Abstract
Objective: A major challenge in closed-loop brain-computer interfaces (BCIs) is finding optimal stimulation patterns as a function of ongoing neural activity for different subjects and objectives. Traditional approaches, such as those currently used for deep brain stimulation, have largely followed a trial- and-error strategy to search for effective open-loop stimulation parameters, a strategy that is inefficient and does not generalize to closed-loop activity-dependent stimulation. Approach: To achieve goal-directed closed-loop neurostimulation, we propose the use of brain co-processors, devices which exploit artificial intelligence (AI) to shape neural activity and bridge injured neural circuits for targeted repair and rehabilitation. Here we investigate a specific type of co-processor called a "neural co-processor" which uses artificial neural networks (ANNs) to learn optimal closed-loop stimulation policies. The co-processor adapts the stimulation policy as the biological circuit itself adapts to the stimulation, achieving a form of brain-device co-adaptation. We tested the neural co-processor's ability to restore function after stroke by simulating a variety of lesions in a previously published cortical model of grasping. Main results: Our results show that a neural co-processor can restore reaching and grasping function after a simulated stroke in a cortical model, achieving recovery towards healthy function in the range 75-90%. Significance: This is the first proof-of-concept demonstration, using computer simulations, of a neural co-processor for activity-dependent closed-loop neurosimulation for optimizing a rehabilitation goal after injury. Our results provide insights on how such co-processors may eventually be developed for in vivo use to learn complex adaptive stimulation policies for a variety of neural rehabilitation and neuroprosthetic applications.
Abstract (translated)
URL
https://arxiv.org/abs/2210.11478
