Temporal Basis Function Models for Closed-Loop Neural Stimulation

TL;DR

This paper introduces temporal basis function models (TBFMs) for efficient, low-latency closed-loop neural stimulation, demonstrating their ability to predict and control neural activity in primate models with minimal training data.

Contribution

The paper presents TBFMs as a novel, simple, and sample-efficient approach for real-time neural prediction and control, bridging AI modeling with clinical neural stimulation applications.

Findings

TBFMs accurately predict optogenetic effects on neural signals.

TBFMs train rapidly (2-4 min) and operate with low latency (0.2 ms).

Successful closed-loop control demonstrated in simulations.

Abstract

Closed-loop neural stimulation provides novel therapies for neurological diseases such as Parkinson's disease (PD), but it is not yet clear whether artificial intelligence (AI) techniques can tailor closed-loop stimulation to individual patients or identify new therapies. Progress requires us to address a number of translational issues, including sample efficiency, training time, and minimizing loop latency such that stimulation may be shaped in response to changing brain activity. We propose temporal basis function models (TBFMs) to address these difficulties, and explore this approach in the context of excitatory optogenetic stimulation. We demonstrate the ability of TBF models to provide a single-trial, spatiotemporal forward prediction of the effect of optogenetic stimulation on local field potentials (LFPs) measured in two non-human primates. We further use simulations to demonstrate the use of TBF models for closed-loop stimulation, driving neural activity towards target patterns. The simplicity of TBF models allow them to be sample efficient, rapid to train (2-4min), and low latency (0.2ms) on desktop CPUs. We demonstrate the model on 40 sessions of previously published excitatory optogenetic stimulation data. For each session, the model required 15-20min of data collection to successfully model the remainder of the session. It achieved a prediction accuracy comparable to a baseline nonlinear dynamical systems model that requires hours to train, and superior accuracy to a linear state-space model. In our simulations, it also successfully allowed a closed-loop stimulator to control a neural circuit. Our approach begins to bridge the translational gap between complex AI-based approaches to modeling dynamical systems and the vision of using such forward prediction models to develop novel, clinically useful closed-loop stimulation protocols.