Press "Enter" to skip to content

BrainGate interface improvements allow for better accuracy, longer sessions

Three software innovations have improved the user experience and performance of the BrainGate brain computer interface at Brown University, according to results recently published in Science Translational Medicine.

According to a Brown University press release, the goal of the BrainGate project is to create a brain computer interface (BCI) that allows people with paralysis to independently control external devices with ease and consistency. BrainGate is an intracortical BCI, which converts brain signals into digital commands. Signals are translated by a decoder controlled by an algorithm.

The new advances allow the system to decode movement with fewer interruptions. The algorithm is able to update itself, eliminating the need for the user to stop a calibration task whenever signals change. According to the study results, the new decoder preserves BCI performance for a longer time and was shown to improve users’ accurate typing speed on an on-screen keyboard.

“Eliminating the need to run a calibration task whenever the recorded signals change will make a clinical BCI more user-friendly and easy to use,” Beata Jarosiewicz, PhD, assistant professor of neuroscience at Brown University and the Brown Institute for Brain Science, investigator at the Providence Veterans Affairs Medical Center (PVAMC) and a lead author of the study, stated in the release.

“Watching our participants use this more robust system to type on a computer screen highlights the progress being made toward a clinically useful system,” Leigh Hochberg, MD, PhD, professor of engineering at Brown, director of the Center for Neurorestoration and Neurotechnology at PVAMC, director of the Neurotechnology Trials Unit at MGH Neurology and senior author of the paper, added.

The innovations in the BCI make use of the data gathered from trial participants, learning to better interpret their intentions the more they use the system. In addition, the decoder can now track baseline levels of neural activity in the motor cortex when participants voluntarily pause their actions. This improves the system’s calibration, according to the release. The third innovation tracks emerging biases in the velocity of cursor movement for individual users and removes them from the decoded movements, reportedly leading to improved accuracy.

Researchers tested the innovations by asking participants to type for an hour or 2 hours in some sessions with the new features engaged and other sessions without the new features. Results showed performance was consistent when the features were turned on, but “degraded significantly” when the features were turned off, according to the release. The system was even able to rescue degraded performance when the new features were turned on in the midst of a research session.

The researchers hope to apply the improvements to other BCI tasks, such as 3-D control of a robot arm or the person’s own electronically re-animated arm or hand.

“There is still a lot of research to do,” Hochberg stated. “With continued clinical research, we will learn how our findings extend to more participants. We want to make the system faster, easier, smaller, fully implanted, more portable, less requiring of an expert researcher or caregiver, and more nimble in its ability to provide control of external devices.”

He added, “In these studies, we are making steps toward robust and flexible communication systems for people with severely limited movement, including limited or no speech. We are also dedicated not only to enabling control over computers or robotic assistive devices, but — for people with spinal cord injury or stroke — working toward the goal of reconnecting brain to limb, allowing the powerful intracortical signals to activate fully implanted functional electrical stimulation devices, and re-enabling intuitive movement of one’s own arm and hand.”

Reference: Jarosiewicz B, et al. Sci Transl Med. 2015;doi: 10.1126/scitranslmed.aac7328.

Disclosures: Jarosiewicz reports the research was supported by the Department of Veterans Affairs (Rehabilitation Research & Development Service awards: B6310W, B6453R, B6459L, A6779I); the National Institutes of Health (NIDCD grants R01DC009899, R01DC014034; NICHD-NCMRR grants N01HD10018, RC1HD063931, N01HD53403; and NINDS grant R01NS066311-S1); the Doris Duke Charitable Foundation; the MGH-Deane Institute; the Joseph Martin Prize for Basic Research; the Katie Samson Foundation; the Craig H. Neilsen Foundation; Stanford BioX-NeuroVentures and the Garlick Family.

Be First to Comment

Leave a Reply

Your email address will not be published.