In-depth performance analysis of an EEG based neonatal seizure detection algorithm

Loading...
Thumbnail Image
Files
1-s2.0-S1388245716000705-main.pdf(3.06 MB)
Published version
1-s2.0-S1388245716000705-mmc2.docx(13.52 KB)
Supplementary file 1
1-s2.0-S1388245716000705-mmc1.docx(16.24 KB)
Supplementary file 2
Date
2016-02-21
Authors
Mathieson, Sean
Rennie, Janet
Livingstone, Vicki
Temko, Andriy
Low, Evonne
Pressler, R. M.
Boylan, Geraldine B.
Journal Title
Journal ISSN
Volume Title
Publisher
Elsevier
Research Projects
Organizational Units
Journal Issue
Abstract
Objective: To describe a novel neurophysiology based performance analysis of automated seizure detection algorithms for neonatal EEG to characterize features of detected and non-detected seizures and causes of false detections to identify areas for algorithmic improvement. Methods: EEGs of 20 term neonates were recorded (10 seizure, 10 non-seizure). Seizures were annotated by an expert and characterized using a novel set of 10 criteria. ANSeR seizure detection algorithm (SDA) seizure annotations were compared to the expert to derive detected and non-detected seizures at three SDA sensitivity thresholds. Differences in seizure characteristics between groups were compared using univariate and multivariate analysis. False detections were characterized. Results: The expert detected 421 seizures. The SDA at thresholds 0.4, 0.5, 0.6 detected 60%, 54% and 45% of seizures. At all thresholds, multivariate analyses demonstrated that the odds of detecting seizure increased with 4 criteria: seizure amplitude, duration, rhythmicity and number of EEG channels involved at seizure peak. Major causes of false detections included respiration and sweat artefacts or a highly rhythmic background, often during intermediate sleep. Conclusion: This rigorous analysis allows estimation of how key seizure features are exploited by SDAs. Significance: This study resulted in a beta version of ANSeR with significantly improved performance.
Description
Keywords
Automated seizure detection , Neonatal seizures , Detection algorithm
Citation
Mathieson, S., Rennie, J., Livingstone, V., Temko, A., Low, E., Pressler, R. M. and Boylan, G. B. (2016), 'In-depth performance analysis of an EEG based neonatal seizure detection algorithm', Clinical Neurophysiology, 127(5), pp. 2246-2256. DOI: 10.1016/j.clinph.2016.01.026