Automated classification of neonatal sleep states using EEG

Ninah Koolen; Lisa Oberdorfer; Zsofia Rona; Vito Giordano; Tobias Werther; Katrin Klebermass-Schrehof; Nathan Stevenson; Sampsa Vanhatalo

doi:10.1016/j.clinph.2017.02.025

Automated classification of neonatal sleep states using EEG

Clin Neurophysiol. 2017 Jun;128(6):1100-1108. doi: 10.1016/j.clinph.2017.02.025. Epub 2017 Mar 15.

Authors

Ninah Koolen¹, Lisa Oberdorfer², Zsofia Rona², Vito Giordano², Tobias Werther², Katrin Klebermass-Schrehof², Nathan Stevenson¹, Sampsa Vanhatalo³

Affiliations

¹ BABA Center, Department of Children's Clinical Neurophysiology, Children's Hospital, HUS Medical Imaging Center, Helsinki University Central Hospital and University of Helsinki, Finland.
² Medical University Vienna, Department of Pediatrics, Division of Neonatology, Pediatric Intensive Care and Neuropediatrics, Vienna, Austria.
³ BABA Center, Department of Children's Clinical Neurophysiology, Children's Hospital, HUS Medical Imaging Center, Helsinki University Central Hospital and University of Helsinki, Finland. Electronic address: sampsa.vanhatalo@helsinki.fi.

PMID: 28359652
DOI: 10.1016/j.clinph.2017.02.025

Abstract

Objective: To develop a method for automated neonatal sleep state classification based on EEG that can be applied over a wide range of age.

Methods: We collected 231 EEG recordings from 67 infants between 24 and 45weeks of postmenstrual age. Ten minute epochs of 8 channel polysomnography (N=323) from active and quiet sleep were used as a training dataset. We extracted a set of 57 EEG features from the time, frequency, and spatial domains. A greedy algorithm was used to define a reduced feature set to be used in a support vector machine classifier.

Results: Performance tests showed that our algorithm was able to classify quiet and active sleep epochs with 85% accuracy, 83% sensitivity, and 87% specificity. The performance was not substantially lowered by reducing the epoch length or EEG channel number. The classifier output was used to construct a novel trend, the sleep state probability index, that improves the visualisation of brain state fluctuations.

Conclusions: A robust EEG-based sleep state classifier was developed. It performs consistently well across a large span of postmenstrual ages.

Significance: This method enables the visualisation of sleep state in preterm infants which can assist clinical management in the neonatal intensive care unit.

Keywords: Brain monitoring; Classification; Neonatal EEG; Sleep-wake cycling; Support vector machine.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Child Development / classification*
Electroencephalography / methods*
Electroencephalography / standards
Humans
Infant, Newborn
Infant, Premature / growth & development
Infant, Premature / physiology*
Infant, Premature, Diseases / diagnosis*
Sleep*
Support Vector Machine