May 12, 2022

Automated Seizure Detection with Non-Invasive Wearable Devices: A Systematic Review and Meta-Analysis

Abstract found in Wiley Online Library


Objective: To review the reported performance of non-invasive wearable devices in detecting epileptic seizures and psychogenic non-epileptic seizures (PNES).

Methods: We conducted a systematic review and meta-analysis of studies reported up to November 15, 2021. We included studies that used video-EEG monitoring as the gold standard to determine the sensitivity and false alarm rate (FAR) of non-invasive wearables for automated seizure detection.

Results: Twenty-eight studies met the criteria for the systematic review, of which 23 were eligible for meta-analysis. These studies (1269 patients in total; median recording time 52.9 hours per patient) investigated devices for tonic-clonic seizures using wrist worn and/or ankle worn devices to measure 3D accelerometry (15 studies), and/or wearable surface devices to measure electromyography (eight studies). The mean sensitivity for detecting tonic-clonic seizures was 0.91 (95% confidence interval, 0.85-0.96; I2 =83.8%); sensitivity was similar between the wrist worn (0.93) and surface devices (0.90). The overall FAR was 2.1/24 hours (95% CI, 1.7–2.6; I2 =99.7%); FAR was higher in wrist worn (2.5/24 hours) than in wearable surface devices (0.96/24 hours). Three of the 23 studies also detected PNES; the mean sensitivity and FAR from these studies were 62.9% and 0.79/24 hours, respectively. Four studies detected both focal and tonic clonic seizures and one study detected focal seizures only; the sensitivities ranged from 31.1% to 93.1% in these studies.

Significance: Reported non-invasive wearable devices had high sensitivity but relatively high false alarm rate in detecting tonic-clonic seizures during limited recording time in a video-EEG setting. Future studies should focus on reducing false alarm rate, detection of other seizure types and PNES, and longer recording in the community.