Microstate Analysis Reflects Maturation of the Preterm Brain.

Preterm neonates are at risk of long-term neurodevelopmental impairments due to disruption of natural brain development. Electroencephalography (EEG) analysis can provide insights into brain development of preterm neonates. This study aims to explore the use of microstate (MS) analysis to evaluate global brain dynamics changes during maturation in preterm neonates with normal neurodevelopmental outcome.The dataset included 135 EEGs obtained from 48 neonates at varying postmenstrual ages (26.4 to 47.7 weeks), divided into four age groups. For each recording we extracted a 5-minute epoch during quiet sleep (QS) and during non-quiet sleep (NQS), resulting in eight groups (4 age group x 2 sleep states). We compared MS maps and corresponding (map-specific) MS metrics across groups using group-level maps. Additionally, we investigated individual map metrics.Four group-level MS maps accounted for approximately 70% of the global variance and showed non-random syntax. MS topographies and transitions changed significantly when neonates reached 37 weeks. For both sleep states and all MS maps, MS duration decreased and occurrence increased with age. The same relationships were found using individual maps, showing strong correlations (Pearson coefficients up to 0.74) between individual map metrics and post-menstrual age. Moreover, the Hurst exponent of the individual MS sequence decreased with age.The observed changes in MS metrics with age might reflect the development of the preterm brain, which is characterized by formation of neural networks. Therefore, MS analysis is a promising tool for monitoring preterm neonatal brain maturation, while our study can serve as a valuable reference for investigating EEGs of neonates with abnormal neurodevelopmental outcomes.

A multi-task and multi-channel convolutional neural network for semi-supervised neonatal artefact detection.

Objective. Automated artefact detection in the neonatal electroencephalogram (EEG) is crucial for reliable automated EEG analysis, but limited availability of expert artefact annotations challenges the development of deep learning models for artefact detection. This paper proposes a semi-supervised deep learning approach for artefact detection in neonatal EEG that requires few labelled data by training a multi-task convolutional neural network (CNN).Approach. An unsupervised and a supervised objective were jointly optimised by combining an autoencoder and an artefact classifier in one multi-output model that processes multi-channel EEG inputs. The proposed semi-supervised multi-task training strategy was compared to a classical supervised strategy and other existing state-of-the-art models. The models were trained and tested separately on two different datasets, which contained partially annotated multi-channel neonatal EEG. Models were evaluated using the F1-statistic and the relevance of the method was investigated in the context of a functional brain age (FBA) prediction model.Main results. The proposed multi-task and multi-channel CNN methods outperformed state-of-the-art methods, reaching F1 scores of 86.2% and 95.7% on two separate datasets. The proposed semi-supervised multi-task training strategy was shown to be superior to a classical supervised training strategy when the amount of labels in the dataset was artificially reduced. Finally, we found that the error of a brain age prediction model correlated with the amount of automatically detected artefacts in the EEG segment.Significance. Our results show that the proposed semi-supervised multi-task training strategy can train CNNs successfully even when the amount of labels in the dataset is limited. Therefore, this method is a promising semi-supervised technique for developing deep learning models with scarcely labelled data. Moreover, a correlation between the error of FBA estimates and the amount of detected artefacts in the corresponding EEG segments indicates the relevance of artefact detection for robust automated EEG analysis.

Partial wavelet coherence as a robust method for assessment of neurovascular coupling in neonates with hypoxic ischemic encephalopathy.

In neonates with hypoxic ischemic encephalopathy, the computation of wavelet coherence between electroencephalogram (EEG) power and regional cerebral oxygen saturation (rSO2) is a promising method for the assessment of neurovascular coupling (NVC), which in turn is a promising marker for brain injury. However, instabilities in arterial oxygen saturation (SpO2) limit the robustness of previously proposed methods. Therefore, we propose the use of partial wavelet coherence, which can eliminate the influence of SpO2. Furthermore, we study the added value of the novel NVC biomarkers for identification of brain injury compared to traditional EEG and NIRS biomarkers. 18 neonates with HIE were monitored for 72 h and classified into three groups based on short-term MRI outcome. Partial wavelet coherence was used to quantify the coupling between C3-C4 EEG bandpower (2-16 Hz) and rSO2, eliminating confounding effects of SpO2. NVC was defined as the amount of significant coherence in a frequency range of 0.25-1 mHz. Partial wavelet coherence successfully removed confounding influences of SpO2 when studying the coupling between EEG and rSO2. Decreased NVC was related to worse MRI outcome. Furthermore, the combination of NVC and EEG spectral edge frequency (SEF) improved the identification of neonates with mild vs moderate and severe MRI outcome compared to using EEG SEF alone. Partial wavelet coherence is an effective method for removing confounding effects of SpO2, improving the robustness of automated assessment of NVC in long-term EEG-NIRS recordings. The obtained NVC biomarkers are more sensitive to MRI outcome than traditional rSO2 biomarkers and provide complementary information to EEG biomarkers.

Cerebral oxygenation and body position in the preterm infant: A systematic review and meta-analysis.

AIM: After preterm birth, supine head midline position is supported for stable cerebral blood flow (CBF) and prevention of intraventricular haemorrhage (IVH), while prone position supports respiratory function and enables skin-to-skin care. The prone compared to supine position could lead to a change in near-infrared derived cerebral tissue oxygen saturation (rScO2), which is a surrogate for cerebral blood flow (CBF). By monitoring rScO2 neonatologists aim to stabilise CBF during intensive care and prevent brain injury. In this systematic review and meta-analysis, we investigate the effect of the body position on rScO2. METHODS: A comprehensive literature search was performed to identify all trials that included preterm infants in the first 2 weeks after birth and compared rScO2 in the prone versus supine head in midline position of the infant. A meta-analysis, including two subgroup analyses based on postnatal age (PNA) and gestational age (GA), was performed. RESULTS: Six observational cohort studies were included. In the second, but not the first week after birth, a significant higher rScO2 in the prone position was found with a mean difference of 1.97% (95% CI 0.87-3.07). No rScO2 difference was observed between positions in the extremely preterm nor the preterm group. CONCLUSION: No consistent evidence was found that body position influences rScO2 in the first 2 weeks after preterm birth. Subgroup analysis suggests that in the second week after birth, the prone position might result in higher cerebral rScO2 than the supine position with head in midline. Multiple factors determine the best body position in preterms.

Assessing Neurovascular Coupling Using Wavelet Coherence in Neonates with Asphyxia.

Brain monitoring is important in neonates with asphyxia in order to assess the severity of hypoxic ischaemic encephalopathy (HIE) and identify neonates at risk of adverse neurodevelopmental outcome. Previous studies suggest that neurovascular coupling (NVC), quantified as the interaction between electroencephalography (EEG) and near-infrared spectroscopy (NIRS)-derived regional cerebral oxygen saturation (rSO2) is a promising biomarker for HIE severity and outcome. In this study, we explore how wavelet coherence can be used to assess NVC. Wavelet coherence was computed in 18 neonates undergoing therapeutic hypothermia in the first 3 days of life, with varying HIE severities (mild, moderate, severe). We compared two pre-processing methods of the EEG prior to wavelet computation: amplitude integrated EEG (aEEG) and EEG bandpower. Furthermore, we proposed average real coherence as a biomarker for NVC. Our results indicate that NVC as assessed by wavelet coherence between EEG bandpower and rSO2 can be a valuable biomarker for HIE severity in neonates with peripartal asphyxia. More specifically, average real coherence in a very low frequency range (0.21-0.83 mHz) tends to be high (positive) in neonates with mild HIE, low (positive) in neonates with moderate HIE, and negative in neonates with severe HIE. Further investigation in a larger patient cohort is needed to validate our findings.

Automated detection and removal of flat line segments and large amplitude fluctuations in neonatal electroencephalography.

Background: Artefact removal in neonatal electroencephalography (EEG) by visual inspection generally depends on the expertise of the operator, is time consuming and is not a consistent pre-processing step to the pipeline for the automated EEG analysis. Therefore, there is the need for the automated detection and removal of artefacts in neonatal EEG, especially of distinct and predominant artefacts such as flat line segments (mainly caused by instrumental error where contact between electrodes and head box is lost) and large amplitude fluctuations (related to neonatal movements). Method: A threshold-based algorithm for the automated detection and removal of flat line segments and large amplitude fluctuations in neonatal EEG of infants at term-equivalent age is developed. The algorithm applies thresholds to the absolute second difference, absolute amplitude, absolute first difference and the ratio between the frequency content above 50 Hz and the frequency content across all frequencies. Results: The algorithm reaches a median accuracy of 0.91, a median hit rate of 0.91 and a median false discovery rate of 0.37. Also, a significant improvement (≈10%) in the performance of a four-stage sleep classifier is observed after artefact removal with the proposed algorithm as compared to before its application. Significance: An automated artefact removal method contributes to the pipeline of automated EEG analysis. The proposed algorithm has shown to have good performance and to be effective in neonatal EEG applications.

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.

Functional brain maturation and sleep organisation in neonates with congenital heart disease.

OBJECTIVE: Neonates with Congenital Heart Disease (CHD) have structural delays in brain development. To evaluate whether functional brain maturation and sleep-wake physiology is also disturbed, the Functional Brain Age (FBA) and sleep organisation on EEG during the neonatal period is investigated. METHODS: We compared 15 neonates with CHD who underwent multichannel EEG with healthy term newborns of the same postmenstrual age, including subgroup analysis for d-Transposition of the Great Arteries (d-TGA) (n = 8). To estimate FBA, a prediction tool using quantitative EEG features as input, was applied. Second, the EEG was automatically classified into the 4 neonatal sleep stages. Neonates with CHD underwent neurodevelopmental testing using the Bayley Scale of Infant Development-III at 24 months. RESULTS: Preoperatively, the FBA was delayed in CHD infants and more so in d-TGA infants. The FBA was positively correlated with motor scores. Sleep organisation was significantly altered in neonates with CHD. The duration of the sleep cycle and the proportion of Active Sleep Stage 1 was decreased, again more marked in the d-TGA infants. Neonates with d-TGA spent less time in High Voltage Slow Wave Sleep and more in Tracé Alternant compared to healthy terms. Both FBA and sleep organisation normalised postoperatively. The duration of High Voltage Slow Wave Sleep remained positively correlated with motor scores in d-TGA infants. INTERPRETATION: Altered early brain function and sleep is present in neonates with CHD. These results are intruiging, as inefficient neonatal sleep has been linked with adverse long-term outcome. Identifying how these rapid alterations in brain function are mitigated through improvements in cerebral oxygenation, surgery, drugs and nutrition may have relevance for clinical practice and outcome.

The effect of early procedural pain in preterm infants on the maturation of electroencephalogram and heart rate variability.

ABSTRACT: Preterm infants show a higher incidence of cognitive, social, and behavioral problems, even in the absence of major medical complications during their stay in the neonatal intensive care unit (NICU). Several authors suggest that early-life experience of stress and procedural pain could impact cerebral development and maturation resulting in an altered development of cognition, behavior, or motor patterns in later life. However, it remains very difficult to assess this impact of procedural pain on physiological development. This study describes the maturation of electroencephalogram (EEG) signals and heart rate variability in a prospective cohort of 92 preterm infants (<34 weeks gestational age) during their NICU stay. We took into account the number of noxious, ie, skin-breaking, procedures they were subjected in the first 5 days of life, which corresponded to a median age of 31 weeks and 4 days. Using physiological signal modelling, this study shows that a high exposure to early procedural pain, measured as skin-breaking procedures, increased the level of discontinuity in both EEG and heart rate variability in preterm infants. These findings have also been confirmed in a subset of the most vulnerable preterm infants with a gestational age lower than 29 weeks. We conclude that a high level of early pain exposure in the NICU increases the level of functional dysmaturity, which can ultimately impact preterm infants' future developmental outcome.

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 (δmax). 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 δmax 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 δmax 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.

A convolutional neural network outperforming state-of-the-art sleep staging algorithms for both preterm and term infants.

OBJECTIVE: To classify sleep states using electroencephalogram (EEG) that reliably works over a wide range of preterm ages, as well as term age. APPROACH: A convolutional neural network is developed to perform 2- and 4-class sleep classification in neonates. The network takes as input an 8-channel 30 s EEG segment and outputs the sleep state probabilities. Apart from simple downsampling of the input and smoothing of the output, the suggested network is an end-to-end algorithm that avoids the need for hand-crafted feature selection or complex pre/post processing steps. To train and test this method, 113 EEG recordings from 42 infants are used. MAIN RESULTS: For quiet sleep detection (the 2-class problem), mean kappa between the network estimate and the ground truth annotated by EEG human experts is 0.76. The sensitivity and specificity are 90% and 88%, respectively. For 4-class classification, mean kappa is 0.64. The averaged sensitivity and specificity (1 versus all) respectively equal 72% and 91%. The results outperform current state-of-the-art methods for which kappa ranges from 0.66 to 0.70 in preterm and from 0.51 to 0.61 in term infants, based on training and testing using the same database. SIGNIFICANCE: The proposed method has the highest reported accuracy for EEG sleep state classification for both preterm and term age neonates.

Automated EEG background analysis to identify neonates with hypoxic-ischemic encephalopathy treated with hypothermia at risk for adverse outcome: A pilot study.

BACKGROUND: To improve the objective assessment of continuous video-EEG (cEEG) monitoring of neonatal brain function, the aim was to relate automated derived amplitude and duration parameters of the suppressed periods in the EEG background (dynamic Interburst Interval= dIBIs) after neonatal hypoxic-ischemic encephalopathy (HIE) to favourable or adverse neurodevelopmental outcome. METHODS: Nineteen neonates (gestational age 36-41 weeks) with HIE underwent therapeutic hypothermia and had cEEG-monitoring. EEGs were retrospectively analyzed with a previously developed algorithm to detect the dynamic Interburst Intervals. Median duration and amplitude of the dIBIs were calculated at 1 h-intervals. Sensitivity and specificity of automated EEG background grading for favorable and adverse outcomes were assessed at 6 h-intervals. RESULTS: Dynamic IBI values reached the best prognostic value between 18 and 24 h (AUC of 0.93). EEGs with dIBI amplitude ≥15 µV and duration <10 s had a specificity of 100% at 6-12 h for favorable outcome but decreased subsequently to 67% at 25-42 h. Suppressed EEGs with dIBI amplitude <15 µV and duration >10 s were specific for adverse outcome (89-100%) at 18-24 h (n = 10). Extremely low voltage and invariant EEG patterns were indicative of adverse outcome at all time points. CONCLUSIONS: Automated analysis of the suppressed periods in EEG of neonates with HIE undergoing TH provides objective and early prognostic information. This objective tool can be used in a multimodal strategy for outcome assessment. Implementation of this method can facilitate clinical practice, improve risk stratification and aid therapeutic decision-making. A multicenter trial with a quantifiable outcome measure is warranted to confirm the predictive value of this method in a more heterogeneous dataset.

A Bayesian parametric model for quantifying brain maturation from sleep-EEG in the vulnerable newborn baby.

Newborn babies, particularly preterms, can exhibit early deviations in sleep maturation as seen by Electroencephalogram (EEG) recordings. This may be indicative of cognitive problems by school-age. The current 'clinically-driven' approach uses separate algorithms to first extract sleep states and then predict EEG 'brain-age'. Maturational deviations are identified when the brain-age no longer matches the Postmenstrual Age (PMA, the age since the last menstrual cycle of the mother). However, the PMA range where existing sleep staging algorithms perform optimally, is limited, which subsequently limits the PMA range for brain-age prediction. We introduce a Bayesian Parametric Model (BPM) as a single end-to-end solution to directly estimate brain-age, modelling for sleep state maturation without requiring a separately optimized sleep staging algorithm. Comparison of this model with a traditional multi-stage approach, yields a similar Krippendorff's $\alpha = 0.92$ (a performance measure ranging from 0 (chance agreement) to 1 (perfect agreement)) with the BPM performing better at younger ages <30 weeks PMA. The BPM's potential to detect maturational deviations is also explored on a few preterm babies who were abnormal at 9 months follow-up.

Cerebral autoregulation and activity after propofol for endotracheal intubation in preterm neonates.

BACKGROUND: Despite increasing use of propofol in neonates, observations on cerebral effects are limited. AIM: To investigate cerebral autoregulation (CAR) and activity after propofol for endotracheal intubation in preterm neonates. METHODS: Twenty-two neonates received propofol before intubation as part of a published dose-finding study. Mean arterial blood pressure (MABP), near-infrared spectroscopy-derived cerebral oxygenation (rScO2), and amplitude-integrated electroencephalography (aEEG) were analyzed until 180 min after propofol. CAR was expressed as transfer function (TF) gain, indicating % change in rScO2 per 1 mmHg change in MABP. Values exceeding mean TF gain + 2 standard deviations (SD) defined impaired CAR. RESULTS: After intubation with a median propofol dose of 1 (0.5-4.5) mg/kg, rScO2 remained stable during decreasing MABP. Mean (±SD) TF gain was 0.8 (±0.3)%/mmHg. Impaired CAR was identified in 1 and 5 patient(s) during drug-related hypotension and normal to raised MABP, respectively. Suppressed aEEG was observed up to 60 min after propofol. CONCLUSIONS: Drug-related hypotension and decreased cerebral activity after intubation with low propofol doses in preterm neonates were observed, without evidence of cerebral ischemic hypoxia. CAR remained intact during drug-related hypotension in 95.5% of patients. Cerebral monitoring including CAR clarifies the cerebral impact of MABP fluctuations.

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. This automated sleep scoring can aid in optimizing neonatal care and assessing brain maturation. APPROACH: In this study, we designed and implemented an 18-layer convolutional neural network to discriminate quiet sleep from non-quiet sleep in preterm infants. The network is trained on 54 recordings from 13 preterm neonates and the performance is assessed on 43 recordings from 13 independent patients. All neonates had a normal neurodevelopmental outcome and the EEGs were recorded between 27 and 42 weeks postmenstrual age. MAIN RESULTS: The proposed network achieved an area under the mean and median ROC curve equal to 92% and 98%, respectively. SIGNIFICANCE: Our findings suggest that CNN is a suitable and fast approach to classify neonatal sleep stages in preterm infants.

Automated EEG sleep staging in the term-age baby using a generative modelling approach.

OBJECTIVE: We develop a method for automated four-state sleep classification of preterm and term-born babies at term-age of 38-40 weeks postmenstrual age (the age since the last menstrual cycle of the mother) using multichannel electroencephalogram (EEG) recordings. At this critical age, EEG differentiates from broader quiet sleep (QS) and active sleep (AS) stages to four, more complex states, and the quality and timing of this differentiation is indicative of the level of brain development. However, existing methods for automated sleep classification remain focussed only on QS and AS sleep classification. APPROACH: EEG features were calculated from 16 EEG recordings, in 30 s epochs, and personalized feature scaling used to correct for some of the inter-recording variability, by standardizing each recording's feature data using its mean and standard deviation. Hidden Markov models (HMMs) and Gaussian mixture models (GMMs) were trained, with the HMM incorporating knowledge of the sleep state transition probabilities. Performance of the GMM and HMM (with and without scaling) were compared, and Cohen's kappa agreement calculated between the estimates and clinicians' visual labels. MAIN RESULTS: For four-state classification, the HMM proved superior to the GMM. With the inclusion of personalized feature scaling, mean kappa (±standard deviation) was 0.62 (±0.16) compared to the GMM value of 0.55 (±0.15). Without feature scaling, kappas for the HMM and GMM dropped to 0.56 (±0.18) and 0.51 (±0.15), respectively. SIGNIFICANCE: 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.

Weighted Performance Metrics for Automatic Neonatal Seizure Detection Using Multiscored EEG Data.

In neonatal intensive care units, there is a need for around the clock monitoring of electroencephalogram (EEG), especially for recognizing seizures. An automated seizure detector with an acceptable performance can partly fill this need. In order to develop a detector, an extensive dataset labeled by experts is needed. However, accurately defining neonatal seizures on EEG is a challenge, especially when seizure discharges do not meet exact definitions of repetitiveness or evolution in amplitude and frequency. When several readers score seizures independently, disagreement can be high. Commonly used metrics such as good detection rate (GDR) and false alarm rate (FAR) derived from data scored by multiple raters have their limitations. Therefore, new metrics are needed to measure the performance with respect to the different labels. In this paper, instead of defining the labels by consensus or majority voting, popular metrics including GDR, FAR, positive predictive value, sensitivity, specificity, and selectivity are modified such that they can take different scores into account. To this end, 353 hours of EEG data containing seizures from 81 neonates were visually scored by a clinical neurophysiologist, and then processed by an automated seizure detector. The scored seizures were mixed with false detections of an automated seizure detector and were relabeled by three independent EEG readers. Then, all labels were used in the proposed performance metrics and the result was compared with the majority voting technique and showed higher accuracy and robustness for the proposed metrics. Results were confirmed using a bootstrapping test.