Quorum
Low-Latency Seizure Onset Detection from We…
Research report View only
March 14, 2026

Low-Latency Seizure Onset Detection from Wearable EEG

Wearable EEG classifiers now detect seizure onset within a few seconds of true onset while holding false-alarm rates low enough for at-home use, though performance drops sharply outside the cohort a model was trained on.

Abstract

Compact convolutional–recurrent models detect onset with sensitivity in the low nineties at latencies under six seconds. For example, a depthwise CNN with a two-layer GRU head reaches 93.4% sensitivity at 4.7 s median latency on a single-centre cohort, while a temporal-convolution ensemble reports 91.6–94.2% across focal and generalised events. Eight of eleven studies that reported alarm burden stayed under 0.6 false alarms per hour, with one behavioural-artefact-heavy deployment reporting 2.3 and another a 21% reduction over its own prior baseline. Across the seven studies reporting on-device inference, all ran within the power envelope of a wrist-worn unit. A range of architectures — dilated temporal convolutions, bidirectional recurrent stacks, attention pooling, and small transformer encoders — support onset detection under everyday motion and variable electrode contact.

Methods

We reviewed 11 papers drawn from an initial pool of 63, applying 6 screening criteria. Each paper was assessed on 5 dimensions selected for their bearing on the research question. More on methods

Results

Characteristics of Included Studies

Study
Model Family
Onset Criterion
Cohort Type
Marsden et al., 2023
Depthwise CNN + GRU
Expert-annotated onset
Single centre, 42 adults
Okonjo & Reiss, 2024
Dilated temporal conv.
Consensus of two readers
Multi-site, 118 adults