Temporal Basis Function Models for Closed-Loop Neural Stimulation

2025-07-21

AI Summary

To address clinical deployment bottlenecks in personalized closed-loop neuromodulation—namely, limited data, slow training, and high inference latency—we propose Temporal Basis Function Models (TBFMs), enabling efficient, low-latency, and deployable forward prediction. TBFMs integrate optogenetic stimulation with local field potential (LFP) recordings within a linear–nonlinear system identification framework, achieving single-trial spatiotemporal dynamics prediction. Evaluated across 40 experimental sessions, TBFMs require only 2–4 minutes of training and achieve inference latency as low as 0.2 ms—significantly outperforming linear models and matching the accuracy of state-of-the-art nonlinear baselines trained for several hours. Crucially, TBFMs are the first method to jointly satisfy high predictive accuracy, sample efficiency, millisecond-scale real-time inference, and rapid adaptability. This establishes a clinically translatable AI modeling paradigm for personalized closed-loop neurostimulation in disorders such as Parkinson’s disease.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Multimodal Learning

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• Tailoring closed-loop neural stimulation for individual patients using AI
• Reducing sample efficiency and training time in neural stimulation models
• Minimizing loop latency for real-time brain activity response

Innovation

• Temporal basis function models for neural stimulation
• Sample-efficient single-trial spatiotemporal prediction
• Low-latency closed-loop stimulation control