Neonatal seizures require urgent treatment but can go undetected without expert EEG monitoring. We develop and validate a seizure-detection model using retrospective EEG data from 332 neonates. A convolutional neural network was developed on over 50k hours (n=202) of annotated single-channel EEG containing 12k seizure events. This model was validated on two independent multi-reviewer datasets (n=51 and n=79).
Increasing data and model size improves performance: Matthews correlation coefficient (MCC) and Pearson's correlation (r) increased by up to 50% (15%) with data (model) scaling. The largest model (21m parameters) achieves state-of-the-art on an open-access dataset (MCC=0.764, r=0.824, and AUC=0.982). This model also attains expert-level performance on both validation sets, a first in this field, with no significant difference in inter-rater agreement when the model replaces an expert (Δκ < -0.095, p>0.05).