Paralyzed Patients Use New Brain Stent and AI to Control Computer
A new study of Stentrode BCI enables paralyzed people to resume daily tasks.
Posted Oct 30, 2020
Can the human mind control external digital devices by thoughts alone? Scientists affiliated with the University of Melbourne and Synchron, Inc. published earlier this week in the Journal of NeuroInterventional Surgery the first-in-human study of Stentrode™, a wireless neuroprosthesis that uses machine learning and a stent.
What makes the Stentrode™ technology unique is that it is a stent that records brain activity inside a blood vessel in the brain. It is implanted through the jugular vein so there is no need for open brain surgery. The technology platform originated from the University of Melbourne, in a collaborative effort with the Royal Melbourne Hospital, the Florey Institute of Neuroscience and Mental Health, Monash University, and Synchron, Inc.
A brain-computer interface (BCI) enables two-way communications between the biological brain and a machine. In the field of health care and life sciences, the hope is that brain-computer interfaces can help those with paralysis and brain disorders by restoring independence.
Synchron, Inc. is a clinical-stage neurovascular bioelectronics startup with Series A funding that was founded by Thomas Oxley and Nicholas Opie in 2016 with headquarters in the Silicon Valley. Co-founder Oxley, a Ph.D. and M.D. with over 50 patents filings, garnered initial seed funding by cold calling potential investors. It was successful as Oxley has already raised USD 25 million. Former U.S. President Barack Obama describes the technology as having “the potential to transform the lives of our wounded warriors and others with disabilities.”
In this brain-computer interface breakthrough study, two amyotrophic lateral sclerosis (ALS) patients were implanted a Stentrode BCI in a blood vessel inside the brain in a minimally invasive procedure. Specifically, the location of the implant was adjacent to primary motor cortex in the superior sagittal sinus, adjacent to the precentral gyrus.
“The participants undertook machine-learning-assisted training to use wirelessly transmitted electrocorticography signal associated with attempted movements to control multiple mouse-click actions, including zoom and left-click,” the researchers wrote in the study.
For the first participant, a support vector machine (SVM), a supervised machine learning model that can process complex data transformations, and Gaussian radial basis functions were used. For the second participant, a threshold classifier was applied.
For both participants, the predictions from the classification layer were passed through a layer which interpreted predictions into commands such as click movement.
“Used in combination with an eye-tracker for cursor navigation, participants achieved Windows 10 operating system control to conduct instrumental activities of daily living (IADL) tasks,” wrote the researchers.
The study reported results of a click selection accuracy of around 93 percent on average. The brain-computer interface enabled participants to use brain impulses to control digital devices. Both participants were able to independently perform tasks such as managing finances, online shopping, and text messaging.
“These first in-human data demonstrate the potential for an endovascular motor neuroprosthesis to achieve digital device control with multiple commands in people with paralysis and, when combined with eye-tracking, to improve functional independence,” reported the researchers.
With this new proof-of-concept in humans, scientists have achieved an important milestone in brain-computer interfaces. Advances in artificial intelligence combined with neuroscience offer those suffering from severe paralysis new hope with the potential for a better, more independent future.
Copyright © 2020 Cami Rosso All rights reserved.