A first realization of reinforcement learning-based closed-loop EEG-TMS

2026-02-06

AI Summary

Traditional transcranial magnetic stimulation (TMS) employs a one-size-fits-all approach that fails to account for inter- and intra-individual variations in brain states, thereby limiting its neuromodulatory precision. This study presents the first closed-loop, real-time EEG-TMS system driven by reinforcement learning, which eliminates the need for predefined target phases. Instead, it leverages machine learning to automatically identify individual mu-rhythm phases associated with high or low corticospinal excitability and triggers TMS accordingly in real time. By integrating reinforcement learning, online EEG phase detection, and precise stimulation timing control, the system achieves fully data-driven, user-independent closed-loop neuromodulation for the first time. Experimental results demonstrate its ability to reliably distinguish high- and low-excitability mu phases, with repeated stimulation inducing long-term potentiation or depression of sensorimotor network functional connectivity, respectively, thereby establishing a novel paradigm for personalized brain modulation therapy.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Multimodal Learning
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Background: Transcranial magnetic stimulation (TMS) is a powerful tool to investigate neurophysiology of the human brain and treat brain disorders. Traditionally, therapeutic TMS has been applied in a one-size-fits-all approach, disregarding inter- and intra-individual differences. Brain state-dependent EEG-TMS, such as coupling TMS with a pre-specified phase of the sensorimotor mu-rhythm, enables the induction of differential neuroplastic effects depending on the targeted phase. But this approach is still user-dependent as it requires defining an a-priori target phase. Objectives: To present a first realization of a machine-learning-based, closed-loop real-time EEG-TMS setup to identify user-independently the individual mu-rhythm phase associated with high- vs. low-corticospinal excitability states. Methods: We applied EEG-TMS to 25 participants targeting the supplementary motor area-primary motor cortex network and used a reinforcement learning algorithm to identify the mu-rhythm phase associated with high- vs. low corticospinal excitability. We employed linear mixed effects models and Bayesian analysis to determine effects of reinforced learning on corticospinal excitability indexed by motor evoked potential amplitude, and functional connectivity indexed by the imaginary part of resting-state EEG coherence. Results: Reinforcement learning effectively identified the mu-rhythm phase associated with high- vs. low-excitability states, and their repetitive stimulation resulted in long-term increases vs. decreases in functional connectivity in the stimulated sensorimotor network. Conclusions: We demonstrated for the first time the feasibility of closed-loop EEG-TMS in humans, a critical step towards individualized treatment of brain disorders.

Problem

• closed-loop EEG-TMS
• individualized brain stimulation
• mu-rhythm phase
• corticospinal excitability
• reinforcement learning

Innovation

• reinforcement learning
• closed-loop EEG-TMS
• mu-rhythm phase
• corticospinal excitability
• individualized neuromodulation