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. Electrographic patterns evolve over time and are gradually time locked with behavioural characteristics which allow classification of quiet sleep and active sleep periods during the last 10weeks of gestation. Near term age, the neonate expresses a short ultradian sleep cycle, with two distinct active and quiet sleep, as well as brief periods of transitional or indeterminate sleep. Qualitative assessment of neonatal sleep is however challenged by biological and environmental variables that influence the expression of EEG-sleep patterns and sleep organization. Developing normative EEG-sleep data with the aid of automated analytic methods, can further improve our understanding of extra-uterine brain development and state organization under stressful or pathological conditions. Based on those developmental biomarkers of normal and abnormal brain function, research can be conducted to support and optimise sleep in the NICU, with the ultimate goal to improve therapeutic interventions and neurodevelopmental outcome.

Sleep state development in preterm neonates can provide crucial information regarding functional brain maturation and give insight into neurological well being. However, visual labeling of sleep stages from EEG requires expertise and is very time consuming, prompting the need for an automated procedure. We present a robust method for automated detection of preterm sleep from EEG, over a wide postmenstrual age (PMA = gestational age + postnatal age) range, focusing first on Quiet Sleep (QS) as an initial marker for sleep assessment. Our algorithm, CLuster-based Adaptive Sleep Staging (CLASS), detects QS if it remains relatively more discontinuous than non-QS over PMA. CLASS was optimized on a training set of 34 recordings aged 27-42 weeks PMA, and performance then assessed on a distinct test set of 55 recordings of the same age range. Results were compared to visual QS labeling from two independent raters (with inter-rater agreement Kappa = 0.93), using Sensitivity, Specificity, Detection Factor (DF = proportion of visual QS periods correctly detected by CLASS) and Misclassification Factor (MF = proportion of CLASS-detected QS periods that are misclassified). CLASS performance proved optimal across recordings at 31-38 weeks (median DF = 1.0, median MF 0-0.25, median Sensitivity 0.93-1.0, and median Specificity 0.80-0.91 across this age range), with minimal misclassifications at 35-36 weeks (median MF = 0). To illustrate the potential of CLASS in facilitating clinical research, normal maturational trends over PMA were derived from CLASS-estimated QS periods, visual QS estimates, and nonstate specific periods (containing QS and non-QS) in the EEG recording. CLASS QS trends agreed with those from visual QS, with both showing stronger correlations than nonstate specific trends. This highlights the benefit of automated QS detection for exploring brain maturation.

This is the first study to present a successful method for the automated staging of four states in term-age sleep using multichannel EEG. Results suggested a benefit in incorporating transition information using an HMM, and correcting for inter-recording variability through personalized feature scaling. Determining the timing and quality of these states are indicative of developmental delays in both preterm and term-born babies that may lead to learning problems by school age.

A convolutional neural network outperforming state-of-the-art sleep staging algorithms for both preterm and term infantsAccepted for publication in Journal of neural engineering, 2019.

Premature babies are subjected to environmental stresses that can affect brain maturation and cause abnormal neurodevelopmental outcome later in life. Better understanding this link is crucial to developing a clinical tool for early outcome estimation. We defined maturational trajectories between the electroencephalography (eeG)-derived 'brain-age' and postmenstrual age (the age since the last menstrual cycle of the mother) from longitudinal recordings during the baby's stay in the neonatal Intensive Care Unit. Data consisted of 224 recordings (65 patients) separated for normal and abnormal outcome at 9-24 months follow-up. Trajectory deviations were compared between outcome groups using the root mean squared error (RMSE) and maximum trajectory deviation (δ max). 113 features were extracted (per sleep state) to train a data-driven model that estimates brain-age, with the most prominent features identified as potential maturational and outcome-sensitive biomarkers. RMSE and δ max showed significant differences between outcome groups (cluster-based permutation test, p < 0.05). RMSE had a median (IQR) of 0.75 (0.60-1.35) weeks for normal outcome and 1.35 (1.15-1.55) for abnormal outcome, while δ max had a median of 0.90 (0.70-1.70) and 1.90 (1.20-2.90) weeks, respectively. Abnormal outcome trajectories were associated with clinically defined dysmature and disorganised EEG patterns, cementing the link between early maturational trajectories and neurodevelopmental outcome.

Highlights Multi-modal sensory stimulation is used to assess premature infant brain function. A template analysis approach is outlined for multi-modal stimulus-evoked EEG activity. Stimulus-evoked template magnitudes change with age. Prematurity results in accelerated maturation of visual and tactile sensory systems.

Objective. Automatic sleep stage scoring is of great importance for investigating sleep architecture during infancy. In this work, we introduce a novel multichannel approach based on deep learning networks and hidden Markov models (HMM) to improve the accuracy of sleep stage classification in term neonates. Approach. The classification performance was evaluated on quiet sleep (QS) and active sleep (AS) stages, each with two sub-states, using multichannel EEG data recorded from sixteen neonates with postmenstrual age of 38–40 weeks. A comprehensive set of linear and nonlinear features were extracted from thirty-second EEG segments. The feature space dimensionality was then reduced by using an evolutionary feature selection method called MGCACO (Modified Graph Clustering Ant Colony Optimization) based on the relevance and redundancy analysis. A bi-directional long-short time memory (BiLSTM) network was trained for sleep stage classification. The number of channels was optimized using the sequential forward selection method to reduce the spatial space. Finally, an HMM-based postprocessing stage was used to reduce false positives by incorporating the knowledge of transition probabilities between stages into the classification process. The method performance was evaluated using the K-fold (KFCV) and leave-one-out cross-validation (LOOCV) strategies. Main results. Using six-bipolar channels, our method achieved a mean kappa and an overall accuracy of 0.71–0.76 and 78.9%–82.4% using the KFCV and LOOCV strategies, respectively. Significance. The presented automatic sleep stage scoring method can be used to study the neurodevelopmental process and to diagnose brain abnormalities in term neonates.

In this paper, we introduce a new variation of the Convolutional Neural Network Inception block, called Sinc, for sleep stage classification in premature newborn babies using electroencephalogram (EEG). In practice, there are many medical centres where only a limited number of EEG channels are recorded. Existing automated algorithms mainly use multichannel EEGs which perform poorly when fewer numbers of channels are available. The proposed Sinc utilizes multi-scale analysis to place emphasis on the temporal EEG information to be less dependent on the number of EEG channels. In Sinc, we increase the receptive fields through Inception while by additionally sharing the filters that have similar receptive fields, overfitting is controlled and the number of trainable parameters dramatically reduced. To train and test this model, 96 longitudinal EEG recordings from 26 premature infants are used. The Sincbased model significantly outperforms state-of-the-art neonatal quiet sleep detection algorithms, with mean Kappa 0.77 ± 0.01 (with 8-channel EEG) and 0.75 ± 0.01 (with a single bipolar channel EEG). This is the first study using Inception-based networks for EEG analysis that utilizes filter sharing to improve efficiency and trainability. The suggested network can successfully detect quiet sleep stages with even a single EEG channel making it more practical especially in the hospital setting where cerebral function monitoring is predominantly used.