Conference Publication Details
Mandatory Fields
Temko, A., Marnane, W., Boylan, G. and Lightbody, G
IEEE EMBS Biannual International Conference on Biomedical Engineering & Science, IECBES 2012
Adaptive Modelling of Background EEG for Robust Detection of Neonatal Seizures
2012
December
Published
1
()
Optional Fields
Neonatal, Seizure, Background, EEG
46
51
Langkawi, Malaysia
17-DEC-12
19-DEC-12
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 modelled level of background activity. The robustness of the system to long duration, seizure-like artefacts (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 artefact, with the average increase of 20% (relative) across all patients.
10.1109/IECBES.2012.6498109
Grant Details
Science Foundation Ireland
10/IN.1/B3036