Computationally efficient neural network classifiers for next generation closed loop neuromodulation therapy - a case study in epilepsy

Abstract

This work explores the potential utility of neural network classifiers for real-time classification of field-potential based biomarkers in next-generation responsive neuromodulation systems. Compared to classical filter-based classifiers, neural networks offer an ease of patient-specific parameter tuning, promising to reduce the burden of programming on clinicians. The paper explores a compact, feed-forward neural network architecture of only dozens of units for seizure-state classification in refractory epilepsy. The proposed classifier offers comparable accuracy to filterclassifiers on clinician-labeled data, while reducing detection latency. As a trade-off to classical methods, the paper focuses on keeping the complexity of the architecture minimal, to accommodate the on-board computational constraints of implantable pulse generator systems.Clinical relevance-A neural network-based classifier is presented for responsive neurostimulation, with comparable accuracy to classical methods at reduced latency.

An embedded intracranial seizure monitor for objective outcome measurements and rhythm identification

“…There is a clear need to embed seizure detection capabilities into next-generation DBS devices for the treatment of patients with epilepsy. Recorded signal features such as line-length or spectral power can be utilized to train DBS device-embedded classifiers for the online detection of seizure events as a surrogate to patient-reported seizure diaries [6], [7], [8]. At present, however, there are several technical issues that may hamper the implementation of these devices as reliable seizure monitors.…”