Time-Varying EEG Correlations Improve Automated Neonatal Seizure Detection

No Thumbnail Available

Access rights

openAccess

URL

Journal Title

Journal ISSN

Volume Title

A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Date

2019-05-01

Major/Subject

Mcode

Degree programme

Language

en

Pages

15

Series

International Journal of Neural Systems, Volume 29, issue 4

Abstract

The aim of this study was to develop methods for detecting the nonstationary periodic characteristics of neonatal electroencephalographic (EEG) seizures by adapting estimates of the correlation both in the time (spike correlation; SC) and time-frequency domain (time-frequency correlation; TFC). These measures were incorporated into a seizure detection algorithm (SDA) based on a support vector machine to detect periods of seizure and nonseizure. The performance of these nonstationary correlation measures was evaluated using EEG recordings from 79 term neonates annotated by three human experts. The proposed measures were highly discriminative for seizure detection (median AUCSC: 0.933 IQR: 0.821-0.975, median AUCTFC: 0.883 IQR: 0.707-0.931). The resultant SDA applied to multi-channel recordings had a median AUC of 0.988 (IQR: 0.931-0.998) when compared to consensus annotations, outperformed two state-of-the-art SDAs (p < 0.001) and was noninferior to the human expert for 73/79 of neonates.

Description

| openaire: EC/H2020/656131/EU//APE

Keywords

Electroencephalography, neonatal seizure detection, nonstationary signal processing, support vector machines, time-frequency distributions

Other note

Citation

Tapani, K T, Vanhatalo, S & Stevenson, N J 2019, ' Time-Varying EEG Correlations Improve Automated Neonatal Seizure Detection ', International Journal of Neural Systems, vol. 29, no. 4, 1850030 . https://doi.org/10.1142/S0129065718500302