Optimization of an NLEO-based algorithm for automated detection of spontaneous activity transients in early preterm EEG

We propose here a simple algorithm for automated detection of spontaneous activity transients (SATs) in early preterm electroencephalography (EEG). The parameters of the algorithm were optimized by supervised learning using a gold standard created from visual classification data obtained from three human raters. The generalization performance of the algorithm was estimated by leave-one-out cross-validation. The mean sensitivity of the optimized algorithm was 97% (range 91-100%) and specificity 95% (76-100%). The optimized algorithm makes it possible to systematically study brain state fluctuations of preterm infants.

[1]  Sampsa Vanhatalo,et al.  Slow endogenous activity transients and developmental expression of K+–Cl− cotransporter 2 in the immature human cortex , 2005, The European journal of neuroscience.

[2]  J. Fleiss Measuring nominal scale agreement among many raters. , 1971 .

[3]  D. Azzopardi,et al.  Artifacts on Electroencephalograms May Influence the Amplitude-Integrated EEG Classification: A Qualitative Analysis in Neonatal Encephalopathy , 2006, Pediatrics.

[4]  D Samson-Dollfus,et al.  [Electroencephalography of the premature and term newborn. Maturational aspects and glossary]. , 1999, Neurophysiologie clinique = Clinical neurophysiology.

[5]  Heiko J. Luhmann,et al.  Early patterns of electrical activity in the developing cerebral cortex of humans and rodents , 2006, Trends in Neurosciences.

[6]  K. Kaila,et al.  Generation of ‘positive slow waves’ in the preterm EEG: By the brain or by the EEG setup? , 2008, Clinical Neurophysiology.

[7]  J. F. Kaiser,et al.  On a simple algorithm to calculate the 'energy' of a signal , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[8]  Timo Saarela,et al.  No Improvement in Outcome of Nationwide Extremely Low Birth Weight Infant Populations Between 1996–1997 and 1999–2000 , 2007, Pediatrics.

[9]  N. Marlow,et al.  Neurologic and developmental disability at six years of age after extremely preterm birth. , 2005, The New England journal of medicine.

[10]  M. Toet,et al.  Brain monitoring in neonates. , 2009, Early human development.

[11]  D. Samson-Dollfus,et al.  Électroencéphalographie du nouveau-né prématuré et à terme. Aspects maturatifs et glossaire , 1999, Neurophysiologie Clinique/Clinical Neurophysiology.

[12]  Sampsa Vanhatalo,et al.  Detection of ‘EEG bursts’ in the early preterm EEG: Visual vs. automated detection , 2010, Clinical Neurophysiology.

[13]  J. Perlman,et al.  Amplitude-Integrated Electroencephalography in the NICU: Frequent Artifacts in Premature Infants May Limit Its Utility as a Monitoring Device , 2009, Pediatrics.

[14]  David Ley,et al.  Early amplitude‐integrated EEG correlates with cord TNF‐α and brain injury in very preterm infants , 2008, Acta paediatrica.

[15]  Hiroyuki Kidokoro,et al.  Chronologic Changes in Neonatal EEG Findings in Periventricular Leukomalacia , 2009, Pediatrics.

[16]  Mark Quigg,et al.  Engineering Aspects of the Quantified Amplitude-Integrated Electroencephalogram in Neonatal Cerebral Monitoring , 2009, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[17]  P. VandenBerg,et al.  Neurologic and Developmental Disability at Six Years of Age After Extremely Preterm Birth , 2005 .

[18]  K. Kaila,et al.  Development of neonatal EEG activity: from phenomenology to physiology. , 2006, Seminars in fetal & neonatal medicine.

[19]  J Gotman,et al.  Automatic EEG analysis during long-term monitoring in the ICU. , 1998, Electroencephalography and clinical neurophysiology.

[20]  Tapio Seppänen,et al.  Automatic Analysis and Monitoring of Burst Suppression in Anesthesia , 2002, Journal of Clinical Monitoring and Computing.

[21]  S. Mukhopadhyay,et al.  A new interpretation of nonlinear energy operator and its efficacy in spike detection , 1998, IEEE Transactions on Biomedical Engineering.