Closed-loop control of seizure activity via real-time seizure forecasting by reservoir neuromorphic computing

TL;DR

This paper introduces a neuromorphic reservoir computing system for real-time seizure forecasting and personalized brain stimulation, significantly improving epilepsy treatment by reducing seizures with adaptive, low-frequency stimulation.

Contribution

The study presents a novel neuromorphic hardware system capable of real-time seizure prediction and personalized stimulation, addressing limitations of current methods.

Findings

Achieved 83.33% accuracy in seizure forecasting.

Reduced seizures by over 97% in a testbed.

Used low-frequency stimulation within 20 Hz.

Abstract

Closed-loop brain stimulation holds potential as personalized treatment for drug-resistant epilepsy (DRE) but still suffers from limitations that result in highly variable efficacy. First, stimulation is typically delivered upon detection of the seizure to abort rather than prevent it; second, the stimulation parameters are established by trial and error, requiring lengthy rounds of fine-tuning, which delay steady-state therapeutic efficacy. Here, we address these limitations by leveraging the potential of neuromorphic computing. We present a neuromorphic reservoir computing hardware system capable of driving real-time personalized free-run stimulations based on seizure forecasting, wherein each forecast triggers an electrical pulse rather than an arbitrarily predefined fixed-frequency stimulus train. The system achieves 83.33% accuracy in forecasting seizure occurrences during the training phase. We validate the system using hippocampal spheroids coupled to 3D microelectrode array as a simplified testbed, achieving seizure reduction >97% during the real-time processing while primarily using instantaneous stimulation frequencies within 20 Hz, well below what typically used in clinical practice. Our work demonstrates the potential of neuromorphic systems as a next-generation neuromodulation strategy for personalized DRE treatment, leveraging their sparse and event-driven processing for real-time applications.