BCI devices enable those with motor disabilities like paralysis to control prosthetic limbs, computers and other interfaces by using their minds. However, one of the biggest problems to using these devices in a clinical setting is the instability in the neural recordings themselves as with time the signals picked up by the BCI can vary and as a result the individual can lose the ability to control the device.
When loss of control occurs the individual must go through a re-calibration session that requires them to go through a process to reset the connection between their mental commands and the tasks being performed, and typically a technician needs to be involved just to get the system to work.
“Imagine if every time we wanted to use our cell phone, to get it to work correctly, we had to somehow calibrate the screen so it knew what part of the screen we were pointing at,” says William Bishop, who was previously a PhD student and postdoctoral fellow in the Department of Machine Learning at CMU and is now a fellow at Janelia Farm Research Campus. “The current state of the art in BCI technology is sort of like that. Just to get these BCI devices to work, users have to do this frequent recalibration. So that’s extremely inconvenient for the users, as well as the technicians maintaining the devices.”
This report presents a machine learning algorithm that is suggested to be able to account for these varying signals to allow the individual to remain in control of the BCI in the presence of these instabilities by leveraging the finding that neural population activity resides in a low dimensional neural manifold. Neural activity can be stabilized to maintain good BCI performance even in the presence of recording instabilities according to the researchers.
“When we say ‘stabilization,’ what we mean is that our neural signals are unstable, possibly because we’re recording from different neurons across time,” explains Alan Degenhart, a postdoctoral researcher in electrical and computer engineering at CMU. “We have figured out a way to take different populations of neurons across time and use their information to essentially reveal a common picture of the computation that’s going on in the brain, thereby keeping the BCI calibrated despite neural instabilities.”
“Let’s say that the instability were so large such that the subject were no longer able to control the BCI,” explains Byron Yu, a professor of electrical and computer engineering and biomedical engineering at CMU. “Existing self-recalibration procedures are likely to struggle in that scenario, whereas in our method, we’ve demonstrated it can in many cases recover from those catastrophic instabilities.”
“Neural recording instabilities are not well characterized, but it’s a very large problem,” says Emily Oby, a postdoctoral researcher in neurobiology at Pitt. “There’s not a lot of literature we can point to, but anecdotally, a lot of the labs that do clinical research with BCI have to deal with this issue quite frequently. This work has the potential to greatly improve the clinical viability of BCIs, and to help stabilize other neural interfaces.”
This report is not the first to propose a self re-calibration method as the issue with unstable neural recordings has been the subject of debate for many years. A few studies have suggested procedures but they have faced issues when dealing with the instabilities. The current method presented in this report suggests that it is able to recover from catastrophic instabilities as it does not rely on the subject performing well during the re-calibrations.
