RAMSES: A full-stack application for detecting seizures and reducing data during continuous EEG monitoring
Abstract
Objective: Continuous EEG (cEEG) monitoring is associated with lower mortality in critically ill patients, however it is underutilized due to the difficulty of manually interpreting prolonged streams of cEEG data. Here we present a novel real-time, machine learning-based alerting and monitoring system for epilepsy and seizures (RAMSES) that dramatically reduces the amount of manual EEG review. Methods: We developed a custom data reduction algorithm using a random forest, and deployed it within an online cloud-based platform which streams data and communicates interactively with caregivers via a web interface to display algorithm results. We validate RAMSES on cEEG recordings from 77 patients undergoing routine scalp ICU EEG monitoring. Results: On subjects with seizures we achieved >80% overall data reduction, while detecting a mean of 84% of seizures across all validation patients, with 19/27 patients achieving 100% seizure detection. On seizure free-patients, the majority of cEEG records, we reduced data requiring manual review by >83%. Conclusion: This study validates a platform for machine-learning assisted data reduction. Significance: This work represents a meaningful step towards improving utility and decreasing cost for cEEG monitoring We also make our high-quality annotated dataset of 77 ICU cEEG recordings public for others to validate and improve upon our methods.
Keywords
Cite
@article{arxiv.2009.01920,
title = {RAMSES: A full-stack application for detecting seizures and reducing data during continuous EEG monitoring},
author = {John M. Bernabei and Olaoluwa Owoputi and Shyon D. Small and Nathaniel T. Nyema and Elom Dumenyo and Joongwon Kim and Steven N. Baldassano and Christopher Painter and Erin C. Conrad and Taneeta M. Ganguly and Ramani Balu and Kathryn A. Davis and Jay Pathmanathan and Brian Litt},
journal= {arXiv preprint arXiv:2009.01920},
year = {2020}
}