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

Early automated classification of neonatal hypoxic-ischemic encephalopathy - An aid to the decision to use therapeutic hypothermia

OBJECTIVE

The study aimed to address the challenge of early assessment of neonatal hypoxic-ischemic encephalopathy (HIE) severity to identify candidates for therapeutic hypothermia (TH). The objective was to develop an automated classification model for neonatal EEGs, enabling accurate HIE severity assessment 24/7.

METHODS

EEGs recorded within 6 h of life after perinatal anoxia were visually graded into 3 severity groups (HIE French Classification) and quantified using 6 qEEG markers measuring amplitude, continuity and frequency content. Machine learning models were developed on a dataset of 90 EEGs and validated on an independent dataset of 60 EEGs.

RESULTS

The selected model achieved an overall accuracy of 80.6% in the development phase and 80% in the validation phase. Notably, the model accurately identified 28 out of 30 children for whom TH was indicated after visual EEG analysis, with only 2 cases (moderate EEG abnormalities) not recommended for cooling.

CONCLUSIONS

The combination of clinically relevant qEEG markers led to the development of an effective automated EEG classification model, particularly suited for the post-anoxic latency phase. This model successfully discriminated neonates requiring TH.

SIGNIFICANCE

The proposed model has potential as a bedside clinical decision support tool for TH.

Negative central activity in extremely preterm newborns: EEG characterization and relationship with brain injuries and neurodevelopmental outcome

OBJECTIVE

To characterize Negative Central Activity (NCA), an overlooked electroencephalographic activity of preterm newborns and investigate its relationship with brain injuries, dysfunction, and neurodevelopmental outcome.

METHODS

109 preterm infants (23-28 weeks) were retrospectively included. NCA were selected at the negative peak on EEG. Individual averaged NCA were automatically characterized. Brain structural data were collected from cranial ultrasounds (cUS). The neurodevelopmental outcome at two years of age was assessed by the Denver Developmental Screening Test-II.

RESULTS

Thirty-six (33%) children showed NCA: 6,721 NCA were selected, a median of 75 (interquartile range, 25/157.3) per EEG. NCA showed a triphasic morphology, with a mean amplitude and duration of the negative component of 24.6-40.0 µV and 222.7-257.3 ms. The presence of NCA on EEG was associated with higher intraventricular haemorrhage (IVH) grade on the first (P = 0.016) and worst neonatal cUS (P < 0.001) and poorer neurodevelopmental outcome (P < 0.001).

CONCLUSIONS

NCA is an abnormal EEG feature of extremely preterm newborns that may correspond to the functional neural impact of a vascular pathology.

SIGNIFICANCE

The NCA relationships with an adverse outcome and the presence/severity of IVH argue for considering NCA in the assessment of pathological processes in the developing brain network and for early outcome prediction.

Deep Learning for Generalized EEG Seizure Detection after Hypoxia-Ischemia-Preclinical Validation

Brain maturity and many clinical treatments such as therapeutic hypothermia (TH) can significantly influence the morphology of neonatal EEG seizures after hypoxia-ischemia (HI), and so there is a need for generalized automatic seizure identification. This study validates efficacy of advanced deep-learning pattern classifiers based on a convolutional neural network (CNN) for seizure detection after HI in fetal sheep and determines the effects of maturation and brain cooling on their accuracy. The cohorts included HI-normothermia term (n = 7), HI-hypothermia term (n = 14), sham-normothermia term (n = 5), and HI-normothermia preterm (n = 14) groups, with a total of >17,300 h of recordings. Algorithms were trained and tested using leave-one-out cross-validation and k-fold cross-validation approaches. The accuracy of the term-trained seizure detectors was consistently excellent for HI-normothermia preterm data (accuracy = 99.5%, area under curve (AUC) = 99.2%). Conversely, when the HI-normothermia preterm data were used in training, the performance on HI-normothermia term and HI-hypothermia term data fell (accuracy = 98.6%, AUC = 96.5% and accuracy = 96.9%, AUC = 89.6%, respectively). Findings suggest that HI-normothermia preterm seizures do not contain all the spectral features seen at term. Nevertheless, an average 5-fold cross-validated accuracy of 99.7% (AUC = 99.4%) was achieved from all seizure detectors. This significant advancement highlights the reliability of the proposed deep-learning algorithms in identifying clinically translatable post-HI stereotypic seizures in 256Hz recordings, regardless of maturity and with minimal impact from hypothermia.

Pitfalls in scalp EEG: Current obstacles and future directions

Although electroencephalography (EEG) serves a critical role in the evaluation and management of seizure disorders, it is commonly misinterpreted, resulting in avoidable medical, social, and financial burdens to patients and health care systems. Overinterpretation of sharply contoured transient waveforms as being representative of interictal epileptiform abnormalities lies at the core of this problem. However, the magnitude of these errors is amplified by the high prevalence of paroxysmal events exhibited in clinical practice that compel investigation with EEG. Neurology training programs, which vary considerably both in the degree of exposure to EEG and the composition of EEG didactics, have not effectively addressed this widespread issue. Implementation of competency-based curricula in lieu of traditional educational approaches may enhance proficiency in EEG interpretation amongst general neurologists in the absence of formal subspecialty training. Efforts in this regard have led to the development of a systematic, high-fidelity approach to the interpretation of epileptiform discharges that is readily employable across medical centers. Additionally, machine learning techniques hold promise for accelerating accurate and reliable EEG interpretation, particularly in settings where subspecialty interpretive EEG services are not readily available. This review highlights common diagnostic errors in EEG interpretation, limitations in current educational paradigms, and initiatives aimed at resolving these challenges.

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.

The prognostic value of neonatal conventional-EEG monitoring in hypoxic-ischemic encephalopathy during therapeutic hypothermia

AIM

To determine the prognostic value of conventional electroencephalography (EEG) monitoring in neonatal hypoxic-ischemic encephalopathy (HIE).

METHOD

In this multicentre retrospective study, 95 full-term neonates (mean of 39.3wks gestational age [SD  1.4], 36 [38%] females, 59 [62%] males) with HIE (2013-2016) undergoing therapeutic hypothermia were divided between favourable or adverse outcomes. Background EEG activity (French classification scale: 0-1-2-3-4-5) and epileptic seizure burden (epileptic seizure scale: 0-1-2) were graded for seven 6-hour periods. Conventional EEG monitoring was investigated by principal component analysis (PCA), with clustering methods to extract prognostic biomarkers of development at 2 years and infant death.

RESULTS

Eighty-one per cent of infants with an adverse outcome had a French classification scale equal to or greater than 3 after H48 (100% at H6-12). The H6-12 epileptic seizure scale was equal to or greater than 1 for 39%, increased to 52% at H30-36 and then remained equal to or greater than 1 for 39% after H48. Forty-five per cent of infants with a favourable outcome had a H6-12 French classification scale equal to or greater than 3, which dropped to 5% after H48; 13% had a H6-12 epileptic seizure scale equal to or greater than 1 but no seizures after H48. Clustering methods based on PCA showed the high efficiency (96%) of conventional EEG monitoring for outcome prediction and allowed the definition of three prognostic EEG biomarkers: H6-78 French classification scale mean, H6-78 French classification scale slope, and H30-78 epileptic seizure scale mean.

INTERPRETATION

Early lability and recovery of physiological features is prognostic of a favourable outcome. Seizure onset from the second day should also be considered to accurately predict neurodevelopment in HIE and support the importance of conventional EEG monitoring in HIE in infants cooled with therapeutic hypothermia.

WHAT THIS PAPER ADDS

Comprehensive analysis showed the high prognostic efficiency (96%) of conventional electroencephalography (EEG) monitoring. Prognostic EEG biomarkers consist of the grade of background EEG activity, its evolution, and the mean seizure burden. Persistent seizures (H48) without an improvement in background EEG activity were consistently associated with an adverse outcome.

EEG in neonatal seizures: where to look and what to see

INTRODUCTION

Neonatal seizures are frequent and carry a detrimental prognostic outlook. Diagnosis is based on EEG confirmation. Classification has recently changed.

AREAS COVERED

We consulted original papers, book chapters, atlases, and reviews to provide a narrative overview on EEG characteristics of neonatal seizures. We searched PubMed, without time restrictions (last visited: 31 May 2022). Additional papers were extracted from the references list of selected papers. We describe the typical neonatal ictal EEG discharges morphology, location, and propagation, together with age-dependent features. Etiology-dependent electroclinical features, when identifiable, are presented for both acute symptomatic neonatal seizures and neonatal-onset epilepsies and developmental/epileptic encephalopathies. The few ictal variables known to predict long-term outcome have been discussed.

EXPERT OPINION

Multimodal neuromonitoring in critically ill newborns, high-density EEG, and functional neuroimaging might increase our insight into the neurophysiological bases of seizures in newborns. Increasing availability of long-term monitoring with conventional video-EEG and automated detection methods will allow clinicians and researchers to gather an ever expanding bulk of clinical and neurophysiological data to enhance accuracy with deep phenotyping. The latest classification proposal represents an input for critically revising our diagnostic abilities with respect to seizure definition, duration, and semiology, possibly further promoting clinical research.

The frontal sharp transient in newborns: An endogenous neurobiomarker concomitant to the physiological and critical transitional period around delivery?

The frontal sharp transient (FST) consists of transient electrical activity recorded around the transitional period from the in to ex utero environment. Although its positive predictive value is assumed, nothing is known about its functionality or origin. The objectives were (i) to define its characteristics and (ii) to develop functional hypothesis. The 128-channels high-resolution electroencephalograms of 20 healthy newborns (37.1-41.6 weeks) were studied. The morphological and time-frequency characteristics of 418 FSTs were analyzed. The source localization of the FSTs was obtained using a finite element head model (5 layers and fontanels) and various source localization methods (distributed and dipolar). The characteristics (duration, slopes, and amplitude) and the localization of FSTs were not modulated by the huge developmental neuronal processes that occur during the very last period of gestation. The sources were located beneath the ventral median part of the frontal lobe around the interhemispheric fissure, suggesting that the olfactory bulbs and orbitofrontal cortex, essential in olfaction and the mother-infant attachment relationship, are likely candidates for the generation of FSTs. FSTs may contribute to the implementation of the functionalities of brain structures involved in the higher-order processing necessary for survival ahead of delivery, with a genetic fingerprint.

Expert consensus on minimum technical standards for neonatal electroencephalography operation and report writing

Electroencephalography (EEG) monitoring is an important examination method in the management of critically ill neonates, which can be used to evaluate brain function and developmental status, severity of encephalopathy, and seizures and predict the long-term neurodevelopmental outcome of high-risk neonates with brain injury. EEG monitoring for neonates is different from that for adults and children, and its operation and interpretation are easily affected by the number of recording electrodes, electrode montage, and monitoring quality. Therefore, standard operation must be followed to ensure the quality of signal acquisition and correct interpretation, thereby ensuring proper management of critically ill neonates. The Subspecialty Group of Neonatology, Society of Pediatrics, Chinese Medical Association established an expert group composed of professionals in neonatology and brain electrophysiology to perform a literature review, summarize the minimum technical standards for neonatal EEG monitoring, and develop the expert consensus on minimum technical standards for neonatal EEG operation and report writing. This consensus will provide guidance for neonatal EEG operation, including technical parameters of EEG monitoring device, operation procedures of EEG monitoring, and specifications for report writing.

Expert consensus on grading management of electroencephalogram monitoring in neonates

Neonatal electroencephalogram (EEG) monitoring guidelines have been published by American Clinical Neurophysiology Society, and the expert consensus on neonatal amplitude-integrated EEG (aEEG) has also been published in China. It is difficult to strictly follow the guidelines or consensus for EEG monitoring in different levels of neonatal units due to a lack of EEG monitoring equipment and professional interpreters. The Subspecialty Group of Neonatology, Society of Pediatrics, Chinese Medical Association, established an expert group composed of professionals in neonatology, pediatric neurology, and brain electrophysiology to review published guidelines and consensuses and the articles in related fields and propose grading management recommendations for EEG monitoring in different levels of neonatal units. Based on the characteristics of video EEG and aEEG, local medical resources, and disease features, the expert group recommends that video EEG and aEEG can complement each other and can be used in different levels of neonatal units. The consensus also gives recommendations for promoting collaboration between professionals in neonatology, pediatric neurology, and brain electrophysiology and implementing remote EEG monitoring.