Prospective Study of a Multimodal Convulsive Seizure Detection Wearable System on Pediatric and Adult Patients in the Epilepsy Monitoring Unit.

Francesco Onorati,Jonathan Bidwell,Giulia Regalia,Rosalind Picard,Chiara Caborni,Rani A Sarkis,W Curt Lafrance,Rima El Atrache,Fatemeh Mohammadpour-Touserkani,Daniel Friedman,Tobias Loddenkemper,Andrew S Blum,Paola De Liso,Jay Jeschke

doi:10.3389/fneur.2021.724904

Abstract

Background: Using machine learning to combine wrist accelerometer (ACM) and electrodermal activity (EDA) has been shown effective to detect primarily and secondarily generalized tonic-clonic seizures, here termed as convulsive seizures (CS). A prospective study was conducted for the FDA clearance of an ACM and EDA-based CS-detection device based on a predefined machine learning algorithm. Here we present its performance on pediatric and adult patients in epilepsy monitoring units (EMUs).Methods: Patients diagnosed with epilepsy participated in a prospective multi-center clinical study. Three board-certified neurologists independently labeled CS from video-EEG. The Detection Algorithm was evaluated in terms of Sensitivity and false alarm rate per 24 h-worn (FAR) on all the data and on only periods of rest. Performance were analyzed also applying the Detection Algorithm offline, with a less sensitive but more specific parameters configuration (“Active mode”).Results: Data from 152 patients (429 days) were used for performance evaluation (85 pediatric aged 6–20 years, and 67 adult aged 21–63 years). Thirty-six patients (18 pediatric) experienced a total of 66 CS (35 pediatric). The Sensitivity (corrected for clustered data) was 0.92, with a 95% confidence interval (CI) of [0.85-1.00] for the pediatric population, not significantly different (p > 0.05) from the adult population's Sensitivity (0.94, CI: [0.89–1.00]). The FAR on the pediatric population was 1.26 (CI: [0.87–1.73]), higher (p < 0.001) than in the adult population (0.57, CI: [0.36–0.81]). Using the Active mode, the FAR decreased by 68% while reducing Sensitivity to 0.95 across the population. During rest periods, the FAR's were 0 for all patients, lower than during activity periods (p < 0.001).Conclusions: Performance complies with FDA's requirements of a lower bound of CI for Sensitivity higher than 0.7 and of a FAR lower than 2, for both age groups. The pediatric FAR was higher than the adult FAR, likely due to higher pediatric activity. The high Sensitivity and precision (having no false alarms) during sleep might help mitigate SUDEP risk by summoning caregiver intervention. The Active mode may be advantageous for some patients, reducing the impact of the FAR on daily life. Future work will examine the performance and usability outside of EMUs.

Highlights

Generalized tonic-clonic seizures and focal-to-bilateral tonicclonic seizures are the most dangerous types of seizures and represent major risk factors for sudden unexpected death in epilepsy (SUDEP), especially when patients are left unattended, e.g., nighttime [1,2,3,4]
We evaluate the detection of two seizure types, i.e., “focal onset to bilateral/unilateral tonic-clonic” (FBTC) seizures, previously known as secondary generalized tonicclonic seizure, and “generalized onset tonic-clonic” (GTC) seizures, previously defined as primary generalized tonic-clonic seizures
This is a prospective, non-randomized multi-site Epilepsy Monitoring Unit (EMU) clinical trial undertaken to get the clearance by the US Food and Drug Administration (FDA) of an investigational monitoring and alerting system for the identification of specific types of seizures (i.e., convulsive seizures (CS)) using a device worn on the wrist

Summary

Introduction

Generalized tonic-clonic seizures and focal-to-bilateral tonicclonic seizures are the most dangerous types of seizures and represent major risk factors for sudden unexpected death in epilepsy (SUDEP), especially when patients are left unattended, e.g., nighttime [1,2,3,4]. Wearable devices equipped with automated seizure detection algorithms have been suggested to complement and overcome limitations of the gold standard video-electroencephalography (v-EEG) performed in the Epilepsy Monitoring Unit (EMU) [8,9,10,11,12]. Such devices target a continuous, remote, unobtrusive and less expensive monitoring of patients. We present its performance on pediatric and adult patients in epilepsy monitoring units (EMUs)

Methods

Results

Discussion

Conclusion