Search

INTRODUCTION: Existing automated seizure detection algorithms report sensitivities between 43% and 77% and specificities between 56% and 90%. The algorithms suffer from false alarms when applied to neonatal EEG because of the high degree of nurse handling and rhythmic patting used to soothe neonates. Computer vision technology that quantifies movement in real time could distinguish artifactual motion and improve automated neonatal seizure detection algorithms. METHODS: The authors used video EEG recordings from 43 neonates undergoing monitoring for seizures as part of the NEOLEV2 clinical trial. The Persyst neonatal automated seizure detection algorithm ran in real time during study EEG acquisitions. Computer vision algorithms were applied to extract detailed accounts of artifactual movement of the neonate or people near the neonate though dense optical flow estimation. RESULTS: Using the methods mentioned above, 197 periods of patting activity were identified and quantified, of which 45 generated false-positive automated seizure detection events. A binary patting detection algorithm was trained with a subset of 470 event videos. This supervised detection algorithm was applied to a testing subset of 187 event videos with 8 false-positive events, which resulted in a 24% reduction in false-positive automated seizure detections and a 50% reduction in false-positive events caused by neonatal care patting, while maintaining 11 of 12 true-positive seizure detection events. CONCLUSIONS: This work presents a novel approach to improving automated seizure detection algorithms used during neonatal video EEG monitoring. This artifact detection mechanism can improve the ability of a seizure detector algorithm to distinguish between artifact and true seizure activity.

Newborn care has witnessed significant improvements in survival, but ongoing concerns persist about neurodevelopmental outcome. Protecting the newborn brain is the focus of neurocritical care in the intensive care unit. Brain-focused care places emphasis on clinical practices supporting neurodevelopment in conjunction with early detection, diagnosis, and treatment of brain injury. Technology now facilitates continuous cot-side monitoring of brain function. Neuromonitoring techniques in neonatal intensive care units include the use of electroencephalography (EEG) or amplitude-integrated EEG (aEEG) and near-infrared spectroscopy. This article aims to provide an introduction to EEG, which is appropriate for neonatal healthcare professionals.

ObjectiveEstablish if serial, multichannel video electroencephalography (EEG) in preterm infants can accurately predict 2-year neurodevelopmental outcome.Design and patientsEEGs were recorded at three time points over the neonatal course for infants SettingNeonatal intensive care unit at Cork University Maternity Hospital, Ireland.Main outcome measuresBayley Scales of Infant Development III at 2 years’ corrected age.ResultsSixty-seven infants were prospectively enrolled in the study and 57 had follow-up available (median GA 28.9 weeks (IQR 26.5–30.4)). Forty had normal outcome, 17 had abnormal outcome/died. All EEG time points were individually predictive of abnormal outcome; however, the 35-week EEG performed best. The area under the receiver operating characteristic curve (AUC) for this time point was 0.91 (95% CI 0.83 to 1), pConclusionMultichannel EEG is a strong predictor of 2-year outcome in preterm infants particularly when recorded around 35 weeks’ PMA. Infants at high risk of brain injury may benefit from early postnatal EEG recording which, if normal, is reassuring. Postnatal clinical complications can contribute to poor outcome; therefore, we state that a later EEG around 35 weeks has a role to play in prognostication.

To identify relevant quantitative parameters for early classification of neonatal hypoxic-ischemic encephalopathy (HIE) severity from conventional EEGs.Ninety EEGs, recorded in full-term infants within 6 h of life after perinatal hypoxia, were visually classified according to the French EEG classification into three groups of increasing HIE severity. Physiologically significant EEG features (signal amplitude, continuity and frequency content) were automatically quantified using different parameters. The EEG parameters selection was based on their ability to reproduce the visual EEG classification. Post hoc analysis based on clinical outcome was performed.Six EEG parameters were selected, with overall EEG classification performances between 61% and 70%. All parameters differed significantly between group 3 (severe) and groups 1 (normal-mildly abnormal) and 2 (moderate) EEGs (p 0.001). Amplitude and discontinuity parameters were different between the 3 groups (p 0.01) and were also the best predictors of clinical outcome. Conversely, pH and lactate did not differ between groups.This study provides quantitative EEG parameters that are complementary to visual analysis as early markers of neonatal HIE severity. These parameters could be combined in a multiparametric algorithm to improve their classification performance. The absence of relationship between pH lactate and HIE severity reinforces the central role of early neonatal EEG.

Electroencephalography (EEG) is the reference tool for the analysis of brain function, reflecting normal and pathological neuronal network activity. During the neonatal period, EEG patterns evolve weekly, according to gestational age. The first analytical criteria for the various maturational stages and standardized neonatal EEG terminology were published by a group of French neurophysiologists training in Paris (France) in 1999. These criteria, defined from analog EEG, were completed in 2010 with digital EEG analysis. Since then, this work has continued, aided by the technical progress in EEG acquisition, the improvement of knowledge on the maturating processes of neuronal networks, and the evolution of critical care. In this review, we present an exhaustive and didactic overview of EEG characteristics from extremely premature to full-term infants. This update is based on the scientific literature, enhanced by the study of normal EEGs of extremely premature infants by our group of neurophysiologists. For educational purposes, particular attention has been paid to illustrations using new digital tools.

Highlights • Higher power of cortical bursts after postnatal day 3 predicted worse cognitive, language and motor outcomes. • Association between cortical bursts and outcome was independent of structural MRI findings. • EEG may provide additional information by indexing persistent active mechanisms that support recovery or exacerbate damage., Objective Early prediction of neurological deficits following neonatal hypoxic-ischemic encephalopathy (HIE) may help to target support. Neonatal animal models suggest that recovery following hypoxia-ischemia depends upon cortical bursting. To test whether this holds in human neonates, we correlated the magnitude of cortical bursting during recovery (≥postnatal day 3) with neurodevelopmental outcomes. Methods We identified 41 surviving infants who received therapeutic hypothermia for HIE (classification at hospital discharge: 19 mild, 18 moderate, 4 severe) and had 9-channel electroencephalography (EEG) recordings as part of their routine care. We correlated burst power with Bayley-III cognitive, motor and language scores at median 24 months. To examine whether EEG offered additional prognostic information, we controlled for structural MRI findings. Results Higher power of central and occipital cortical bursts predicted worse cognitive and language outcomes, and higher power of central cortical bursts predicted worse motor outcome, all independently of structural MRI findings. Conclusions Clinical EEG after postnatal day 3 may provide additional prognostic information by indexing persistent active mechanisms that either support recovery or exacerbate brain damage, especially in infants with less severe encephalopathy. Significance These findings could allow for the effect of clinical interventions in the neonatal period to be studied instantaneously in the future.

The conventional assessment of preterm somatosensory functions using averaged cortical responses to electrical stimulation ignores the characteristic components of preterm somatosensory evoked responses (SERs). Our study aimed to systematically evaluate the occurrence and development of SERs after tactile stimulus in preterm infants. We analysed SERs performed during 45 electroencephalograms (EEGs) from 29 infants at the mean post-menstrual age of 30.7 weeks. Altogether 2,087 SERs were identified visually at single trial level from unfiltered signals capturing also their slowest components. We observed salient SERs with a high amplitude slow component at a high success rate after hand (95%) and foot (83%) stimuli. There was a clear developmental change in both the slow wave and the higher frequency components of the SERs. Infants with intraventricular haemorrhage (IVH; eleven infants) had initially normal SERs, but those with bilateral IVH later showed a developmental decrease in the ipsilateral SER occurrence after 30 weeks of post-menstrual age. Our study shows that tactile stimulus applied at bedside elicits salient SERs with a large slow component and an overriding fast oscillation, which are specific to the preterm period. Prior experimental research indicates that such SERs allow studying both subplate and cortical functions. Our present findings further suggest that they might offer a window to the emergence of neurodevelopmental sequalae after major structural brain lesions and, hence, an additional tool for both research and clinical neurophysiological evaluation of infants before term age.

Background Delayed brain function development in small-gestational-age (SGA) infants has been reported. We aimed to quantify rates of immature neonatal EEG patterns and their association with neurodevelopment in SGA full-term neonates. Methods Using a cohort design, 50 SGA (birthweight 3 h. Seventy-three of them were assessed at 2-years-old using Bayley-III-Scales. For EEG analysis, several segments of discontinuous/alternating EEG tracings were selected. Main outcomes measured: (1) Visual analysis (patterns of EEG maturity); (2) Power spectrum in δ, θ, α and β frequency bands; and (3) scores in motor, cognitive and language development. Results (1) SGA infants, compared to AGA, showed: (a) higher percentages of discontinuous EEG, both asynchrony and interhemispheric asymmetry, and bursts with delta-brushes, longer interburst-interval duration and more transients/hour; (b) lower relative power spectrum in δ and higher in α; and (c) lower scores on motor, language and cognitive neurodevelopment. (2) Asymmetry >5%, interburst-interval >5 s, discontinuity >11%, and bursts with delta-brushes >11% were associated with lower scores on Bayley-III. Conclusions In this prospective study, SGA full-term neonates showed high rates of immature EEG patterns. Low-birthweight and immaturity EEG were both correlated with low development scores.

Research using electroencephalography (EEG) as a measure of brain function and maturation has demonstrated links between cortical activity and cognitive processes during infancy and early childhood. The current study examines whether neonatal EEG is correlated with later atypical socioemotional behaviors or neurocognitive delays. Parental-report developmental assessments were administered to families with children ages 24 to 36 months who had previously participated in a neonatal EEG study (N = 129). Significant associations were found between neonatal EEG (higher frequencies in the frontal-polar, temporal, and parietal brain regions) and BITSEA ASD risk scores. Infants with lower EEG power in these brain areas were more likely to have higher risk of socio-emotional problems. When examining sex differences, significant links were found for males but not for females. These results demonstrate some promising associations between early neural biomarkers and later risk for atypical behaviors, which may shape early neurobehavioral development and could lead to earlier identification and intervention.

This study was aimed to assess electrophysiological brain activity in newborns of various gestational ages using electroencephalography (EEG). We summarized the data on the main EEG characteristics of premature infants and their dynamics and described the most common pathological EEG changes that can be identified at this age. We also discussed prognostic value of various neonatal EEG patterns (including their proportion and location), which allow verification of functional brain disorders at early stages. © 2019 ABV-Press Publishing House. All rights reserved. Russian Science Foundation, RSF Финансирование. Работа выполнена при финансовой поддержке гранта №16-18-10371 Российского научного фонда. Исследование прово-дится в рамках программы, поддержанной постановлением №211 Правительства Российской Федерации, соглашение №02.A03.21.0006. Financing. The study was funded by the grant No. 16-18-10 371 from the Russian Science Foundation. The study conducts within a program, supported by the resolution of the Russian Government No. 211, agreement No. 02.A03.21.0006.

EEG is the gold standard for seizure detection in the newborn infant, but EEG interpretation in the preterm group is particularly challenging; trained experts are scarce and the task of interpreting EEG in real-time is arduous. Preterm infants are reported to have a higher incidence of seizures compared to term infants. Preterm EEG morphology differs from that of term infants, which implies that seizure detection algorithms trained on term EEG may not be appropriate. The task of developing preterm specific algorithms becomes extra-challenging given the limited amount of annotated preterm EEG data available. This paper explores novel deep learning (DL) architectures for the task of neonatal seizure detection in preterm infants. The study tests and compares several approaches to address the problem: training on data from full-term infants; training on data from preterm infants; training on age-specific preterm data and transfer learning. The system performance is assessed on a large database of continuous EEG recordings of 575[Formula: see text]h in duration. It is shown that the accuracy of a validated term-trained EEG seizure detection algorithm, based on a support vector machine classifier, when tested on preterm infants falls well short of the performance achieved for full-term infants. An AUC of 88.3% was obtained when tested on preterm EEG as compared to 96.6% obtained when tested on term EEG. When re-trained on preterm EEG, the performance marginally increases to 89.7%. An alternative DL approach shows a more stable trend when tested on the preterm cohort, starting with an AUC of 93.3% for the term-trained algorithm and reaching 95.0% by transfer learning from the term model using available preterm data. The proposed DL approach avoids time-consuming explicit feature engineering and leverages the existence of the term seizure detection model, resulting in accurate predictions with a minimum amount of annotated preterm data.

Electroencephalography (EEG) is an important clinical tool for reviewing sleep-wake cycling in neonates in intensive care. Trace alternant (TA)-a characteristic pattern of EEG activity during quiet sleep in term neonates-is defined by alternating periods of short-duration, high-voltage activity (bursts) separated by lower-voltage activity (inter-bursts). This study presents a novel approach for detecting TA activity by first detecting the inter-bursts and then processing the temporal map of the bursts and inter-bursts. EEG recordings from 72 healthy term neonates were used to develop and evaluate performance of 1) an inter-burst detection method which is then used for 2) detection of TA activity. First, multiple amplitude and spectral features were combined using a support vector machine (SVM) to classify bursts from inter-bursts within TA activity, resulting in a median area under the operating characteristic curve (AUC) of 0.95 (95% confidence interval, CI: 0.93 to 0.98). Second, post-processing of the continuous SVM output, the confidence score, was used to produce a TA envelope. This envelope was used to detect TA activity within the continuous EEG with a median AUC of 0.84 (95% CI: 0.80 to 0.88). These results validate how an inter-burst detection approach combined with post processing can be used to classify TA activity. Detecting the presence or absence of TA will help quantify disruption of the clinically important sleep-wake cycle., 4 pages, to be appearing in upcoming 2020 EMBC Conference

Many preterm infants suffer from neural disorders caused by early birth complications. The detection of children with neurological risk is an important challenge. The electroencephalogram is an important technique for establishing long-term neurological prognosis. Within this scope, the goal of this study is to propose an automatic detection of abnormal preterm babies’ electroencephalograms (EEG). A corpus of 316 neonatal EEG recordings of 100 infants born after less than 35 weeks of gestation were preprocessed and a time series of standard deviation was computed. This time series was thresholded to detect Inter Burst Intervals (IBI). Temporal features were extracted from bursts and IBI. Feature selection was carried out with classification in one step so as to select the best combination of features in terms of classification performance. Two classifiers were tested: Multiple Linear Regressions and Support Vector Machines (SVM). Performance was computed using cross validations. Methods were validated on a corpus of 100 infants with no serious brain damage. The Multiple Linear Regression method shows the best results with a sensitivity of 86.11% ± 10.01%, a specificity of 77.44% ± 7.62% and an AUC (Area under the ROC curves) of 0.82 ± 0.04. An accurate detection of abnormal EEG for preterm infants is feasible. This study is a first step towards an automatic analysis of the premature brain, making it possible to lighten the physician’s workload in the future.

In this paper, we propose a new method, based on the nonlinear energy operator (NLEO), to automatically detect burst---suppression (B---S) patterns in multichannel newborn electroencephalograms (EEGs). The proposed approach consists of two algorithms: (1) per-brain region B---S detection and (2) global B---S detection. At first, B---S patterns are detected in each channel using NLEO. Average of NLEO values obtained for all the channels is then calculated to detect the presence of B---S patterns in each brain region. After local B---S detection, the global B---S detection algorithm classifies a sample-point as burst if most of regions are bursting. Otherwise, the sample-point is classified as suppression. The proposed method is validated using a database composed of multichannel EEG signals acquired from 6 neonates. The experimental results show that the proposed approach can detect bursts which occur locally and classify global B---S patterns with a very high accuracy of 98%.

Electroencephalography (EEG) is used in neonatal care to assess encephalopathy, seizure recognition and classification, to make epilepsy syndrome diagnoses and to assess the maturity of neonatal brain activity. A basic understanding of the EEG is very helpful in ensuring that clinicians gain as much information as possible from this helpful, non-invasive investigation. The neonatal EEG is complex and accurate reporting requires detailed clinical information to be provided on request forms. Even when this is provided EEG reports are frequently returned to the neonatal unit loaded with technical details, making it difficult for neonatal staff to fully understand them. This article reviews the basics of EEG, the changes seen with increasing gestational age, and changes seen in common pathologies. We also provide a structured approach to the interpretation of the neonatal EEG report, and discuss its role in prognostication. Amplitude integrated EEG is reviewed in our companion paper.

Background: Continuous EEG monitoring, in the form of amplitude-integrated (aEEG) or conventional EEG (cEEG), is used in the neonatal intensive care unit (NICU) to detect subclinical central nervous system pathologies, inform management, and prognosticate neurodevelopmental outcomes. To learn more about provider attitudes and current practices in Canada, we evaluated neurologist and neonatologist opinions regarding NICU EEG monitoring. Methods: A 15-item electronic questionnaire was distributed to 114 pediatric neurologists and 176 neonatologists working across 25 sites. Results: The survey was completed by 87 of 290 physicians. Continuous EEG monitoring is utilized by 97% of pediatric neurologists and 92% of neonatologists. Neurologists and neonatologists differ in their EEG monitoring preferences. For seizure detection and diagnosis of encephalopathy, significantly more neonatologists favor aEEG alone or in combination with cEEG, whereas most neurologists prefer cEEG (p = 0.047, 0.001). There is a significant difference in the perceived gaps in monitoring patients with cEEG between neonatologists (13% would monitor more) and neurologists (41% would monitor more) (p = 0.007). Half of all respondents (53%) reported that they would be interested in attending an education session on neonatal EEG monitoring. Conclusions: Canadian neurologists and neonatologists do not agree on the best monitoring approach for critically ill neonates. Furthermore, neonatologists perceive a smaller cEEG monitoring gap as compared with neurologists. However, many participants from both specialties would like to increase long-term EEG monitoring in the NICU setting. Facilitating access to EEG monitoring and enhancing education may help to address these needs.

Neonatal seizures are a common emergency in the neonatal intensive care unit (NICU). There are many questions yet to be answered regarding the temporal/spatial characteristics of seizures from different pathologies, response to medication, effects on neurodevelopment and optimal detection. The dataset presented in this descriptor contains EEG recordings from human neonates, the visual interpretation of the EEG by the human experts, supporting clinical data and codes to assist access. Multi-channel EEG was recorded from 79 term neonates admitted to the NICU at the Helsinki University Hospital. The median recording duration was 74 min (IQR: 64 to 96 min). The presence of seizures in the EEGs was annotated independently by three experts. An average of 460 seizures were annotated per expert in the dataset; 39 neonates had seizures and 22 were seizure free, by consensus. The dataset can be used as a reference set of neonatal seizures, in studies of inter-observer agreement and for the development of automated methods of seizure detection and other EEG analyses. Machine-accessible metadata file describing the reported data (ISA-Tab format)

Background Electroencephalography (EEG) monitoring is widely used in neonatal intensive care units (NICUs). However, conventional EEG report generation processes are time-consuming and labor-intensive. Therefore, an automatic, objective, and comprehensive pipeline for brain age estimation and EEG report conclusion prediction is urgently needed to assist clinician's decision-making. Methods We recruited patients who underwent EEG monitoring from the NICU at Children's Hospital of Fudan University from Jan. 2016 to Mar. 2018. A total of 1,851 subjects were enrolled, including the patient's conceptional age (CA) and the clinical EEG report conclusion (normal, slightly abnormal, moderately abnormal, or severely abnormal). A total of 1,591 subjects were used to generate predictive models and 260 were used as the validation dataset. We developed Auto-Neo-EEG (an automatic prediction system to assist clinical neonatal EEG report generation), including signal feature extraction, supervised machine learning realized by gradient boosted models, to estimate brain age and predict EEG report conclusion. Results The predicted results from the validation dataset were compared with the clinical observations to assess the performance. In the independent validation dataset, the model could achieve accordance 0.904 on estimating brain age for neonates with normal clinical EEG report conclusion, and differences between the predicted and observed brain age were strongly related with EEG report conclusion abnormality. Further, as for the EEG report conclusion prediction, the model could achieve area under the curve (AUC) of 0.984 for severely abnormal situations, and 0.857 for moderately abnormal ones. Conclusions The Auto-Neo-EEG has the high accuracy of estimating brain age and EEG report conclusion, which can potentially greatly accelerate the EEG report generation processes assist in clinical decision making.

Purpose The present study evaluated the risk factors for electroencephalographic (EEG)-confirmed seizures during the whole neonatal period in preterm and term neonates born in the province of Parma between January 2009 and December 2014. Methods We selected as cases the infants that presented EEG-confirmed neonatal seizures (NS). Two population controls for each case were matched by gestational age (GA), sex, hospital, and period of birth. Information on the mother, the pregnancy, the labor and delivery, and the neonates were taken from the Emilia-Romagna Certificate of Delivery Assistance database and from hospital charts and ICD-9-CM codes. Results and interpretation In the 6-year period of this study, 22 patients were recorded with NS. The association between at least one pregnancy complication and at least one neonatal complication, a low Apgar score, the need for resuscitation at birth, intraventricular hemorrhages (IVH) grades II–IV for preterm, and acute perinatal asphyxia/hypoxic–ischemic encephalopathy (HIE) for term infants were all statistically significant among cases. Neonates presenting these risk factors are more prone to develop NS and have to be strictly monitored.

Haemodynamic changes during neonatal transition increase the vulnerability of the preterm brain to injury. Real-time monitoring of brain function during this period would help identify the immediate impact of these changes on the brain. Neonatal EEG provides detailed real-time information about newborn brain function but can be difficult to interpret for non-experts; preterm neonatal EEG poses even greater challenges. An objective quantitative measure of preterm brain health would be invaluable during neonatal transition to help guide supportive care and ultimately protect the brain. Appropriate quantitative measures of preterm EEG must be calculated and care needs to be taken when applying the many techniques available for this task in the era of modern data science. This review provides valuable information about the factors that influence quantitative EEG analysis and describes the common pitfalls. Careful feature selection is required and attention must be paid to behavioural state given the variations encountered in newborn EEG during different states. Finally, the detrimental influence of artefacts on quantitative EEG analysis is illustrated.

In this chapter, the peculiar aspects of the normal neonatal EEG are discussed, alongside with the recording modalities and the characteristic and age-specific electroencephalographic physiological patterns of the newborn, from preterm birth to the end of the neonatal period. In the iconographic material the physiological markers of electrogenesis maturation have been highlighted; in the Appendix, the terms utilized to describe the neonatal EEG will be defined. The knowledge of normal EEG patterns is a prerequisite for the interpretation of the abnormal neonatal EEG.

The distinctive features of the normal neonatal EEG pattern have been described in the first part of this Manual. This chapter will be dedicated to the description of the most characteristic artifacts and the abnormal EEG findings in the neonatal age. Particular attention has been devoted to the iconographic material..Both EEG backgroud abnormalities and ictal epileptiform discharges are the milestones in the knowledge of abnormal neonatal electroencephalography. The caption of the figures will report the anamnestic, clinical, and instrumental data related to the clinical cases described, in order to underline and confirm the importance of a complete integration among clinical, neurophysiological, and neuroimaging data in the approach of newborns with neurological impairments.

Summary The aim of this study was to evaluate whether specific etiologies of neonatal seizures have distinct ictal electroclinical features. A systematic review of English articles using the PubMed database since 2004 (last update 9/26/16). Search terms included text words and Medical Subject Headings (MeSH) terms related to neonatal seizures. Eligible articles included reports of neonates with seizures with a full description of seizure semiology and electroclinical findings. Independent extraction of data was performed by 2 authors using predefined data fields, including study quality indicators. Data were collected for every individual patient described in the articles. The dataset was analyzed with the Fisher exact test. The initial search led to 8507 titles; using filters, 2910 titles and abstracts were identified, with 177 full texts selected to be read. Fifty‐seven studies were included in the analysis with 151 neonates (37.7 male and 62.9% term). Genetic etiologies (51%) and sequential seizures (41.1%) predominated in this sample and hypoxic‐ischemic encephalopathy (HIE) accounted for only 4%. The low prevalence of HIE observed was probably due to a publication bias. A significant association was found between etiology and seizure type: hemorrhage with autonomic seizures (P = 0.003), central nervous system (CNS) infection and stroke with clonic seizures (P = 0.042, P

This paper describes the design considerations and performance evaluation of a novel high-performance instrumentation, termed the neoEEG Board, able to record neonatal EEG signals with high precision. This prototype EEG recording modality is proposed as an alternative to the currently utilised in NICU state-of-the-art device, the CFM™. Among other characteristics, the neoEEG Board is modular, portable, wearable, wireless and battery operated. It offers 8 channels per module, each providing independent spectral analysis from 0.5 to 100 Hz, with a novel topology for variable bandwidth. The proposed instrument’s noise figure has been measured and found to be equal to 3 nV / Hz , allowing it to resolve very weak signals down to 6 nV p - p . In addition it provides high CMRR (>130 dB), wide gain range (74 dB to 95.5 dB), DC-offset tolerance up to ±35 mV, sampling rate per channel up to 32 kHz and supports wireless data transmission up to 2 Mbits / s .

Clinical neurophysiologists often find it difficult to recall rare EEG patterns despite the fact that this information could be diagnostic and help with treatment intervention. Traditional search methods may take time to retrieve the archived EEGs that could provide the meaning or cause of the specific pattern which is not acceptable as time can be critical for sick neonates. If neurophysiologists had the ability to quickly recall similar patterns, the prior occurrence of the pattern may help make an earlier diagnosis. This paper presents a system that may be used to assist a clinical neurophysiologist in the recall of neonatal EEG patterns. The proposed system consists of an alignment technique followed by an approximate nearest neighbour search algorithm called locality sensitive hashing. The system was tested on six different neonatal EEG pattern types with 430 events in total and the results are presented in this paper.

Purpose Many neonates undergo electroencephalogram (EEG) monitoring to identify and manage acute symptomatic seizures. Information about brain function contained in the EEG background data may also help predict neurobehavioral outcomes. For EEG background features to be useful as prognostic indicators, the interpretation of these features must be standardized across electroencephalographers. We aimed at determining the interrater and intrarater agreement among electroencephalographers interpreting neonatal EEG background patterns. Methods Five neonatal electroencephalographers reviewed 5-to-7.5-minute epochs of EEG from full-term neonates who underwent continuous conventional EEG monitoring. The EEG assessment tool used to classify background patterns was based on the American Clinical Neurophysiology Society's guideline for neonatal EEG terminology. Interrater and intrarater agreement were measured using Kappa coefficients. Results Interrater agreement was consistently highest for voltage (binary: substantial, kappa = 0.783; categorical: moderate, kappa = 0.562), seizure presence (fair-substantial; kappa = 0.375-0.697), continuity (moderate; kappa = 0.481), burst voltage (moderate; kappa = 0.574), suppressed background presence (moderate-substantial; kappa = 0.493-0.643), delta activity presence (fair-moderate; kappa = 0.369-0.432), theta activity presence (fair-moderate; kappa = 0.347-0.600), presence of graphoelements (fair; kappa = 0.381), and overall impression (binary: moderate, kappa = 0.495; categorical: fair-moderate, kappa = 0.347, 0.465). Agreement was poor or inconsistent for all other patterns. Intrarater agreement was variable, with highest average agreement for voltage (binary: substantial, kappa = 0.75; categorical: substantial, kappa = 0.714) and highest consistent agreement for continuity (moderate-substantial; kappa = 0.43-0.67) and overall impression (moderate-substantial; kappa = 0.42-0.68). Conclusions This study demonstrates substantial variability in neonatal EEG background interpretation across electroencephalographers, indicating a need for educational and technological strategies aimed at improving performance.

The aim of this feasibility study is to experimentally verify the detection of changes of sleep stages in neonates with our proposed semi-automated approach using k-NN classification in comparison with a fully automated approach using simple k-means cluster analysis for classification (instead of k-NN). Our semi-automatic approach uses the k-NN classifier trained on etalons (prototypes) created by semi-automated etalons extraction (k-means for etalons suggestion and expert-in-the-loop for verification). Both methods are compared to labelling of sleep stages made by an experienced physician Dr. K. Paul. An EEG recording of full-term neonate is chosen from group of EEG recordings: full-term and preterm neonates recorded from eight electrodes positioned in standard conditions. The EEG recording is digitally preprocessed by mean-removal filter (no other filters are applied) and segmented adaptively. For each segment, 24 features are extracted and send to two classification processes: k-means and k-NN. Classified segments are plotted in temporal profiles (class membership in time) that are analysed for sleep stages using our method of creating a single detection curve from all channels and a threshold is applied on this detection curve to detect sleep stages.

Highlights • Seizure detection algorithm (SDA) validated on unseen, unedited EEG of 70 neonates. • Results at SDA sensitivity settings of 0.5–0.3 acceptable for clinical use. • Seizure detection rate of 52.6–75.0%, false detection rate 0.04–0.36 FD/h., 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 0.04–0.36 FD/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.

Objective This work presents a novel automated system to classify the severity of hypoxic–ischemic encephalopathy (HIE) in neonates using EEG. Methods A cross disciplinary method is applied that uses the sequences of short-term features of EEG to grade an hour long recording. Novel post-processing techniques are proposed based on majority voting and probabilistic methods. The proposed system is validated with one-hour-long EEG recordings from 54 full term neonates. Results An overall accuracy of 87% is achieved. The developed grading system has improved both the accuracy and the confidence/quality of the produced decision. With a new label ‘unknown’ assigned to the recordings with lower confidence levels an accuracy of 96% is attained. Conclusion The statistical long-term model based features extracted from the sequences of short-term features has improved the overall accuracy of grading the HIE injury in neonatal EEG. Significance The proposed automated HIE grading system can provide significant assistance to healthcare professionals in assessing the severity of HIE. This represents a practical and user friendly implementation which acts as a decision support system in the clinical environment. Its integration with other EEG analysis algorithms may improve neonatal neurocritical care.

In this paper, an algorithm for epileptic seizure detection using empirical mode decomposition (EMD) method is proposed. The EMD technique decomposes EEG signals into intrinsic mode functions (IMF). Further, statistical features representing seizure and non-seizure EEG activities were computed over these IMFs. The useful features were selected using t-test score and fed to artificial neural network (ANN) classifier to recognizing seizure and non-seizure EEG. The scalp EEG signals recorded from neonatal subjects are used to test the efficacy of the proposed algorithm.

CORRIGENDUM: DOI: 10.1093/cercor/bhy100 Published: APR 2019 Preterm birth is the greatest risk factor for lifelong neurocognitive deficits, globally. The effect of prematurity on early cortical network function has, however, remained poorly understood. Here, we developed a novel methodology that allows reliable assessment of functional connectivity in neonatal brain activity at millisecond and multisecond scales in terms of cortical phase and amplitude correlations, respectively. We measured scalp electroencephalography at term-equivalent age in infants exposed to very early prematurity as well as in healthy controls. We found that newborn cortical activity organizes into multiplex networks that differ significantly between vigilance states. As compared with healthy control infants, prematurity was found to cause frequency-specific patterns of dysconnectivity in cortical network, changes that were distinct for networks of phase and amplitude correlations. Neuroanatomically, the most prominent markers of prematurity were found in connections involving the frontal regions. Phase synchrony in frontally connected networks was correlated with newborn neurological performance, suggesting the first measure of cortical functional coupling that correlates with neurological performance in human infant.

© 2017 by the authors. Automated analysis of the electroencephalographic (EEG) data for the brain monitoring of preterm infants has gained attention in the last decades. In this study, we analyze the complexity of neonatal EEG, quantified using multiscale entropy. The aim of the current work is to investigate how EEG complexity evolves during electrocortical maturation and whether complexity features can be used to classify sleep stages. First, we developed a regression model that estimates the postmenstrual age (PMA) using a combination of complexity features. Then, these features are used to build a sleep stage classifier. The analysis is performed on a database consisting of 97 EEG recordings from 26 prematurely born infants, recorded between 27 and 42 weeks PMA. The results of the regression analysis revealed a significant positive correlation between the EEG complexity and the infant's age. Moreover, the PMA of the neonate could be estimated with a root mean squared error of 1.88 weeks. The sleep stage classifier was able to discriminate quiet sleep from nonquiet sleep with an area under the curve (AUC) of 90%. These results suggest that the complexity of the brain dynamics is a highly useful index for brain maturation quantification and neonatal sleep stage classification. ispartof: ENTROPY vol:19 issue:10 status: published

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., Personalized detector of neonatal seizures through on-the-fly unsupervised adaptation of a generic model improves detection accuracy.

Clinical evaluation of electroencephalogram (EEG) is important for understanding and monitoring the electrical activity present in the brain. In collusion with engineering advances, the movement towards portable, rapid and low-cost EEG monitoring is growing. This will allow a greater availability of monitoring technologies for assessing brain function and health in disadvantaged communities. This paper presents an alternative method for interpreting neonatal brain health in real-time via the sonification of EEG on a smartphone. The paper discusses the implementation of the real-time EEG sonification using a phase vocoder and shows how the method is achievable using low-cost smartphone technologies with energy efficient algorithms.

The aim of this study is the detection of changes in sleep stages in EEG recordings in full-term and preterm newborns. We use a k-NN algorithm as a method of classification. The novelty of our approach lies in semi-automatic etalon (prototype) selection with combination of temporal analysis for sleep stages detection. The semi-automated etalon extraction includes the k-means algorithm for etalons suggestion and an expert-in-the-loop for verification of these etalons. The semi-automated approach improves significantly the time spent on the etalon selection (extraction) by the expert. The whole procedure of EEG signal processing consists of adaptive segmentation, feature extraction, semi-automatic etalon selection using k-means and expert-in-the-loop, classification using k-NN algorithm and temporal profile analysis that is able to detect the neonatal sleep stages for the full-term and even for the preterm neonates, which makes it a unique detection method.

In this paper, we have adapted a spike correlation (SC) method of neonatal EEG seizure detection, so that it can be directly incorporated into an SVM-based algorithm. To this end, we estimate several features based on the analysis of the smoothed non-linear energy operator (SNLEO). SNLEO features alone resulted in a median AUC of 0.963 (IQR 0.919-0.985). This AUC was significantly higher than with the original SVM-based method (p=0.024). The SNLEO method was significantly improved by incorporating a selected number of features from the SVM-based detector (p=0.002). Median AUC with this feature set was 0.981 (IQR 0.942-0.994). This study confirms, that incorporating SNLEO features adapted from the SC method significantly improve the performance of an SVM-based neonatal EEG seizure detector.

Clinical evaluation of electroencephalogram (EEG) is essential for monitoring the electrical activity present in the brain. In collusion with engineering advances, the movement towards portable, rapid and low-cost EEG acquisition and monitoring is growing. A low-cost and portable system for neonatal EEG is presented in this paper that aims to improve signal quality and robustness, while decreasing the preparation time and efforts required to complete a routine EEG recording. Several novel designs of dry, wet, active and passive electrodes are presented and compared with the standard EEG acquisition method using objective tests and subjective assessment by an epileptologist. It is shown that sufficient quality is achievable using dry setups, such as microneedle electrodes, with minimal patient preparation for the acquisition of clinical grade recordings.

Objectives: To measure changes in the visual interpretation of the EEG by the human expert for neonatal seizure detection when reducing the number of recording electrodes. Methods: EEGs were recorded from 45 infants admitted to the neonatal intensive care unit (NICU). Three experts annotated seizures in EEG montages derived from 19, 8 and 4 electrodes. Differences between annotations were assessed by comparing intra-montage with inter-montage agreement (K). Results: Three experts annotated 4464 seizures across all infants and montages. The inter-expert agreement was not significantly altered by the number of electrodes in the montage (p = 0.685, n = 43). Reducing the number of EEG electrodes altered the seizure annotation for all experts. Agreement between the 19-electrode montage (K-19,K-19 = 0.832) was significantly higher than the agreement between 19 and 8-electrode montages (dK = 0.114; p

OBJECTIVE: To assess interrater agreement based on majority voting in visual scoring of neonatal seizures. METHODS: An online platform was designed based on a multicentre seizure EEG-database. Consensus decision based on 'majority voting' and interrater agreement was estimated using Fleiss' Kappa. The influences of different factors on agreement were determined. RESULTS: 1919 Events extracted from 280h EEG of 71 neonates were reviewed by 4 raters. Majority voting was applied to assign a seizure/non-seizure classification. 44% of events were classified with high, 36% with moderate, and 20% with poor agreement, resulting in a Kappa value of 0.39. 68% of events were labelled as seizures, and in 46%, all raters were convinced about electrographic seizures. The most common seizure duration was

Objective: To develop a method for automated neonatal sleep state classification based on EEG that can be applied over a wide range of age. Methods: We collected 231 EEG recordings from 67 infants between 24 and 45 weeks of postmenstrual age. Ten minute epochs of 8 channel polysomnography (N = 323) from active and quiet sleep were used as a training dataset. We extracted a set of 57 EEG features from the time, frequency, and spatial domains. A greedy algorithm was used to define a reduced feature set to be used in a support vector machine classifier. Results: Performance tests showed that our algorithm was able to classify quiet and active sleep epochs with 85% accuracy, 83% sensitivity, and 87% specificity. The performance was not substantially lowered by reducing the epoch length or EEG channel number. The classifier output was used to construct a novel trend, the sleep state probability index, that improves the visualisation of brain state fluctuations. Conclusions: A robust EEG-based sleep state classifier was developed. It performs consistently well across a large span of postmenstrual ages. Significance: This method enables the visualisation of sleep state in preterm infants which can assist clinical management in the neonatal intensive care unit. (C) 2017 International Federation of Clinical Neurophysiology. Published by Elsevier Ireland Ltd. All rights reserved.

PURPOSE Neonatal seizures are a common neurologic diagnosis in neonatal intensive care units, occurring in approximately 14,000 newborns annually in the United States. Although the only reliable means of detecting and treating neonatal seizures is with an electroencephalography (EEG) recording, many neonates do not receive an EEG or experience delays in getting them. Barriers to obtaining neonatal EEGs include (1) lack of skilled EEG technologists to apply conventional wet electrodes to delicate neonatal skin, (2) poor signal quality because of improper skin preparation and artifact, and (3) extensive time needed to apply electrodes. Dry sensors have the potential to overcome these obstacles but have not previously been evaluated on neonates. METHODS Sequential and simultaneous recordings with wet and dry sensors were performed for 1 hour on 27 neonates from 35 to 42.5 weeks postmenstrual age. Recordings were analyzed for correlation and amplitude and were reviewed by neurophysiologists. Performance of dry sensors on simulated vernix was examined. RESULTS Analysis of dry and wet signals showed good time-domain correlation (reaching >0.8), given the nonsuperimposed sensor positions and similar power spectral density curves. Neurophysiologist reviews showed no statistically significant difference between dry and wet data on most clinically relevant EEG background and seizure patterns. There was no skin injury after 1 hour of dry sensor recordings. In contrast to wet electrodes, impedance and electrical artifact of dry sensors were largely unaffected by simulated vernix. CONCLUSIONS Dry sensors evaluated in this study have the potential to provide high-quality, timely EEG recordings on neonates with less risk of skin injury.

The goal of this paper is to describe a robust artifact removal (RAR) method, an automatic sequential procedure which is capable of removing short-duration, high-amplitude artifacts from long-term neonatal EEG recordings. Such artifacts are mainly caused by movement activity, and have an adverse effect on the automatic processing of long-term sleep recordings. The artifacts are removed sequentially in short-term signals using independent component analysis (ICA) transformation and wavelet denoising. In order to gain robustness of the RAR method, the whole EEG recording is processed multiple times. The resulting tentative reconstructions are then combined. We show results in a data set of signals from ten healthy newborns. Those results prove, both qualitatively and quantitatively, that the RAR method is capable of automatically rejecting the mentioned artifacts without changes in overall signal properties such as the spectrum. The method is shown to perform better than either the wavelet-enhanced ICA or the simple artifact rejection method without the combination procedure.

1.Department of Children’s Clinical Neurophysiology, Helsinki University Central Hospital, Helsinki, Finland2.Department of Neurological Sciences, University of Helsinki, Helsinki, FinlandCorrespondenceS Vanhatalo, Department of Clinical Neurophysiol-ogy, Children’s Hospital, Helsinki University CentralHospital, PO Box 280, FIN-00029 HUS, Helsinki, Fin-land.Email: sampsa.vanhatalo@helsinki.fiReceived15 March 2012; accepted 2 May 2012.DOI:10.1111/j.1651-2227.2012.02724.x

Objective The accuracy of electroencephalography source reconstruction largely depends on the accuracy of head model, which, in turn, is dependent on the geometry and electrical properties of head tissues. Methods Based on a MR/CT coregistered images of one neonate we created a highly realistic 6 compartment head model. using a state of art finite element method, we performed numerical simulations to investigate localization errors in dipole source position, orientation and magnitude caused by CSF and fontanel exclusion and GM/WM distinction. Results Our results showed that exclusion of CSF from the head model caused source localization errors up to 7.5 mm. GM/WM distinction affected widely all sources with localization errors up to 4.3 mm. Exclusion of the fontanels led to localization errors of less than 4.9 mm specifically for sources located in the areas beneath the fontanels. The majority of sources showed orientation errors up to 24.6°, 19.2° and 17.6°, caused by CSF exclusion, GM/WM distinction and fontanel exclusion, respectively. Discussion Our results systematically emphasized the importance of the inclusion of the CSF as a highly conductive layer and GM/WM distinction in head model construction. The exclusion of fontanels also led to substantial local localization errors for sources located in the areas beneath the fontanels. Conclusion In this study we investigated the effect of different head compartments in neonatal head models on EEG source analysis. Significance Our findings have practical implications for a better understanding of the importance of inaccuracies in head model and their impact on localization of brain electrical activity in neonates.

Neonatal electroencephalography (EEG) presents a challenge due to its difficult interpretation that differs significantly from interpretation in older children and adolescents. Also, from the technological point of view, it is more difficult to perform and is not a standard procedure in all neonatal intensive care units (NICUs). During recent years, long-term cerebral function monitoring by the means of amplitude-integrated EEG (aEEG) has become popular in NICUs because it is easy to apply, allows real-time interpretation by the neonatologist treating the newborn, and has predictive value for outcome. On the other side, to record conventional EEG (cEEG), which is still considered the gold standard of neonatal EEG, the EEG technician should not only be well trained in performing neonatal EEG but also has to adapt to suboptimal working conditions. These issues need to be understood when approaching the neonatal cEEG in NICU and the main structure of the article is dedicated to this technique. The authors discuss the benefits of the digitalization and its positive effects on the improvement of NICU recording. The technical aspects as well as the standards for cEEG recording are described, and a section is dedicated to possible artifacts. Thereafter, alternative and concomitant use of aEEG and its benefits are briefly discussed. At the end there is a section that presents a review of our own cEEG and aEEG recordings that were chosen as the most frequently encountered patterns according to Consensus statement on the use of EEG in the intensive care unit.

Objective This study discusses an appropriate framework to measure system performance for the task of neonatal seizure detection using EEG. The framework is used to present an extended overview of a multi-channel patient-independent neonatal seizure detection system based on the Support Vector Machine (SVM) classifier. Methods The appropriate framework for performance assessment of neonatal seizure detectors is discussed in terms of metrics, experimental setups, and testing protocols. The neonatal seizure detection system is evaluated in this framework. Several epoch-based and event-based metrics are calculated and curves of performance are reported. A new metric to measure the average duration of a false detection is proposed to accompany the event-based metrics. A machine learning algorithm (SVM) is used as a classifier to discriminate between seizure and non-seizure EEG epochs. Two post-processing steps proposed to increase temporal precision and robustness of the system are investigated and their influence on various metrics is shown. The resulting system is validated on a large clinical dataset of 267 h. Results In this paper, it is shown how a complete set of metrics and a specific testing protocol are necessary to extensively describe neonatal seizure detection systems, objectively assess their performance and enable comparison with existing alternatives. The developed system currently represents the best published performance to date with an ROC area of 96.3%. The sensitivity and specificity were ∼90% at the equal error rate point. The system was able to achieve an average good detection rate of ∼89% at a cost of 1 false detection per hour with an average false detection duration of 2.7 min. Conclusions It is shown that to accurately assess the performance of EEG-based neonatal seizure detectors and to facilitate comparison with existing alternatives, several metrics should be reported and a specific testing protocol should be followed. It is also shown that reporting only event-based metrics can be misleading as they do not always reflect the true performance of the system. Significance This is the first study to present a thorough method for performance assessment of EEG-based seizure detection systems. The evaluated SVM-based seizure detection system can greatly assist clinical staff, in a neonatal intensive care unit, to interpret the EEG.

Introduction Continuous EEG monitoring provides valuable diagnostic and prognostic information for critically ill neonates that are at high risk of adverse neurological sequelae. The EEG of a developing brain is unique. The parameters used to monitor brain electrophysiological functions in neonates are different from fully mature brains. The EEG report should contain all these essential parameters. Consensus guidelines were published in 2013(1) to standardize the neonatal EEG reports for neurophysiologist, bedside physicians, and clinical researchers. In this study, we compared our neonatal EEG reports to consensus guidelines and attempted to modify it to include all clinically relevant information. Methods We retrospectively reviewed EEG reports of ten (10) neonates that underwent EEG monitoring at Duke Neonatal ICU from March 2017 to June 2017. We compared these reports to consensus guideline published in 2013. We then created a new standardized neonatal EEG report. It included all of the parameters suggested in the guidelines such as characteristics of background activity, awake and sleep state, normal graphoelements, EEG transient patterns and seizure burden. The updated EEG template was implemented in July 2017. We conducted another chart review from September 2017 to November 2017 for ten (10) more EEG reports. We compared the results of both chart reviews. Results From the consensus statement, we identified 20 parameters that were deemed essential for a neonatal EEG report The first chart review from March 2017 to June 2017 of ten patient suggested that majority of reports were inadequate or missing critical information. Out of 20 parameters, only three were regularly documented. After three months of implementing the updated EEG report, the quality of documentation improved. Out of 20 parameters, 18 were consistently documented (100%). One parameter was documented 80% of the time, and only one parameter was reported 20% of the time. Conclusion Our chart review suggested documentation for neonatal EEG reports was lagging behind what was recommended in the consensus report. We made a template in the electronic health record to include all of the important parameters suggested by ACNS guidelines. On a follow-up chart review we noted a marked improvement in our documentation of neonatal EEGs. The standardize EEG reports for neonates will improve patient care, caregiver communication, and future clinical research.The neonatal EEG template made can be used in other institutions to achieve similar results.

Aim: To investigate factors that influenced parental consent/non-consent in a non-therapeutic electroencephalogram (EEG) study in healthy newborns. Methods: Parents of healthy newborns were approached to participate in a neonatal EEG study within 36 h of birth. The rationale and risks/benefits of the study were explained. Any concerns were discussed, and detailed information about the EEG study was provided in the consent form. In the case of refusing/withdrawing consent, an informal interview was used to investigate the reasons, which were subsequently analysed and grouped according to the four principles of the consent process. Results: A total of 123 parents were included in the study. Parental consent was obtained in 72/123 (59%) cases, 10/123 (8%) parents subsequently withdrew their consent and 41/123 (33%) parents refused to participate in the study. Consent was more likely if both parents were present (p