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

S Mathieson,E Low,J Rennie,V Livingstone,G.B Boylan,A Temko,R.M Pressler

doi:10.1016/j.clinph.2016.01.026

Abstract

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. 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. 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. This rigorous analysis allows estimation of how key seizure features are exploited by SDAs. This study resulted in a beta version of ANSeR with significantly improved performance.

Highlights

Full term neonates with neurological conditions such as hypoxic-ischaemic encephalopathy (HIE), stroke and meningitis are at high risk of developing seizures
The seizure detection/false detection rates for the seizure detection algorithm (SDA) for seizure neonates are given in Supplementary Table S1a and the false detection rates for nonseizure neonates are given in Supplementary Table S1b
The multivariate analysis in this study has shown that only four seizure features were consistent predictors of automated seizure detection across all three ANSeR sensitivity thresholds tested including: signal amplitude, the apparent rhythmicity of seizures from second to second, seizure duration, and the number of EEG channels involved in the seizure at the peak of seizure

Summary

Introduction

Full term neonates with neurological conditions such as hypoxic-ischaemic encephalopathy (HIE), stroke and meningitis are at high risk of developing seizures. Amplitudeintegrated EEG (aEEG) is used in many neonatal intensive care units (NICUs), comparison of seizure detection using EEG and aEEG has shown that many seizures seen on EEG are missed using aEEG alone (Rennie et al, 2004; Bourez-Swart et al, 2009). Seizure morphology at peak of seizure Seizure duration. Frequency variability Quantitative (over whole seizure) Spatial context. Seizure morphology change from onset to peak.

Methods

Results

Conclusion