Adaptive modelling of background EEG for robust detection of neonatal seizures

Adaptive probabilistic modelling of the EEG background is proposed for seizure detection in neonates with hypoxic ischemic encephalopathy. The decision is made based on temporal derivative of the seizure probability with respect to the adaptively modeled level of background activity. The robustness of the system to long duration, seizure-like artifacts (in particular those due to respiration) is improved. The results are validated on the largest available clinical dataset, comprising 816.7 hours. By exploiting the proposed adaptation, the ROC area is significantly increased for patients with EEG corrupted with respiration artifact, with the average increase of 20% (relative) across all patients.