Neonatal EEG graded for severity of background abnormalities in hypoxic-ischaemic encephalopathy.

This report describes a set of neonatal electroencephalogram (EEG) recordings graded according to the severity of abnormalities in the background pattern. The dataset consists of 169 hours of multichannel EEG from 53 neonates recorded in a neonatal intensive care unit. All neonates received a diagnosis of hypoxic-ischaemic encephalopathy (HIE), the most common cause of brain injury in full term infants. For each neonate, multiple 1-hour epochs of good quality EEG were selected and then graded for background abnormalities. The grading system assesses EEG attributes such as amplitude, continuity, sleep-wake cycling, symmetry and synchrony, and abnormal waveforms. Background severity was then categorised into 4 grades: normal or mildly abnormal EEG, moderately abnormal EEG, majorly abnormal EEG, and inactive EEG. The data can be used as a reference set of multi-channel EEG for neonates with HIE, for EEG training purposes, or for developing and evaluating automated grading algorithms.

Machine learning for the early prediction of infants with electrographic seizures in neonatal hypoxic-ischemic encephalopathy.

OBJECTIVE: To assess if early clinical and electroencephalography (EEG) features predict later seizure development in infants with hypoxic-ischemic encephalopathy (HIE). METHODS: Clinical and EEG parameters <12 h of birth from infants with HIE across eight European Neonatal Units were used to develop seizure-prediction models. Clinical parameters included intrapartum complications, fetal distress, gestational age, delivery mode, gender, birth weight, Apgar scores, assisted ventilation, cord pH, and blood gases. The earliest EEG hour provided a qualitative analysis (discontinuity, amplitude, asymmetry/asynchrony, sleep-wake cycle [SWC]) and a quantitative analysis (power, discontinuity, spectral distribution, inter-hemispheric connectivity) from full montage and two-channel amplitude-integrated EEG (aEEG). Subgroup analysis, only including infants without anti-seizure medication (ASM) prior to EEG was also performed. Machine-learning (ML) models (random forest and gradient boosting algorithms) were developed to predict infants who would later develop seizures and assessed using Matthews correlation coefficient (MCC) and area under the receiver-operating characteristic curve (AUC). RESULTS: The study included 162 infants with HIE (53 had seizures). Low Apgar, need for ventilation, high lactate, low base excess, absent SWC, low EEG power, and increased EEG discontinuity were associated with seizures. The following predictive models were developed: clinical (MCC 0.368, AUC 0.681), qualitative EEG (MCC 0.467, AUC 0.729), quantitative EEG (MCC 0.473, AUC 0.730), clinical and qualitative EEG (MCC 0.470, AUC 0.721), and clinical and quantitative EEG (MCC 0.513, AUC 0.746). The clinical and qualitative-EEG model significantly outperformed the clinical model alone (MCC 0.470 vs 0.368, p-value .037). The clinical and quantitative-EEG model significantly outperformed the clinical model (MCC 0.513 vs 0.368, p-value .012). The clinical and quantitative-EEG model for infants without ASM (n = 131) had MCC 0.588, AUC 0.832. Performance for quantitative aEEG (n = 159) was MCC 0.381, AUC 0.696 and clinical and quantitative aEEG was MCC 0.384, AUC 0.720. SIGNIFICANCE: Early EEG background analysis combined with readily available clinical data helped predict infants who were at highest risk of seizures, hours before they occur. Automated quantitative-EEG analysis was as good as expert analysis for predicting seizures, supporting the use of automated assessment tools for early evaluation of HIE.

Neonatal Seizure Management: Is the Timing of Treatment Critical?

OBJECTIVE: To assess the impact of the time to treatment of the first electrographic seizure on subsequent seizure burden and describe overall seizure management in a large neonatal cohort. STUDY DESIGN: Newborns (36-44 weeks of gestation) requiring electroencephalographic (EEG) monitoring recruited to 2 multicenter European studies were included. Infants who received antiseizure medication exclusively after electrographic seizure onset were grouped based on the time to treatment of the first seizure: antiseizure medication within 1 hour, between 1 and 2 hours, and after 2 hours. Outcomes measured were seizure burden, maximum seizure burden, status epilepticus, number of seizures, and antiseizure medication dose over the first 24 hours after seizure onset. RESULTS: Out of 472 newborns recruited, 154 (32.6%) had confirmed electrographic seizures. Sixty-nine infants received antiseizure medication exclusively after the onset of electrographic seizure, including 21 infants within 1 hour of seizure onset, 15 between 1 and 2 hours after seizure onset, and 33 at >2 hours after seizure onset. Significantly lower seizure burden and fewer seizures were noted in the infants treated with antiseizure medication within 1 hour of seizure onset (P = .029 and .035, respectively). Overall, 258 of 472 infants (54.7%) received antiseizure medication during the study period, of whom 40 without electrographic seizures received treatment exclusively during EEG monitoring and 11 with electrographic seizures received no treatment. CONCLUSIONS: Treatment of neonatal seizures may be time-critical, but more research is needed to confirm this. Improvements in neonatal seizure diagnosis and treatment are also needed.

Heart rate variability analysis for the prediction of EEG grade in infants with hypoxic ischaemic encephalopathy within the first 12†h of birth.

Background and aims: Heart rate variability (HRV) has previously been assessed as a biomarker for brain injury and prognosis in neonates. The aim of this cohort study was to use HRV to predict the electroencephalography (EEG) grade in neonatal hypoxic-ischaemic encephalopathy (HIE) within the first 12 h. Methods: We included 120 infants with HIE recruited as part of two European multi-centre studies, with electrocardiography (ECG) and EEG monitoring performed before 12 h of age. HRV features and EEG background were assessed using the earliest 1 h epoch of ECG-EEG monitoring. HRV was expressed in time, frequency and complexity features. EEG background was graded from 0-normal, 1-mild, 2-moderate, 3-major abnormalities to 4-inactive. Clinical parameters known within 6 h of birth were collected (intrapartum complications, foetal distress, gestational age, mode of delivery, gender, birth weight, Apgar at 1 and 5, assisted ventilation at 10 min). Using logistic regression analysis, prediction models for EEG severity were developed for HRV features and clinical parameters, separately and combined. Multivariable model analysis included 101 infants without missing data. Results: Of 120 infants included, 54 (45%) had normal-mild and 66 (55%) had moderate-severe EEG grade. The performance of HRV model was AUROC 0.837 (95% CI: 0.759-0.914) and clinical model was AUROC 0.836 (95% CI: 0.759-0.914). The HRV and clinical model combined had an AUROC of 0.895 (95% CI: 0.832-0.958). Therapeutic hypothermia and anti-seizure medication did not affect the model performance. Conclusions: Early HRV and clinical information accurately predicted EEG grade in HIE within the first 12 h of birth. This might be beneficial when EEG monitoring is not available in the early postnatal period and for referral centres who may want some objective information on HIE severity.

Grading hypoxic-ischemic encephalopathy in neonatal EEG with convolutional neural networks and quadratic time-frequency distributions.

Objective.To develop an automated system to classify the severity of hypoxic-ischaemic encephalopathy injury (HIE) in neonates from the background electroencephalogram (EEG).Approach. By combining a quadratic time-frequency distribution (TFD) with a convolutional neural network, we develop a system that classifies 4 EEG grades of HIE. The network learns directly from the two-dimensional TFD through 3 independent layers with convolution in the time, frequency, and time-frequency directions. Computationally efficient algorithms make it feasible to transform each 5 min epoch to the time-frequency domain by controlling for oversampling to reduce both computation and computer memory. The system is developed on EEG recordings from 54 neonates. Then the system is validated on a large unseen dataset of 338 h of EEG recordings from 91 neonates obtained across multiple international centres.Main results.The proposed EEG HIE-grading system achieves a leave-one-subject-out testing accuracy of 88.9% and kappa of 0.84 on the development dataset. Accuracy for the large unseen test dataset is 69.5% (95% confidence interval, CI: 65.3%-73.6%) and kappa of 0.54, which is a significant (P<0.001) improvement over a state-of-the-art feature-based method with an accuracy of 56.8% (95% CI: 51.4%-61.7%) and kappa of 0.39. Performance of the proposed system was unaffected when the number of channels in testing was reduced from 8 to 2-accuracy for the large validation dataset remained at 69.5% (95% CI: 65.5%-74.0%).Significance.The proposed system outperforms the state-of-the-art machine learning algorithms for EEG grade classification on a large multi-centre unseen dataset, indicating the potential to assist clinical decision making for neonates with HIE.

A machine-learning algorithm for neonatal seizure recognition: a multicentre, randomised, controlled trial.

BACKGROUND: Despite the availability of continuous conventional electroencephalography (cEEG), accurate diagnosis of neonatal seizures is challenging in clinical practice. Algorithms for decision support in the recognition of neonatal seizures could improve detection. We aimed to assess the diagnostic accuracy of an automated seizure detection algorithm called Algorithm for Neonatal Seizure Recognition (ANSeR). METHODS: This multicentre, randomised, two-arm, parallel, controlled trial was done in eight neonatal centres across Ireland, the Netherlands, Sweden, and the UK. Neonates with a corrected gestational age between 36 and 44 weeks with, or at significant risk of, seizures requiring EEG monitoring, received cEEG plus ANSeR linked to the EEG monitor displaying a seizure probability trend in real time (algorithm group) or cEEG monitoring alone (non-algorithm group). The primary outcome was diagnostic accuracy (sensitivity, specificity, and false detection rate) of health-care professionals to identify neonates with electrographic seizures and seizure hours with and without the support of the ANSeR algorithm. Neonates with data on the outcome of interest were included in the analysis. This study is registered with ClinicalTrials.gov, NCT02431780. FINDINGS: Between Feb 13, 2015, and Feb 7, 2017, 132 neonates were randomly assigned to the algorithm group and 132 to the non-algorithm group. Six neonates were excluded (four from the algorithm group and two from the non-algorithm group). Electrographic seizures were present in 32 (25·0%) of 128 neonates in the algorithm group and 38 (29·2%) of 130 neonates in the non-algorithm group. For recognition of neonates with electrographic seizures, sensitivity was 81·3% (95% CI 66·7-93·3) in the algorithm group and 89·5% (78·4-97·5) in the non-algorithm group; specificity was 84·4% (95% CI 76·9-91·0) in the algorithm group and 89·1% (82·5-94·7) in the non-algorithm group; and the false detection rate was 36·6% (95% CI 22·7-52·1) in the algorithm group and 22·7% (11·6-35·9) in the non-algorithm group. We identified 659 h in which seizures occurred (seizure hours): 268 h in the algorithm versus 391 h in the non-algorithm group. The percentage of seizure hours correctly identified was higher in the algorithm group than in the non-algorithm group (177 [66·0%; 95% CI 53·8-77·3] of 268 h vs 177 [45·3%; 34·5-58·3] of 391 h; difference 20·8% [3·6-37·1]). No significant differences were seen in the percentage of neonates with seizures given at least one inappropriate antiseizure medication (37·5% [95% CI 25·0 to 56·3] vs 31·6% [21·1 to 47·4]; difference 5·9% [-14·0 to 26·3]). INTERPRETATION: ANSeR, a machine-learning algorithm, is safe and able to accurately detect neonatal seizures. Although the algorithm did not enhance identification of individual neonates with seizures beyond conventional EEG, recognition of seizure hours was improved with use of ANSeR. The benefit might be greater in less experienced centres, but further study is required. FUNDING: Wellcome Trust, Science Foundation Ireland, and Nihon Kohden.

Characterisation of neonatal seizures and their treatment using continuous EEG monitoring: a multicentre experience.

OBJECTIVE: The aim of this multicentre study was to describe detailed characteristics of electrographic seizures in a cohort of neonates monitored with multichannel continuous electroencephalography (cEEG) in 6 European centres. METHODS: Neonates of at least 36 weeks of gestation who required cEEG monitoring for clinical concerns were eligible, and were enrolled prospectively over 2 years from June 2013. Additional retrospective data were available from two centres for January 2011 to February 2014. Clinical data and EEGs were reviewed by expert neurophysiologists through a central server. RESULTS: Of 214 neonates who had recordings suitable for analysis, EEG seizures were confirmed in 75 (35%). The most common cause was hypoxic-ischaemic encephalopathy (44/75, 59%), followed by metabolic/genetic disorders (16/75, 21%) and stroke (10/75, 13%). The median number of seizures was 24 (IQR 9-51), and the median maximum hourly seizure burden in minutes per hour (MSB) was 21 min (IQR 11-32), with 21 (28%) having status epilepticus defined as MSB>30 min/hour. MSB developed later in neonates with a metabolic/genetic disorder. Over half (112/214, 52%) of the neonates were given at least one antiepileptic drug (AED) and both overtreatment and undertreatment was evident. When EEG monitoring was ongoing, 27 neonates (19%) with no electrographic seizures received AEDs. Fourteen neonates (19%) who did have electrographic seizures during cEEG monitoring did not receive an AED. CONCLUSIONS: Our results show that even with access to cEEG monitoring, neonatal seizures are frequent, difficult to recognise and difficult to treat. OBERSERVATION STUDY NUMBER: NCT02160171.

Toward a Personalized Real-Time Diagnosis in Neonatal Seizure Detection.

The problem of creating a personalized seizure detection algorithm for newborns is tackled in this paper. A probabilistic framework for semi-supervised adaptation of a generic patient-independent neonatal seizure detector is proposed. A system that is based on a combination of patient-adaptive (generative) and patient-independent (discriminative) classifiers is designed and evaluated on a large database of unedited continuous multichannel neonatal EEG recordings of over 800 h in duration. It is shown that an improvement in the detection of neonatal seizures over the course of long EEG recordings is achievable with on-the-fly incorporation of patient-specific EEG characteristics. In the clinical setting, the employment of the developed system will maintain a seizure detection rate at 70% while halving the number of false detections per hour, from 0.4 to 0.2 FD/h. This is the first study to propose the use of online adaptation without clinical labels, to build a personalized diagnostic system for the detection of neonatal seizures.

Exploring temporal information in neonatal seizures using a dynamic time warping based SVM kernel.

Seizure events in newborns change in frequency, morphology, and propagation. This contextual information is explored at the classifier level in the proposed patient-independent neonatal seizure detection system. The system is based on the combination of a static and a sequential SVM classifier. A Gaussian dynamic time warping based kernel is used in the sequential classifier. The system is validated on a large dataset of EEG recordings from 17 neonates. The obtained results show an increase in the detection rate at very low false detections per hour, particularly achieving a 12% improvement in the detection of short seizure events over the static RBF kernel based system.

Validation of an automated seizure detection algorithm for term neonates.

OBJECTIVE: The objective of this study was to validate the performance of a seizure detection algorithm (SDA) developed by our group, on previously unseen, prolonged, unedited EEG recordings from 70 babies from 2 centres. METHODS: EEGs of 70 babies (35 seizure, 35 non-seizure) were annotated for seizures by experts as the gold standard. The SDA was tested on the EEGs at a range of sensitivity settings. Annotations from the expert and SDA were compared using event and epoch based metrics. The effect of seizure duration on SDA performance was also analysed. RESULTS: Between sensitivity settings of 0.5 and 0.3, the algorithm achieved seizure detection rates of 52.6-75.0%, with false detection (FD) rates of 0.04-0.36FD/h for event based analysis, which was deemed to be acceptable in a clinical environment. Time based comparison of expert and SDA annotations using Cohen's Kappa Index revealed a best performing SDA threshold of 0.4 (Kappa 0.630). The SDA showed improved detection performance with longer seizures. CONCLUSION: The SDA achieved promising performance and warrants further testing in a live clinical evaluation. SIGNIFICANCE: The SDA has the potential to improve seizure detection and provide a robust tool for comparing treatment regimens.

Classification of hypoxic-ischemic encephalopathy using long term heart rate variability based features.

Hypoxic-ischemic HI injury at the time of birth could lead to severe neurological dysfunction at an older age. Therapeutic hypothermia can be used to treat HI if severity of injury is determined within 6 hours of birth. EEG is generally used to assess the brain injury but it is neither widely recorded after birth nor is the expertise to interpret it commonly available. This study presents a novel system to classify HI injury using heart rate variability. The system makes decisions based on long-term statistical features extracted from the short-term HRV features. The preliminary results show the promising performance and robustness of the proposed method given a poor quality dataset. This tool can serve as decision support system in remote maternity units to help clinical staff to initiate hypothermia.

Neonatal seizure detection using atomic decomposition with a novel dictionary.

Atomic decomposition (AD) can be used to efficiently decompose an arbitrary signal. In this paper, we present a method to detect neonatal electroencephalogram (EEG) seizure based on AD via orthogonal matching pursuit using a novel, application-specific, dictionary. The dictionary consists of pseudoperiodic Duffing oscillator atoms which are designed to be coherent with the seizure epochs. The relative structural complexity (a measure of the rate of convergence of AD) is used as the sole feature for seizure detection. The proposed feature was tested on a large clinical dataset of 826 h of EEG data from 18 full-term newborns with 1389 seizures. The seizure detection system using the proposed dictionary was able to achieve a median receiver operator characteristic area of 0.91 (IQR 0.87-0.95) across 18 neonates.

Discriminative and generative classification techniques applied to automated neonatal seizure detection.

A number of automated neonatal seizure detectors have been proposed in recent years. However, there exists a large variability in the morphology of seizure and background patterns, both across patients and over time. This has resulted in relatively poor performance from systems which have been tested over large datasets. Here, the benefits of employing a pattern recognition approach are discussed. Such a system may use numerous features paired with nonlinear classifiers. In particular, two types of nonlinear classifiers are contrasted for the task. Additionally, it is shown that the proposed architecture allows for efficient classifier combination which improves the performance of the algorithm. The resulting automated detector is shown to achieve field leading performance. A particular strength of the proposed algorithm is the performance of the algorithm when very low false detections are required, at 0.25 false detections per hour, the system is able to detect 75.4% of the seizure events.

EEG compression using JPEG2000: how much loss is too much?

Compression of biosignals is an important means of conserving power in wireless body area networks and ambulatory monitoring systems. In contrast to lossless compression techniques, lossy compression algorithms can achieve higher compression ratios and hence, higher power savings, at the expense of some degradation of the reconstructed signal. In this paper, a variant of the lossy JPEG2000 algorithm is applied to Electroencephalogram (EEG) data from the Freiburg epilepsy database. By varying compression parameters, a range of reconstructions of varying signal fidelity is produced. Although lossy compression has been applied to EEG data in previous studies, it is unclear what level of signal degradation, if any, would be acceptable to a clinician before diagnostically significant information is lost. In this paper, the reconstructed EEG signals are applied to REACT, a state-of-the-art seizure detection algorithm, in order to determine the effect of lossy compression on its seizure detection ability. By using REACT in place of a clinician, many hundreds of hours of reconstructed EEG data are efficiently analysed, thereby allowing an analysis of the amount of EEG signal distortion that can be tolerated. The corresponding compression ratios that can be achieved are also presented.

Ambulatory REACT: real-time seizure detection with a DSP microprocessor.

REACT (Real-Time EEG Analysis for event deteCTion) is a Support Vector Machine based technology which, in recent years, has been successfully applied to the problem of automated seizure detection in both adults and neonates. This paper describes the implementation of REACT on a commercial DSP microprocessor; the Analog Devices Blackfin®. The primary aim of this work is to develop a prototype system for use in ambulatory or in-ward automated EEG analysis. Furthermore, the complexity of the various stages of the REACT algorithm on the Blackfin processor is analysed; in particular the EEG feature extraction stages. This hardware profile is used to select a reduced, platform-aware feature set, in order to evaluate the seizure classification accuracy of a lower-complexity, lower-power REACT system.