Review of Neonatal EEG

Resting state electroencephalographic brain activity in neonates can predict age and is indicative of neurodevelopmental outcome

OBJECTIVE

Electroencephalography (EEG) can be used to estimate neonates' biological brain age. Discrepancies between postmenstrual age and brain age, termed the brain age gap, can potentially quantify maturational deviation. Existing brain age EEG models are not well suited to clinical cot-side use for estimating neonates' brain age gap due to their dependency on relatively large data and pre-processing requirements.

METHODS

We trained a deep learning model on resting state EEG data from preterm neonates with normal neurodevelopmental Bayley Scale of Infant and Toddler Development (BSID) outcomes, using substantially reduced data requirements. We subsequently tested this model in two independent datasets from two clinical sites.

RESULTS

In both test datasets, using only 20 min of resting-state EEG activity from a single channel, the model generated accurate age predictions: mean absolute error = 1.03 weeks (p-value = 0.0001) and 0.98 weeks (p-value = 0.0001). In one test dataset, where 9-month follow-up BSID outcomes were available, the average neonatal brain age gap in the severe abnormal outcome group was significantly larger than that of the normal outcome group: difference in mean brain age gap = 0.50 weeks (p-value = 0.04).

CONCLUSIONS

These findings demonstrate that the deep learning model generalises to independent datasets from two clinical sites, and that the model's brain age gap magnitudes differ between neonates with normal and severe abnormal follow-up neurodevelopmental outcomes.

SIGNIFICANCE

The magnitude of neonates' brain age gap, estimated using only 20 min of resting state EEG data from a single channel, can encode information of clinical neurodevelopmental value.

Ensemble Learning Using Individual Neonatal Data for Seizure Detection

Objective: Sharing medical data between institutions is difficult in practice due to data protection laws and official procedures within institutions. Therefore, most existing algorithms are trained on relatively small electroencephalogram (EEG) data sets which is likely to be detrimental to prediction accuracy. In this work, we simulate a case when the data can not be shared by splitting the publicly available data set into disjoint sets representing data in individual institutions. Methods and procedures: We propose to train a (local) detector in each institution and aggregate their individual predictions into one final prediction. Four aggregation schemes are compared, namely, the majority vote, the mean, the weighted mean and the Dawid-Skene method. The method was validated on an independent data set using only a subset of EEG channels. Results: The ensemble reaches accuracy comparable to a single detector trained on all the data when sufficient amount of data is available in each institution. Conclusion: The weighted mean aggregation scheme showed best performance, it was only marginally outperformed by the Dawid–Skene method when local detectors approach performance of a single detector trained on all available data. Clinical impact: Ensemble learning allows training of reliable algorithms for neonatal EEG analysis without a need to share the potentially sensitive EEG data between institutions.

A Deep Shared Multi-Scale Inception Network Enables Accurate Neonatal Quiet Sleep Detection with Limited EEG Channels

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 multi-channel 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 Sinc-based 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.

High-frequency oscillations recorded with surface EEG in neonates with seizures

OBJECTIVE

Neonatal seizures are often the first symptom of perinatal brain injury. High-frequency oscillations (HFOs) are promising new biomarkers for epileptogenic tissue and can be found in intracranial and surface EEG. To date, we cannot reliably predict which neonates with seizures will develop childhood epilepsy. We questioned whether epileptic HFOs can be generated by the neonatal brain and potentially predict epilepsy.

METHODS

We selected 24 surface EEGs sampled at 2048 Hz with 175 seizures from 16 neonates and visually reviewed them for HFOs. Interictal epochs were also reviewed.

RESULTS

We found HFOs in thirteen seizures (7%) from four neonates (25%). 5025 ictal ripples (rate 10 to 1311/min; mean frequency 135 Hz; mean duration 66 ms) and 1427 fast ripples (rate 8 to 356/min; mean frequency 298 Hz; mean duration 25 ms) were marked. Two neonates (13%) showed interictal HFOs (285 ripples and 25 fast ripples). Almost all HFOs co-occurred with sharp transients. We could not find a relationship between neonatal HFOs and outcome yet.

CONCLUSIONS

Neonatal HFOs co-occur with ictal and interictal sharp transients.

SIGNIFICANCE

The neonatal brain can generate epileptic ripples and fast ripples, particularly during seizures, though their occurrence is not common and potential clinical value not evident yet.

Technical recommendations and interpretation guidelines for electroencephalography for premature and full-term newborns

Electroencephalography (EEG) of neonatal patients is amongst the most valuable diagnostic and prognostic tool. EEG recordings, acquired at the bedside of infants, evaluate brain function and the maturation of premature and extremely premature infants. Strict conditions of acquisition and interpretation must be respected to guarantee the quality of the EEG and ensure its safety for fragile children. This article provides guidance for EEG acquisition including: (1) the required equipment and devices, (2) the modalities of installation and asepsis precautions, and (3) the digital signal acquisition parameters to use during the recording. The fundamental role of a well-trained technician in supervising the EEG recording is emphasized. In parallel to the acquisition recommendations, we present a guideline for EEG interpretation and reporting. The successive steps of EEG interpretation, from reading the EEG to writing the report, are described. The complexity of the EEG signal in neonates makes artefact detection difficult. Thus, we provide an overview of certain characteristic artefacts and detail the methods for eliminating them.

Right Temporal Oscillations of Infants in Relation to Contingent Learning

Contingent learning is an agent for infants to explore the environment, which enhances the maturation of different developmental domains. This paper presents one of the first to investigate neural activities related to contingent learning of infants by analyzing their motor response that could elicit an audio-visual feedback. Three different kinds of motor response of infants were investigated, including unilateral kicks, synchronized kicks, and alternate kicks. Electroencephalographic (EEG) signals of infants were recorded before the motor experiments. Higher theta band power and lower upper beta power at the right temporal lobe of infants predicted a higher ratio of total unilateral kicks and a lower ratio of synchronized kicks at the later acquisition stage of the experiment. As contingent learning could be reflected by specific motor response in relation to the audio-visual stimuli, the results suggested that right temporal oscillations could predict different levels of contingent learning of infants.

Applying a data-driven approach to quantify EEG maturational deviations in preterms with normal and abnormal neurodevelopmental outcomes

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.

How Early Can a Seizure Happen? Pathophysiological Considerations of Extremely Premature Infant Brain Development

Seizures in neonates represent a neurologic emergency requiring prompt recognition, determination of etiology, and treatment. Yet, the definition and identification of neonatal seizures remain challenging and controversial, in part due to the unique physiology of brain development at this life stage. These issues are compounded when considering seizures in premature infants, in whom the complexities of brain development may engender different clinical and electrographic seizure features at different points in neuronal maturation. In extremely premature infants (< 28 weeks gestational age), seizure pathophysiology has not been explored in detail. This review discusses the physiological and structural development of the brain in this developmental window, focusing on factors that may lead to seizures and their consequences at this early time point. We hypothesize that the clinical and electrographic phenomenology of seizures in extremely preterm infants reflects the specific pathophysiology of brain development in that age window.

An Automated Quiet Sleep Detection Approach in Preterm Infants as a Gateway to Assess Brain Maturation

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.