Detecting bursts in the EEG of very and extremely premature infants using a multi-feature approach

Early EEG-burst sharpness and 2-year disability in extremely preterm infants

BACKGROUND

Automated computational measures of EEG have the potential for large-scale application. We hypothesised that a predefined measure of early EEG-burst shape (increased burst sharpness) could predict neurodevelopmental impairment (NDI) and mental developmental index (MDI) at 2 years of age over-and-above that of brain ultrasound.

METHODS

We carried out a secondary analysis of data from extremely preterm infants collected for an RCT (SafeBoosC-II). Two hours of single-channel cross-brain EEG was used to analyse burst sharpness with an automated algorithm. The co-primary outcomes were moderate-or-severe NDI and MDI. Complete data were available from 58 infants. A predefined statistical analysis was adjusted for GA, sex and no, mild-moderate, and severe brain injury as detected by cranial ultrasound.

RESULTS

Nine infants had moderate-or-severe NDI and the mean MDI was 87 ± 17.3 SD. The typical burst sharpness was low (negative values) and varied relatively little (mean -0.81 ± 0.11 SD), but the odds ratio for NDI was increased by 3.8 (p = 0.008) and the MDI was reduced by -3.2 points (p = 0.14) per 0.1 burst sharpness units increase (+1 SD) in the adjusted analysis.

CONCLUSION

This study confirms the association between EEG-burst measures in preterm infants and neurodevelopment in childhood. Importantly, this was by a priori defined analysis.

IMPACT

A fully automated, computational measure of EEG in the first week of life was predictive of neurodevelopmental impairment at 2 years of age. This confirms many previous studies using expert reading of EEG. Only single-channel EEG data were used, adding to the applicability. EEG was recorded by several different devices thus this measure appears to be robust to differences in electrodes, amplifiers and filters. The likelihood ratio of a positive EEG test, however, was only about 2, suggesting little immediate clinical value.

Quantitative analysis of high-frequency activity in neonatal EEG

OBJECTIVE

To determine the presence and potential utility of independent high-frequency activity recorded from scalp electrodes in the electroencephalogram (EEG) of newborns.

METHODS

We compare interburst intervals and continuous activity at different frequencies for EEGs retrospectively recorded at 256 Hz from 4 newborn groups: 1) 36 preterms (<32 weeks' gestational age, GA); 2) 12 preterms (32-37 weeks' GA); 3) 91 healthy full terms; 4) 15 full terms with hypoxic-ischemic encephalopathy (HIE). At 4 standard frequency bands (delta, 0.5-3 Hz; theta, 3-8 Hz; alpha, 8-15 Hz; beta, 15-30 Hz) and 3 higher-frequency bands (gamma1, 30-48 Hz; gamma2, 52-99 Hz; gamma3, 107-127 Hz), we compared power spectral densities (PSDs), quantitative features, and machine learning model performance. Feature selection and further machine learning methods were performed on one cohort.

RESULTS

We found significant (P < 0.01) differences in PSDs, quantitative analysis, and machine learning modelling at the higher-frequency bands. Machine learning models using only high-frequency features performed best in preterm groups 1 and 2 with a median (95% confidence interval, CI) Matthews correlation coefficient (MCC) of 0.71 (0.12-0.88) and 0.66 (0.36-0.76) respectively. Interburst interval-detector models using both high- and standard-bandwidths produced the highest median MCCs in all four groups. High-frequency features were largely independent of standard-bandwidth features, with only 11/84 (13.1%) of correlations statistically significant. Feature selection methods produced 7 to 9 high-frequency features in the top 20 feature set.

CONCLUSIONS

This is the first study to identify independent high-frequency activity in newborn EEG using in-depth quantitative analysis. Expanding the EEG bandwidths of analysis has the potential to improve both quantitative and machine-learning analysis, particularly in preterm EEG.

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.

Early brain activity: Translations between bedside and laboratory

Neural activity is both a driver of brain development and a readout of developmental processes. Changes in neuronal activity are therefore both the cause and consequence of neurodevelopmental compromises. Here, we review the assessment of neuronal activities in both preclinical models and clinical situations. We focus on issues that require urgent translational research, the challenges and bottlenecks preventing translation of biomedical research into new clinical diagnostics or treatments, and possibilities to overcome these barriers. The key questions are (i) what can be measured in clinical settings versus animal experiments, (ii) how do measurements relate to particular stages of development, and (iii) how can we balance practical and ethical realities with methodological compromises in measurements and treatments.

Electroencephalographic studies in growth-restricted and small-for-gestational-age neonates

Foetal growth restriction (FGR) and being born small for gestational age (SGA) are associated with neurodevelopmental delay. Early diagnosis of neurological damage is difficult in FGR and SGA neonates. Electroencephalography (EEG) has the potential as a tool for the assessment of brain development in FGR/SGA neonates. In this review, we analyse the evidence base on the use of EEG for the assessment of neonates with FGR or SGA. We found consistent findings that FGR/SGA is associated with measurable changes in the EEG that present immediately after birth and persist into childhood. Early manifestations of FGR/SGA in the EEG include changes in spectral power, symmetry/synchrony, sleep-wake cycling, and the continuity of EEG amplitude. Later manifestations of FGR/SGA into infancy and early childhood include changes in spectral power, sleep architecture, and EEG amplitude. FGR/SGA infants had poorer neurodevelopmental outcomes than appropriate for gestational age controls. The EEG has the potential to identify FGR/SGA infants and assess the functional correlates of neurological damage. IMPACT: FGR/SGA neonates have significantly different EEG activity compared to AGA neonates. EEG differences persist into childhood and are associated with adverse neurodevelopmental outcomes. EEG has the potential for early identification of brain impairment in FGR/SGA neonates.

Deep Learning for EEG Seizure Detection in Preterm Infants

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.

Mathematical Analysis of EEG Concordance in Preterm Twin Infants

PURPOSE

Preterm twins are at higher risk of neurodisability than preterm singletons, with monochorionic-diamniotic (MCDA) twins at higher risk than dichorionic-diamniotic (DCDA) twins. The impact of genetic influences on EEG concordance in preterm twins <32 weeks of gestational age is not established. This study aims to investigate EEG concordance in preterm MCDA and dichorionic-diamniotic twins during maturation.

METHODS

Infants <32 weeks of gestational age had multichannel EEG recordings for up to 72 postnatal hours, with repeat recordings at 32 and 35 weeks of postmenstrual age. Twin pairs had synchronous recordings. Mathematical EEG features were generated to represent EEG power, discontinuity, and symmetry. Intraclass correlations, while controlling for gestational age, estimated similarities within twins.

RESULTS

EEGs from 10 twin pairs, 4 MCDA and 6 dichorionic-diamniotic pairs, and 10 age-matched singleton pairs were analyzed from a total of 36 preterm infants. For MCDA twins, 17 of 22 mathematical EEG features had significant (>0.6; P < 0.05) intraclass correlations at one or more time points, compared with 2 of 22 features for DCDA twins and 0 of 22 for singleton pairs. For MCDA twins, all 10 features of discontinuity and all four features of symmetry were significant at one or more time-points. Three features of the MCDA twins (spectral power at 3-8 Hz, EEG skewness at 3-15 Hz, and kurtosis at 3-15 Hz) had significant intraclass correlations over all three time points.

CONCLUSIONS

Preterm twin EEG similarities are subtle but clearly evident through mathematical analysis. MCDA twins showed stronger EEG concordance across different postmenstrual ages, thus confirming a strong genetic influence on preterm EEG activity at this early development stage.

Multiparametric EEG analysis of brain network dynamics during neonatal seizures

BACKGROUND

One of the most challenging issues in paediatric neurology is the diagnosis of neonatal seizures, whose delayed treatment may affect the neurodevelopment of the newborn. Formulation of the correct diagnosis is conditioned by the high number of perceptually or automatically detected false positives.

NEW METHOD

New methodologies are proposed to assess neonatal seizures trend over time. Our approach is based on the analysis of standardized trends of two properties of the brain network: the Synchronizabilty (S) and the degree of phase synchronicity given by the Circular Omega Complexity (COC). Qualitative and quantitative methods based on network dynamics allow differentiating seizure events from interictal periods and seizure-free patients.

RESULTS

The methods were tested on a public dataset of labelled neonatal seizures. COC shows significant differences among seizure and non-seizure events (p-value <0.001, Cohen's d 0.86). Combining S and COC in standardized temporal instants provided a reliable description of the physiological behaviour of the brain's network during neonatal seizures.

COMPARISON WITH EXISTING METHOD(S)

Few of the existing network methods propose an operative way for carrying their analytical approach into the diagnostic process of neonatal seizures. Our methods offer a simple representation of brain network dynamics easily implementable and understandable also by less experienced staff.

CONCLUSIONS

Our findings confirm the usefulness of the evaluation of brain network dynamics over time for a better understanding and interpretation of the complex mechanisms behind neonatal seizures. The proposed methods could also reliably support existing seizure detectors as a post-processing step in doubtful cases.

Back to basics: the neuronal substrates and mechanisms that underlie the electroencephalogram in premature neonates

Electroencephalography is the only clinically available technique that can address the premature neonate normal and pathological functional development week after week. The changes in the electroencephalogram (EEG) result from gradual structural and functional modifications that arise during the last trimester of pregnancy. Here, we review the structural changes over time that underlie the establishment of functional immature neural networks, the impact of certain anatomical specificities (fontanelles, connectivity, etc.) on the EEG, limitations in EEG interpretation, and the utility of high-resolution EEG (HR-EEG) in premature newborns (a promising technique with a high degree of spatiotemporal resolution). In particular, we classify EEG features according to whether they are manifestations of endogenous generators (i.e. theta activities that coalesce with a slow wave or delta brushes) or come from a broader network. Furthermore, we review publications on EEG in premature animals because the data provide a better understanding of what is happening in premature newborns. We then discuss the results and limitations of functional connectivity analyses in premature newborns. Lastly, we report on the magnetoelectroencephalographic studies of brain activity in the fetus. A better understanding of complex interactions at various structural and functional levels during normal neurodevelopment (as assessed using electroencephalography as a benchmark method) might lead to better clinical care and monitoring for premature neonates.

Detection of Transient Bursts in the EEG of Preterm Infants using Time-Frequency Distributions and Machine Learning

Short-duration bursts of spontaneous activity are important markers of maturation in the electroencephalogram (EEG) of premature infants. This paper examines the application of a feature-less machine learning approach for detecting these bursts. EEGs were recorded over the first 3 days of life for infants with a gestational age below 30 weeks. Bursts were annotated on the EEG from 36 infants. In place of feature extraction, the time-series EEG is transformed into a time-frequency distribution (TFD). A gradient boosting machine is then trained directly on the whole TFD using a leave-one-out procedure. TFD kernel parameters, length of the Doppler and lag windows, are selected within a nested cross-validation procedure during training. Results indicate that detection performance is sensitive to Doppler-window length but not lag-window length. Median area under the receiver operator characteristic for detection is 0.881 (inter-quartile range 0.850 to 0.913). Examination of feature importance highlights a critical wideband region <15 Hz in the TFD. Burst detection methods form an important component in any fully-automated brain-health index for the vulnerable preterm infant.

Identifying tracé alternant activity in neonatal EEG using an inter-burst detection approach

Electroencephalography (EEG) is an important clinical tool for reviewing sleep-wake cycling in neonates in intensive care. Tracé 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.

Machine learning without a feature set for detecting bursts in the EEG of preterm infants

Deep neural networks enable learning directly on the data without the domain knowledge needed to construct a feature set. This approach has been extremely successful in almost all machine learning applications. We propose a new framework that also learns directly from the data, without extracting a feature set. We apply this framework to detecting bursts in the EEG of premature infants. The EEG is recorded within days of birth in a cohort of infants without significant brain injury and born <; 30 weeks of gestation. The method first transforms the time-domain signal to the time-frequency domain and then trains a machine learning method, a gradient boosting machine, on each time-slice of the time-frequency distribution. We control for oversampling the time-frequency distribution with a significant reduction (<; 1%) in memory and computational complexity. The proposed method achieves similar accuracy to an existing multi-feature approach: area under the characteristic curve of 0.98 (with 95% confidence interval of 0.96 to 0.99), with a median sensitivity of 95% and median specificity of 94%. The proposed framework presents an accurate, simple, and computational efficient implementation as an alternative to both the deep learning approach and to the manual generation of a feature set.

A standardised assessment scheme for conventional EEG in preterm infants

OBJECTIVE

To develop a standardised scheme for assessing normal and abnormal electroencephalography (EEG) features of preterm infants. To assess the interobserver agreement of this assessment scheme.

METHODS

We created a standardised EEG assessment scheme for 6 different post-menstrual age (PMA) groups using 4 EEG categories. Two experts, not involved in the development of the scheme, evaluated this on 24 infants <32 weeks gestational age (GA) using random 2 hour EEG epochs. Where disagreements were found, the features were checked and modified. Finally, the two experts independently evaluated 2 hour EEG epochs from an additional 12 infants <37 weeks GA. The percentage of agreement was calculated as the ratio of agreements to the sum of agreements plus disagreements.

RESULTS

Good agreement in all patients and EEG feature category was obtained, with a median agreement between 80% and 100% over the 4 EEG assessment categories. No difference was found in agreement rates between the normal and abnormal features (p = 0.959).

CONCLUSIONS

We developed a standard EEG assessment scheme for preterm infants that shows good interobserver agreement.

SIGNIFICANCE

This will provide information to Neonatal Intensive Care Unit (NICU) staff about brain activity and maturation. We hope this will prove useful for many centres seeking to use neuromonitoring during critical care for preterm infants.

Suitability of an inter-burst detection method for grading hypoxic-ischemic encephalopathy in newborn EEG

Electroencephalography (EEG) is an important clinical tool for grading injury caused by lack of oxygen or blood to the brain during birth. Characteristics of low-voltage waveforms, known as inter-bursts, are related to different grades of injury. This study assesses the suitability of an existing inter-burst detection method, developed from preterm infants born <; 30 weeks of gestational age, to detect inter-bursts in term infants. Different features from the temporal organisation of the inter-bursts are combined using a multi-layer perceptron (MLP) machine learning algorithm to classify four grades of injury in the EEG. We find that the best performing feature, percentage of inter-bursts, has an accuracy of 59.3%. Combining this with the maximum duration of inter-bursts in the MLP produces a testing accuracy of 77.8%, with similar performance to existing multi-feature methods. These results validate the use of the preterm detection method in term EEG and show how simple measures of the inter-burst interval can be used to classify different grades of injury.

Time-Varying EEG Correlations Improve Automated Neonatal Seizure Detection

The aim of this study was to develop methods for detecting the nonstationary periodic characteristics of neonatal electroencephalographic (EEG) seizures by adapting estimates of the correlation both in the time (spike correlation; SC) and time–frequency domain (time–frequency correlation; TFC). These measures were incorporated into a seizure detection algorithm (SDA) based on a support vector machine to detect periods of seizure and nonseizure. The performance of these nonstationary correlation measures was evaluated using EEG recordings from 79 term neonates annotated by three human experts. The proposed measures were highly discriminative for seizure detection (median [Formula: see text]: 0.933 IQR: 0.821–0.975, median [Formula: see text]: 0.883 IQR: 0.707–0.931). The resultant SDA applied to multi-channel recordings had a median AUC of 0.988 (IQR: 0.931–0.998) when compared to consensus annotations, outperformed two state-of-the-art SDAs [Formula: see text] and was noninferior to the human expert for 73/79 of neonates.

Clamping the Umbilical Cord in Premature Deliveries (CUPiD): Neuromonitoring in the Immediate Newborn Period in a Randomized, Controlled Trial of Preterm Infants Born at <32 Weeks of Gestation

OBJECTIVE

To compare cerebral activity and oxygenation in preterm infants (<32 weeks of gestation) randomized to different cord clamping strategies.

STUDY DESIGN

Preterm infants born at <32 weeks of gestation were randomized to immediate cord clamping, umbilical cord milking (cord stripped 3 times), or delayed cord clamping for 60 seconds with bedside resuscitation. All infants underwent electroencephalogram (EEG) and cerebral near infrared spectroscopy for the first 72 hours after birth. Neonatal primary outcome measures were quantitative measures of the EEG (17 features) and near infrared spectroscopy over 1-hour time frames at 6 and 12 hours of life.

RESULTS

Forty-five infants were recruited during the study period. Twelve infants (27%) were randomized to immediate cord clamping, 19 (42%) to umbilical cord milking, and 14 (31%) to delayed cord clamping with bedside resuscitation. There were no significant differences between groups for measures of EEG activity or cerebral near infrared spectroscopy. Three of the 45 infants (6.7%) were diagnosed with severe IVH (2 in the immediate cord clamping group, 1 in the umbilical cord milking group; P = .35).

CONCLUSIONS

There were no differences in cerebral EEG activity and cerebral oxygenation values between cord management strategies at 6 and 12 hours.

TRIAL REGISTRATION

ISRCTN92719670.

Latent Phase Detection of Hypoxic-Ischemic Spike Transients in the EEG of Preterm Fetal Sheep Using Reverse Biorthogonal Wavelets & Fuzzy Classifier

Hypoxic-ischemic (HI) studies in preterms lack reliable prognostic biomarkers for diagnostic tests of HI encephalopathy (HIE). Our group's observations from in utero fetal sheep models suggest that potential biomarkers of HIE in the form of developing HI micro-scale epileptiform transients emerge along suppressed EEG/ECoG background during a latent phase of 6-7h post-insult. However, having to observe for the whole of the latent phase disqualifies any chance of clinical intervention. A precise automatic identification of these transients can help for a well-timed diagnosis of the HIE and to stop the spread of the injury before it becomes irreversible. This paper reports fusion of Reverse-Biorthogonal Wavelets with Type-1 Fuzzy classifiers, for the accurate real-time automatic identification and quantification of high-frequency HI spike transients in the latent phase, tested over seven in utero preterm sheep. Considerable high performance of 99.78 ± 0.10% was obtained from the Rbio-Wavelet Type-1 Fuzzy classifier for automatic identification of HI spikes tested over 42h of high-resolution recordings (sampling-freq:1024Hz). Data from post-insult automatic time-localization of high-frequency HI spikes reveals a promising trend in the average rate of the HI spikes, even in the animals with shorter occlusion periods, which highlights considerable higher number of transients within the first 2h post-insult.

Temporal evolution of quantitative EEG within 3 days of birth in early preterm infants

For the premature newborn, little is known about changes in brain activity during transition to extra-uterine life. We aim to quantify these changes in relation to the longer-term maturation of the developing brain. We analysed EEG for up to 72 hours after birth from 28 infants born <32 weeks of gestation. These infants had favourable neurodevelopment at 2 years of age and were without significant neurological compromise at time of EEG monitoring. Quantitative EEG was generated using features representing EEG power, discontinuity, spectral distribution, and inter-hemispheric connectivity. We found rapid changes in cortical activity over the 3 days distinct from slower changes associated with gestational age: for many features, evolution over 1 day after birth is equivalent to approximately 1 to 2.5 weeks of maturation. Considerable changes in the EEG immediately after birth implies that postnatal adaption significantly influences cerebral activity for early preterm infants. Postnatal age, in addition to gestational age, should be considered when analysing preterm EEG within the first few days after birth.

Quantitative Preterm EEG Analysis: The Need for Caution in Using Modern Data Science Techniques

Hemodynamic 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 behavioral state given the variations encountered in newborn EEG during different states. Finally, the detrimental influence of artifacts on quantitative EEG analysis is illustrated.