Machine-learning-based diagnostics of EEG pathology.

Machine learning (ML) methods have the potential to automate clinical EEG analysis. They can be categorized into feature-based (with handcrafted features), and end-to-end approaches (with learned features). Previous studies on EEG pathology decoding have typically analyzed a limited number of features, decoders, or both.

Delayed neonatal visual evoked potentials are associated to asymmetric growth pattern in twins.

Objectives: To study the association between intrauterine growth and visual pathways maturation by neonatal visual evoked potentials (VEPs) in twins, in view of a possible prognostic role.

Methods: Seventy-four twin neonates from 37 pregnancies were selected based on gestational age of more than 30 weeks and uneventful perinatal clinical course. Flash VEPs were recorded at the same postmenstrual age in each twin pair.

Incorporating feature selection methods into a machine learning-based neonatal seizure diagnosis.

The present study developed a feature selection (FS)-based decision support system using the electroencephalography (EEG) signals recorded from neonates with and without seizures. The study employed 10 different FS algorithms to reduce the classification cost by using fewer features and to improve the classification performance of the model by removing the irrelevant features. In doing so, the classification performance of each FS algorithm on each EEG channel difference was also evaluated.

Large-scale brain modes reorganize between infant sleep states and carry prognostic information for preterms.

Sleep architecture carries vital information about brain health across the lifespan. In particular, the ability to express distinct vigilance states is a key physiological marker of neurological wellbeing in the newborn infant although systems-level mechanisms remain elusive. Here, we demonstrate that the transition from quiet to active sleep in newborn infants is marked by a substantial reorganization of large-scale cortical activity and functional brain networks.

Atypical resting state neuromagnetic connectivity and spectral power in very preterm children.

Background: Children born very preterm often display selective cognitive difficulties at school age even in the absence of major brain injury. Alterations in neurophysiological activity underpinning such difficulties, as well as their relation to specific aspects of adverse neonatal experience, remain poorly understood. In the present study, we examined interregional connectivity and spectral power in very preterm children at school age, and their relationship with clinical neonatal variables and long-term outcomes (IQ, executive functions, externalizing/internalizing behavior, visual-motor integration).

Quiet sleep detection in preterm infants using deep convolutional neural networks.

Objective: Neonates spend most of their time asleep. Sleep of preterm infants evolves rapidly throughout maturation and plays an important role in brain development. Since visual labelling of the sleep stages is a time consuming task, automated analysis of electroencephalography (EEG) to identify sleep stages is of great interest to clinicians.

The Predictive Value of Amplitude-Integrated Electroencephalography in Preterm Infants for IQ and Other Neuropsychological Outcomes at Early School Age.

Background: Amplitude-integrated electroencephalography (aEEG) is used increasingly in neonatal intensive care and seems helpful in predicting outcomes at the age of 2 years.

Objectives: To determine whether early aEEG patterns in preterm infants are equally useful in predicting outcomes at early school age.

Methods: We recorded aEEG in 41 preterms (gestational age 26.

Multicentre prospective randomised single-blind controlled study protocol of the effect of an additional parent-administered sensorimotor stimulation on neurological development of preterm infants: Primebrain.

Introduction: Preterm and very low birthweight infants are at increased risk for neurodevelopmental disorders, including cerebral palsy, sensory impairment and intellectual disability. Several early intervention approaches have been designed in the hope of optimising neurological development in this context. It seems important that the intervention takes into account parental mental health, focuses on parent-child interactions and lasts sufficiently long.

Visual and Quantitative Electroencephalographic Analysis in Healthy Term Neonates Within the First Six Hours and the Third Day of Life.

Background: What constitutes a "normal" background electroencephalography (EEG) rhythm immediately after birth is not well understood. We performed video-electroencephalography recordings in the first six hours (first measure) and the third day of life (second measure) for evidence of transient changes in brain function.

Methods: We performed a cohort study of an incidental sample of healthy term neonates in a single-center nursery.

Review of sleep-EEG in preterm and term neonates.

Neonatal sleep is a crucial state that involves endogenous driven brain activity, important for neuronal survival and guidance of brain networks. Sequential EEG-sleep analysis in preterm infants provides insights into functional brain integrity and can document deviations of the biologically pre-programmed process of sleep ontogenesis during the neonatal period. Visual assessment of neonatal sleep-EEG, with integration of both cerebral and non-cerebral measures to better define neonatal state, is still considered the gold standard.

Brainstem as a developmental gateway to social attention.

Background: Evolution preserves social attention due to its key role in supporting survival. Humans are attracted to social cues from infancy, but the neurobiological mechanisms for the development of social attention are unknown. An evolutionary-based, vertical-hierarchical theoretical model of self-regulation suggests that neonatal brainstem inputs are key for the development of well-regulated social attention.

Multi-feature classifiers for burst detection in single EEG channels from preterm infants.

Objective: The study of electroencephalographic (EEG) bursts in preterm infants provides valuable information about maturation or prognostication after perinatal asphyxia. Over the last two decades, a number of works proposed algorithms to automatically detect EEG bursts in preterm infants, but they were designed for populations under 35 weeks of post menstrual age (PMA). However, as the brain activity evolves rapidly during postnatal life, these solutions might be under-performing with increasing PMA.

Detecting bursts in the EEG of very and extremely premature infants using a multi-feature approach.

Aim: To develop a method that segments preterm EEG into bursts and inter-bursts by extracting and combining multiple EEG features.

Methods: Two EEG experts annotated bursts in individual EEG channels for 36 preterm infants with gestational age < 30 weeks. The feature set included spectral, amplitude, and frequency-weighted energy features.

Periictal activity in cooled asphyxiated neonates with seizures.

Purpose: Seizures are common in critically ill neonates. Both seizures and antiepileptic treatments may lead to short term complications and worsen the outcomes. Predicting the risks of seizure reoccurrence could enable individual treatment regimens and better outcomes.

Severe hypercapnia causes reversible depression of aEEG background activity in neonates: an observational study.

Introduction: Elevated carbon dioxide (CO) blood levels have a depressant effect on the central nervous system and can lead to coma in adults. Less is known about the effect of CO on the neurological function of infants.

Objective: To describe the effect of acute severe hypercapnia (PaCO >70 mm Hg) on amplitude-integrated electroencephalography (aEEG) and cerebral oxygenation in newborn infants.

Spectral Electroencephalogram Analysis for the Evaluation of Encephalopathy Grade in Children With Acute Liver Failure.

Objective: Spectral electroencephalogram analysis is a method for automated analysis of electroencephalogram patterns, which can be performed at the bedside. We sought to determine the utility of spectral electroencephalogram for grading hepatic encephalopathy in children with acute liver failure.

Design: Retrospective cohort study.

Seizure-onset patterns in focal cortical dysplasia and neurodevelopmental tumors: Relationship with surgical prognosis and neuropathologic subtypes.

Objectives: The study of intracerebral electroencephalography (EEG) seizure-onset patterns is crucial to accurately define the epileptogenic zone and guide successful surgical resection. It also raises important pathophysiologic issues concerning mechanisms of seizure generation. Until now, several seizure-onset patterns have been described using distinct recording methods (subdural, depth electrode), mostly in temporal lobe epilepsies or with heterogeneous neocortical lesions.

Comparison of Amplitude-Integrated EEG and Conventional EEG in a Cohort of Premature Infants.

Objective: To compare amplitude-integrated EEG (aEEG) and conventional EEG (EEG) activity in premature neonates.

Methods: Biweekly aEEG and EEG were simultaneously recorded in a cohort of infants born less than 34 weeks gestation. aEEG recordings were visually assessed for lower and upper border amplitude and bandwidth.

Estimating functional brain maturity in very and extremely preterm neonates using automated analysis of the electroencephalogram.

Objective: To develop an automated estimate of EEG maturational age (EMA) for preterm neonates.

Methods: The EMA estimator was based on the analysis of hourly epochs of EEG from 49 neonates with gestational age (GA) ranging from 23 to 32weeks. Neonates had appropriate EEG for GA based on visual interpretation of the EEG.

Longitudinal study of preterm and full-term infants: High-density EEG analyses of cortical activity in response to visual motion.

Electroencephalogram (EEG) was used to investigate brain electrical activity of full-term and preterm infants at 4 and 12 months of age as a functional response mechanism to structured optic flow and random visual motion. EEG data were recorded with an array of 128-channel sensors. Visual evoked potentials (VEPs) and temporal spectral evolution (TSE, time-dependent amplitude changes) were analysed.