Demo: Multi-Modal Seizure Prediction System

TL;DR

SeizNet is a multi-modal, deep learning-based system for real-time epileptic seizure prediction using invasive and non-invasive sensors, achieving over 97% accuracy suitable for implantable devices.

Contribution

Introduces SeizNet, a novel multi-modal sensor system with optimized deep learning algorithms for accurate, real-time seizure prediction on edge devices.

Findings

Achieves >97% prediction accuracy

Utilizes multi-modal data from EEG, iEEG, and ECG

Operates within size and energy constraints of implantable devices

Abstract

This demo presents SeizNet, an innovative system for predicting epileptic seizures benefiting from a multi-modal sensor network and utilizing Deep Learning (DL) techniques. Epilepsy affects approximately 65 million people worldwide, many of whom experience drug-resistant seizures. SeizNet aims at providing highly accurate alerts, allowing individuals to take preventive measures without being disturbed by false alarms. SeizNet uses a combination of data collected through either invasive (intracranial electroencephalogram (iEEG)) or non-invasive (electroencephalogram (EEG) and electrocardiogram (ECG)) sensors, and processed by advanced DL algorithms that are optimized for real-time inference at the edge, ensuring privacy and minimizing data transmission. SeizNet achieves > 97% accuracy in seizure prediction while keeping the size and energy restrictions of an implantable device.