer interface neurotechnology, called NeuroLife, began in 2014. Surgeons at OSU implanted a chip called the Blackrock Utah Array into the brain of the study participant, a young man suffering from quadriplegia following a diving accident. The chip receives neural signals from his brain and sends them to a computer. NeuroLife’s machine learning algorithms decode the participant’s intended movement from the neural data. When the intent to move is decoded, the system sends electrical stimulation to a multi-electrode sleeve on the subject’s arm that provides electrical stimulation to the appropriate muscles to evoke the desired movement.

The current NeuroLife system is used in a controlled laboratory setting, but many hardware and software advances necessary for it to operate in a home environment are in development now at Battelle.

“This is a critical question we’re focused on answering,” said Dave Friedenberg, a Battelle statistician who leads the NeuroLife Machine Learning team and is a co-author of the paper. “What needs to happen for this system to go home with users in the future?”

Necessary advances to enable NeuroLife home use include making the system smaller and more rugged, with high accuracy, rapid response times, multi-functionality and short setup times.

The Nature Medicine paper from the NeuroLife team introduces a novel deep neural network decoding framework aimed at increasing system usability to facilitate the transition of the technology from the lab to the home setting. The neural decoding component of Battelle’s NeuroLife system—the algorithm that translates patterns of brain activity into intended user action—currently limits several desired system characteristics because it requires recalibration every session, with considerable time commitment from the user and the technical team.

In the paper, researchers show that their new decoding method displays highly accurate performance, can sustain this performance for over a year without daily recalibration, responds faster than a current state-of-the-art method that requires greater set-up time, and can increase the number of available functions. They further demonstrated that the study participant could use the decoder to control electrical stimulation of his paralyzed forearm, allowing him to accurately manipulate three common everyday objects.

Surveys conducted by the University of Pittsburgh and the University of Michigan indicated that potential users prioritize high accuracy, minimal daily setup, rapid response times and multi-functionality. “Our paper shows that neural decoders can be designed to help meet these potential end-user performance expectations and advance the clinical translation of the technology,” said Battelle statistician and lead author Michael Schwemmer.

About Battelle

Every day, the people of Battelle apply science and technology to solving what matters most. At major technology centers and national laboratories around the world, Battelle conducts research and development, designs and manufactures products, and delivers critical services for government and commercial customers. Headquartered in Columbus, Ohio since its founding in 1929, Battelle serves the national security, health and life sciences, and energy and environmental industries. For more information, visit www.battelle.org.