Quantitative Preterm EEG Analysis: The Need for Caution in Using Modern Data Science Techniques.

John M O'Toole,Geraldine B Boylan

doi:10.3389/fped.2019.00174

Abstract

Hemodynamic changes during neonatal transition increase the vulnerability of the preterm brain to injury. Real-time monitoring of brain function during this period would help identify the immediate impact of these changes on the brain. Neonatal EEG provides detailed real-time information about newborn brain function but can be difficult to interpret for non-experts; preterm neonatal EEG poses even greater challenges. An objective quantitative measure of preterm brain health would be invaluable during neonatal transition to help guide supportive care and ultimately protect the brain. Appropriate quantitative measures of preterm EEG must be calculated and care needs to be taken when applying the many techniques available for this task in the era of modern data science. This review provides valuable information about the factors that influence quantitative EEG analysis and describes the common pitfalls. Careful feature selection is required and attention must be paid to behavioral state given the variations encountered in newborn EEG during different states. Finally, the detrimental influence of artifacts on quantitative EEG analysis is illustrated.

Highlights

Postnatal adaption presents many challenges for the preterm infant, with hemodynamic changes increasing the risk of brain injury
The aim of this paper is to provide an overview of quantitative measures for the analysis of neonatal EEG that can be used to assess neonatal brain function during transition and to highlight the challenges that can be encountered from both a neurophysiological and signal processing perspective
To highlight the seriousness of these points, we present 3 Quantitative EEG (qEEG) examples generated from different cohorts of newborn EEG

Summary

INTRODUCTION

Postnatal adaption presents many challenges for the preterm infant, with hemodynamic changes increasing the risk of brain injury. AEEG was developed in the 1960s for monitoring comatose adults in intensive care and was never intended for monitoring the neonatal brain It was launched into a technology vacuum and adopted rapidly by NICUs for use in full-term infants in the late 1980s because there was nothing else available to provide the much-needed insight into newborn brain function. The aEEG is essentially just one way to represent the EEG quantitatively and has been used extensively in preterm infants (including during the transitional period) and scores of aEEG maturation have been devised This has happened gradually without any thorough evaluation of the aEEG as an appropriate tool for the assessment of preterm brain function. The measures derived from the EEG using quantitative methods are only of use if there is careful data preparation and management prior to analysis but these steps are easy to overlook in the current era of powerful data science techniques

QUANTITATIVE EEG ANALYSIS

EXAMPLE 1

EXAMPLE 2

EXAMPLE 3

Findings

DISCUSSION