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

2025-05-04

AI Summary

Current closed-loop neuromodulation for drug-resistant epilepsy (DRE) suffers from two key limitations: intervention occurs only post-ictally, and stimulation parameters require labor-intensive manual tuning. To address these, this study proposes a prediction-driven, preventive closed-loop neuromodulation paradigm. We introduce reservoir-based neuromorphic computing for real-time seizure forecasting, enabling personalized, transient electrical stimulation triggered exclusively upon predicted imminent seizure onset—thereby shifting from reactive to truly predictive, adaptive control and eliminating fixed-frequency stimulation. The integrated system comprises a 3D microelectrode array, brain-inspired hardware acceleration, and an ex vivo hippocampal organoid model. In organoid experiments, the approach achieves >97% suppression of epileptiform activity using a primary stimulation frequency <20 Hz—substantially lower than clinical standards—demonstrating both high efficacy and potential for reduced off-target effects.

Technology Category

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

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

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 system capable of driving personalized free-run stimulations based on seizure forecasting, wherein each forecast triggers an electrical pulse rather than an arbitrarily predefined fixed-frequency stimulus train. We validate the system against hippocampal spheroids coupled to 3D microelectrode array as a simplified testbed, showing that it can achieve seizure reduction>97% while primarily using instantaneous stimulation frequencies within 20 Hz, well below what typically used in clinical settings. Our work demonstrates the potential of neuromorphic systems as a next-generation neuromodulation strategy for personalized DRE treatment.

Problem

• Developing real-time seizure forecasting for closed-loop control
• Personalizing brain stimulation to prevent rather than abort seizures
• Reducing trial-and-error in stimulation parameter tuning for epilepsy

Innovation

• Real-time seizure forecasting via neuromorphic computing
• Personalized free-run stimulation triggered by forecasts
• Low-frequency stimulation achieving high seizure reduction