Format

Send to

Choose Destination
Clin Neurophysiol. 2016 May;127(5):2246-56. doi: 10.1016/j.clinph.2016.01.026. Epub 2016 Feb 21.

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

Author information

1
Academic Research Department of Neonatology, Institute for Women's Health, University College London, London, United Kingdom; Neonatal Brain Research Group, Irish Centre for Fetal and Neonatal Translational Research, Department of Paediatrics and Child Health, University College Cork, Ireland. Electronic address: sean.mathieson@uclh.nhs.uk.
2
Academic Research Department of Neonatology, Institute for Women's Health, University College London, London, United Kingdom; Neonatal Brain Research Group, Irish Centre for Fetal and Neonatal Translational Research, Department of Paediatrics and Child Health, University College Cork, Ireland.
3
Neonatal Brain Research Group, Irish Centre for Fetal and Neonatal Translational Research, Department of Paediatrics and Child Health, University College Cork, Ireland.
4
Neonatal Brain Research Group, Irish Centre for Fetal and Neonatal Translational Research, Department of Paediatrics and Child Health, University College Cork, Ireland; Department of Electrical and Electronic Engineering, University College Cork, Ireland.
5
Department of Clinical Neurophysiology, Great Ormond Street Hospital, London, United Kingdom.

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.

KEYWORDS:

Automated seizure detection; Neonatal seizures

PMID:
27072097
PMCID:
PMC4840013
DOI:
10.1016/j.clinph.2016.01.026
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Elsevier Science Icon for PubMed Central
Loading ...
Support Center