Search

Neonatal brain monitoring in the neonatal intensive care units (NICU) requires a continuous review of the spontaneous cortical activity, i.e., the electroencephalograph (EEG) background activity. This needs development of bedside methods for an automated assessment of the EEG background activity. In this paper, we present development of the key components of a neonatal EEG background classifier, starting from the visual background scoring to classifier design, and finally to possible bedside visualization of the classifier results. A dataset with 13,200 5-minute EEG epochs (8-- 16 channels) from 27 infants with birth asphyxia was used for classifier training after scoring by two independent experts. We tested three classifier designs based on 98 computational features, and their performance was assessed with respect to scoring system, pre- and post-processing of labels and outputs, choice of channels, and visualization in monitor displays. The optimal solution achieved an overall classification accuracy of 97% with a range across subjects of 81--100%. We identified a set of 23 features that make the classifier highly robust to the choice of channels and missing data due to artefact rejection. Our results showed that an automated bedside classifier of EEG background is achievable, and we publish the full classifier algorithm to allow further clinical replication and validation studies. [ABSTRACT FROM AUTHOR]

Background: Infantile epileptic spasm syndrome (IESS) is an age-dependent epileptic encephalopathy with a significant risk of developmental regression. This study investigates the association between heart rate variability (HRV) in infants at risk of IESS and the clinical onset of IESS. Methods: Sixty neonates at risk of IESS were prospectively followed from birth to 12 months with simultaneous electroencephalogram (EEG) and electrocardiogram recordings for 60min at every 2-month interval. HRV metrics were calculated from 5min time-epoch during sleep including frequency domain measures, Poincare analysis including cardiac vagal index (CVI) and cardiac sympathetic index (CSI), and detrended fluctuation analysis (DFA a1, DFA a2). To assess the effect of each HRV metric at the 2-month baseline on the time until the first occurrence of either hypsarrhythmia on EEG and/or clinical spasm, univariate cox-proportional hazard models were fitted for each HRV metric. Results: Infantile epileptic spasm syndrome was diagnosed in 20/60 (33%) of the cohort in a 12-month follow-up and 3 (5%) were lost to follow-up. The median age of developing hypsarrhythmia was 25 (7-53) weeks and clinical spasms at 24 (8-40) weeks. Three (5%) patients had clinical spasms without hypsarrhythmia, and 5 (8%) patients had hypsarrhythmia before clinical spasms at the initial presentation. The infants with high CSI (hazard ratio 2.5, 95% CI 1.2-5.2, P = 0.01) and high DFA α1 (hazard ratio 16, 95% CI 1.1-240, P = 0.04) at 2 months were more likely to develop hypsarrhythmia by the first year of age. There was a trend toward decreasing CSI and DFA a1 and increasing CVI in the first 8 months of age. Conclusion: Our data suggest that relative sympathetic predominance at an early age of 2monthsmay be a potential predictor for developing IESS. Hence, early HRV patterns may provide valuable prognostic information in children at risk of IESS allowing early detection and optimization of cognitive outcomes. Whether early intervention to restore sympathovagal balance per se would provide clinical benefit must be addressed by future studies. [ABSTRACT FROM AUTHOR]

This document is a corrigendum for an article titled "Building an open source classifier for the neonatal EEG background: a systematic feature-based approach from expert scoring to clinical visualization." The corrigendum corrects an error in the spelling of one of the author's names, changing "Saeed Montazeri Moghadam" to "Saeed Montazeri." The authors apologize for the error and state that it does not affect the scientific conclusions of the article. The corrigendum also includes copyright information and a note from the publisher stating that the views expressed in the article are solely those of the authors. [Extracted from the article]