Epilepsy can be treated with medication, however, 30% of epileptic patients are still drug resistive. Devices like responsive neurostimluation systems are implanted in select patients who may not be amenable to surgical resection. However, state-of-the-art devices suffer from low accuracy and high sensitivity. We propose a novel patient-specific seizure detection system based on na\"ive Bayesian inference using M\"uller C-elements. The system improves upon the current leading neurostimulation device, NeuroPace's RNS by implementing analog signal processing for feature extraction, minimizing the power consumption compared to the digital counterpart. Preliminary simulations were performed in MATLAB, demonstrating that through integrating multiple channels and features, up to 98% detection accuracy for individual patients can be achieved. Similarly, power calculations were performed, demonstrating that the system uses 6.5μW per channel, which when compared to the state-of-the-art NeuroPace system would increase battery life by up to 50%.
@article{arxiv.2106.06590,
title = {Analog Seizure Detection for Implanted Responsive Neurostimulation},
author = {Abbas A. Zaki and Noah C. Parker and Tae-Yoon Kim and Sam Ishak and Ty E. Stovall and Genchang Peng and Hina Dave and Jay Harvey and Mehrdad Nourani and Xuan Hu and Alexander J. Edwards and Joseph S. Friedman},
journal= {arXiv preprint arXiv:2106.06590},
year = {2021}
}