How can we improve decoder algorithms to enhance neuroprosthetic control?
We have spearheaded the development of closed-loop decoder adaptation (CLDA) algorithms, where the parameters of the BMI decoder are adapted during closed-loop operation (i.e., while the subject is using the BMI).
CLDA algorithms represent more accurately the mapping between the user’s neural activity and their intended movements, which accelerates learning and boosts performance. The error signals required to adapt the decoder can be estimated in a variety of different ways, including using the task goals to infer the subject’s intention, Bayesian methods to self-train the decoder, and extracting error signals directly from the brain.
The design process of a CLDA algorithm requires important decisions not only about what parameters of the decoder should be adapted and how these should be adapted, but also when, (i.e., how often), as the rate at which the decoder changes can influence performance. Also important is the way in which the decoder is initialized. Movement disorders such as paralysis and stroke prevent patients from making the types of natural movements that are often used to initiate the decoder. As a result, less favorable methods of decoder initialization such as motor imagery must be used, typically resulting in low initial performance.
To address this problem we developed SmoothBatch, a CLDA algorithm that infers the subject’s intended movement goals during online control and updates the decoder on an intermediate (1–2 min) time-scale. The main feature of SmoothBatch is that it can readily improve performance in a relatively short time, independent of the subject’s initial closed-loop BMI performance. This could be particularly useful in clinical applications in which the patient cannot move the limbs.