A growth chart of brain function from infancy to adolescence based on EEG

BACKGROUND

In children, objective, quantitative tools that determine functional neurodevelopment are scarce and rarely scalable for clinical use. Direct recordings of cortical activity using routinely acquired electroencephalography (EEG) offer reliable measures of brain function.

METHODS

We developed and validated a measure of functional brain age (FBA) using a residual neural network-based interpretation of the paediatric EEG. In this cross-sectional study, we included 1056 children with typical development ranging in age from 1 month to 18 years. We analysed a 10- to 15-min segment of 18-channel EEG recorded during light sleep (N1 and N2 states).

FINDINGS

The FBA had a weighted mean absolute error (wMAE) of 0.85 years (95% CI: 0.69-1.02; n = 1056). A two-channel version of the FBA had a wMAE of 1.51 years (95% CI: 1.30-1.73; n = 1056) and was validated on an independent set of EEG recordings (wMAE = 2.27 years, 95% CI: 1.90-2.65; n = 723). Group-level maturational delays were also detected in a small cohort of children with Trisomy 21 (Cohen's d = 0.36, p = 0.028).

INTERPRETATION

A FBA, based on EEG, is an accurate, practical and scalable automated tool to track brain function maturation throughout childhood with accuracy comparable to widely used physical growth charts.

FUNDING

This research was supported by the National Health and Medical Research Council, Australia, Helsinki University Diagnostic Center Research Funds, Finnish Academy, Finnish Paediatric Foundation, and Sigrid Juselius Foundation.

Clinical outcome prediction with an automated EEG trend, Brain State of the Newborn, after perinatal asphyxia

OBJECTIVE

To evaluate the utility of a fully automated deep learning -based quantitative measure of EEG background, Brain State of the Newborn (BSN), for early prediction of clinical outcome at four years of age.

METHODS

The EEG monitoring data from eighty consecutive newborns was analyzed using the automatically computed BSN trend. BSN levels during the first days of life (a of total 5427 hours) were compared to four clinical outcome categories: favorable, cerebral palsy (CP), CP with epilepsy, and death. The time dependent changes in BSN-based prediction for different outcomes were assessed by positive/negative predictive value (PPV/NPV) and by estimating the area under the receiver operating characteristic curve (AUC).

RESULTS

The BSN values were closely aligned with four visually determined EEG categories (p < 0·001), as well as with respect to clinical milestones of EEG recovery in perinatal Hypoxic Ischemic Encephalopathy (HIE; p < 0·003). Favorable outcome was related to a rapid recovery of the BSN trend, while worse outcomes related to a slow BSN recovery. Outcome predictions with BSN were accurate from 6 to 48 hours of age: For the favorable outcome, the AUC ranged from 95 to 99% (peak at 12 hours), and for the poor outcome the AUC ranged from 96 to 99% (peak at 12 hours). The optimal BSN levels for each PPV/NPV estimate changed substantially during the first 48 hours, ranging from 20 to 80.

CONCLUSIONS

We show that the BSN provides an automated, objective, and continuous measure of brain activity in newborns.

SIGNIFICANCE

The BSN trend discloses the dynamic nature that exists in both cerebral recovery and outcome prediction, supports individualized patient care, rapid stratification and early prognosis.

EEG response to a high volume (1.5 mL/kg) caudal block in infants less than 3 months

INTRODUCTION

The substantial compression of the dural sac and the subsequent cranial shift of cerebrospinal fluid caused by a high-volume caudal block has been shown to significantly but transiently reduce cerebral blood flow. The aim of the present study was to determine whether this reduction in cerebral perfusion is significant enough to alter brain function, as assessed by electroencephalography (EEG).

METHODS

Following ethics approval and parental informed consent, 11 infants (0-3 months) scheduled to undergo inguinal hernia repair were included in the study. EEG electrodes (using nine electrodes according to the 10-20 standard) were applied following anesthesia induction. Following a 5 min baseline period, a caudal block was performed (1.5 mL/kg), whereafter the EEG, hemodynamic, and cerebral near-infrared spectroscopy responses were followed during a 20 min observation period that was divided into four 5 min segments. Special attention was given to alterations in delta power activity since this may indicate cerebral ischemia.

RESULTS

All 11 infants displayed transient EEG changes, mainly represented by increased relative delta power, during the initial 5-10 min postinjection. The observed changes had returned close to baseline values 15 min postinjection. Heart rate and blood pressure remained stable throughout the study.

CONCLUSION

A high-volume caudal block appears to increase intracranial pressure, thereby reducing cerebral blood flow, to the extent that it transiently will affect cerebral function as assessed by EEG (increased delta power activity) in approximately 90% of small infants.

TRIAL REGISTRATION NUMBER

ACTRN12620000420943.

Automatic assessment of infant carrying and holding using at-home wearable recordings

Assessing infant carrying and holding (C/H), or physical infant-caregiver interaction, is important for a wide range of contexts in development research. An automated detection and quantification of infant C/H is particularly needed in long term at-home studies where development of infants' neurobehavior is measured using wearable devices. Here, we first developed a phenomenological categorization for physical infant-caregiver interactions to support five different definitions of C/H behaviors. Then, we trained and assessed deep learning-based classifiers for their automatic detection from multi-sensor wearable recordings that were originally used for mobile assessment of infants' motor development. Our results show that an automated C/H detection is feasible at few-second temporal accuracy. With the best C/H definition, the automated detector shows 96% accuracy and 0.56 kappa, which is slightly less than the video-based inter-rater agreement between trained human experts (98% accuracy, 0.77 kappa). The classifier performance varies with C/H definition reflecting the extent to which infants' movements are present in each C/H variant. A systematic benchmarking experiment shows that the widely used actigraphy-based method ignores the normally occurring C/H behaviors. Finally, we show proof-of-concept for the utility of the novel classifier in studying C/H behavior across infant development. Particularly, we show that matching the C/H detections to individuals' gross motor ability discloses novel insights to infant-parent interaction.

Multiplex dynamic networks in the newborn brain disclose latent links with neurobehavioral phenotypes

The higher brain functions arise from coordinated neural activity between distinct brain regions, but the spatial, temporal, and spectral complexity of these functional connectivity networks (FCNs) has challenged the identification of correlates with neurobehavioral phenotypes. Characterizing behavioral correlates of early life FCNs is important to understand the activity dependent emergence of neurodevelopmental performance and for improving health outcomes. Here, we develop an analysis pipeline for identifying multiplex dynamic FCNs that combine spectral and spatiotemporal characteristics of the newborn cortical activity. This data-driven approach automatically uncovers latent networks that show robust neurobehavioral correlations and consistent effects by in utero drug exposure. Altogether, the proposed pipeline provides a robust end-to-end solution for an objective assessment and quantitation of neurobehaviorally meaningful network constellations in the highly dynamic cortical functions.

Detailed statistical analysis plan for ALBINO: effect of Allopurinol in addition to hypothermia for hypoxic-ischemic Brain Injury on Neurocognitive Outcome - a blinded randomized placebo-controlled parallel group multicenter trial for superiority (phase III)

BACKGROUND

Despite therapeutic hypothermia (TH) and neonatal intensive care, 45-50% of children affected by moderate-to-severe neonatal hypoxic-ischemic encephalopathy (HIE) die or suffer from long-term neurodevelopmental impairment. Additional neuroprotective therapies are sought, besides TH, to further improve the outcome of affected infants. Allopurinol - a xanthine oxidase inhibitor - reduced the production of oxygen radicals and subsequent brain damage in pre-clinical and preliminary human studies of cerebral ischemia and reperfusion, if administered before or early after the insult. This ALBINO trial aims to evaluate the efficacy and safety of allopurinol administered immediately after birth to (near-)term infants with early signs of HIE.

METHODS/DESIGN

The ALBINO trial is an investigator-initiated, randomized, placebo-controlled, double-blinded, multi-national parallel group comparison for superiority investigating the effect of allopurinol in (near-)term infants with neonatal HIE. Primary endpoint is long-term outcome determined as survival with neurodevelopmental impairment versus death versus non-impaired survival at 2 years.

RESULTS

The primary analysis with three mutually exclusive responses (healthy, death, composite outcome for impairment) will be on the intention-to-treat (ITT) population by a generalized logits model according to Bishop, Fienberg, Holland (Bishop YF, Discrete Multivariate Analysis: Therory and Practice, 1975) and ."will be stratified for the two treatment groups.

DISCUSSION

The statistical analysis for the ALBINO study was defined in detail in the study protocol and implemented in this statistical analysis plan published prior to any data analysis. This is in accordance with the Declaration of Helsinki and the International Conference on Harmonization Good Clinical Practice guidelines.

TRIAL REGISTRATION

ClinicalTrials.gov NCT03162653. Registered on 22 May 2017.

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.

Networks of cortical activity show graded responses to perinatal asphyxia

BACKGROUND

Perinatal asphyxia often leads to hypoxic-ischemic encephalopathy (HIE) with a high risk of neurodevelopmental consequences. While moderate and severe HIE link to high morbidity, less is known about brain effects of perinatal asphyxia with no or only mild HIE. Here, we test the hypothesis that cortical activity networks in the newborn infants show a dose-response to asphyxia.

METHODS

We performed EEG recordings for infants with perinatal asphyxia/HIE of varying severity (n = 52) and controls (n = 53) and examined well-established computational metrics of cortical network activity.

RESULTS

We found graded alterations in cortical activity networks according to severity of asphyxia/HIE. Furthermore, our findings correlated with early clinical recovery measured by the time to attain full oral feeding.

CONCLUSION

We show that both local and large-scale correlated cortical activity are affected by increasing severity of HIE after perinatal asphyxia, suggesting that HIE and perinatal asphyxia are better represented as a continuum rather than the currently used discreet categories. These findings imply that automated computational measures of cortical function may be useful in characterizing the dose effects of adversity in the neonatal brain; such metrics hold promise for benchmarking clinical trials via patient stratification or as early outcome measures.

IMPACT

Perinatal asphyxia causes every fourth neonatal death worldwide and provides a diagnostic and prognostic challenge for the clinician. We report that infants with perinatal asphyxia show specific graded responses in cortical networks according to severity of asphyxia and ensuing hypoxic-ischaemic encephalopathy. Early EEG recording and automated computational measures of brain function have potential to help in clinical evaluation of infants with perinatal asphyxia.

Neonatal cortical activity organizes into transient network states that are affected by vigilance states and brain injury

Early neurodevelopment is critically dependent on the structure and dynamics of spontaneous neuronal activity; however, the natural organization of newborn cortical networks is poorly understood. Recent adult studies suggest that spontaneous cortical activity exhibits discrete network states with physiological correlates. Here, we studied newborn cortical activity during sleep using hidden Markov modeling to determine the presence of such discrete neonatal cortical states (NCS) in 107 newborn infants, with 47 of them presenting with a perinatal brain injury. Our results show that neonatal cortical activity organizes into four discrete NCSs that are present in both cardinal sleep states of a newborn infant, active and quiet sleep, respectively. These NCSs exhibit state-specific spectral and functional network characteristics. The sleep states exhibit different NCS dynamics, with quiet sleep presenting higher fronto-temporal activity and a stronger brain-wide neuronal coupling. Brain injury was associated with prolonged lifetimes of the transient NCSs, suggesting lowered dynamics, or flexibility, in the cortical networks. Taken together, the findings suggest that spontaneously occurring transient network states are already present at birth, with significant physiological and pathological correlates; this NCS analysis framework can be fully automatized, and it holds promise for offering an objective, global level measure of early brain function for benchmarking neurodevelopmental or clinical research.

Mechanisms underlying pathological cortical bursts during metabolic depletion

Cortical activity depends upon a continuous supply of oxygen and other metabolic resources. Perinatal disruption of oxygen availability is a common clinical scenario in neonatal intensive care units, and a leading cause of lifelong disability. Pathological patterns of brain activity including burst suppression and seizures are a hallmark of the recovery period, yet the mechanisms by which these patterns arise remain poorly understood. Here, we use computational modeling of coupled metabolic-neuronal activity to explore the mechanisms by which oxygen depletion generates pathological brain activity. We find that restricting oxygen supply drives transitions from normal activity to several pathological activity patterns (isoelectric, burst suppression, and seizures), depending on the potassium supply. Trajectories through parameter space track key features of clinical electrophysiology recordings and reveal how infants with good recovery outcomes track toward normal parameter values, whereas the parameter values for infants with poor outcomes dwell around the pathological values. These findings open avenues for studying and monitoring the metabolically challenged infant brain, and deepen our understanding of the link between neuronal and metabolic activity.

Inter-site generalizability of EEG based age prediction algorithms in the preterm infant

OBJECTIVE

To assess and overcome the effects of site differences in EEG -based brain age prediction in preterm infants. &#xD;Approach: We used a 'bag of features' with a combination function estimated using support vector regression (SVR) and feature selection (filter then wrapper) to predict post-menstrual age (PMA). The SVR was trained on a dataset containing 138 EEG recordings from 37 preterm infants (site 1). A separate set of 36 EEG recordings from 36 preterm infants was used to validate the age predictor (site 2). The feature distributions were compared between sites, and training used only features that were not significantly different between sites. The mean absolute error between predicted age and PMA was used to define the accuracy of prediction. Successful validation was defined as no significant differences in error between site 1 (cross-validation) and site 2.&#xD;Main results: The age predictor based on all features and trained on site 1 was not validated on site 2 (p < 0.001; MAE site 1 = 1.0 weeks, n = 59 vs MAE site 2 = 2.1 weeks, n = 36). The MAE was improved by training on a restricted features set (MAE site 1 = 1.0 weeks, n = 59 vs MAE site 2 = 1.1 weeks, n = 36), resulting in a validated age predictor (p = 0.68). The selected features closely aligned with features selected when trained on a combination of data from site 1 and site 2.&#xD;Significance: The ability of EEG classifiers, such as brain age prediction, to maintain accuracy on data collected at other sites may be challenged by unexpected, site-dependent differences in EEG signals. Permitting a small amount of data leakage between sites improves generalization, leading towards universal methods of EEG interpretation in preterm infants.&#xD.

Evaluation of self-supervised pre-training for automatic infant movement classification using wearable movement sensors

The recently-developed infant wearable MAIJU provides a means to automatically evaluate infants' motor performance in an objective and scalable manner in out-of-hospital settings. This information could be used for developmental research and to support clinical decision-making, such as detection of developmental problems and guiding of their therapeutic interventions. MAIJU-based analyses rely fully on the classification of infant's posture and movement; it is hence essential to study ways to increase the accuracy of such classifications, aiming to increase the reliability and robustness of the automated analysis. Here, we investigated how self-supervised pre-training improves performance of the classifiers used for analyzing MAIJU recordings, and we studied whether performance of the classifier models is affected by context-selective quality-screening of pre-training data to exclude periods of little infant movement or with missing sensors. Our experiments show that i) pre-training the classifier with unlabeled data leads to a robust accuracy increase of subsequent classification models, and ii) selecting context-relevant pre-training data leads to substantial further improvements in the classifier performance.Clinical relevance- This study showcases that self-supervised learning can be used to increase the accuracy of out-of-hospital evaluation of infants' motor abilities via smart wearables.

Optimization of time series features to estimate brain age in children from electroencephalography

Functional brain age measures in children, derived from the electroencephalogram (EEG), offer direct and objective measures in assessing neurodevelopmental status. Here we explored the effectiveness of 32 preselected 'handcrafted' EEG features in predicting brain age in children. These features were benchmarked against a large library of highly comparative multivariate time series features (>7000 features). Results showed that age predictors based on handcrafted EEG features consistently outperformed a generic set of time series features. These findings suggest that optimization of brain age estimation in children benefits from careful preselection of EEG features that are related to age and neurodevelopmental trajectory. This approach shows potential for clinical translation in the future.Clinical Relevance-Handcrafted EEG features provide an accurate functional neurodevelopmental biomarker that tracks brain function maturity in children.

Analysing heart rate variability in preterm infants: the effect of temporal adjustment of NN peaks and missing data

The measurement of heart rate variability (HRV) in preterm infants provides important information on function to clinicians. Measuring the underlying electrocardiogram (ECG) in the neonatal intensive care unit is a challenge and there is a trade off between extracting accurate measurements of the HRV and the amount of ECG processed due to contamination. Knowledge on the effects of 1) quantization in the time domain and 2) missing data on the calculation of HRV features will inform clinical implementation. In this paper, we studied multiple 5 minute epochs from 148 ECG recordings on 56 extremely preterm infants. We found that temporal adjustment of NN peaks improves the estimate of the NN interval resulting in HRV features (m = 9) that are better correlated with age (median percentage increase in correlation of individual features: 0.2%, IQR: 0.0 to 5.6%; correlation with age predictor and age from 0.721 to 0.787). Improved (sub-sample) quantization of the NN intervals (via interpolation) reduced the overall value of HRV features (median percentage reduction in feature value: -1.3%, IQR: -18.8 to 0.0; m = 9), primarily through a reduction in the energy of high-frequency oscillations. HRV features were also robust to missing data, with measures such as mean NN, fractal dimension and the smoothed nonlinear energy operator (SNEO) less susceptible to missing data than features such as VLF, LF, and HF. Furthermore, age predictions derived from a combination of HRV measures were more robust to missing data than individual HRV measures.Clinical Relevance-Poor quantization in time when estimating the NN peak and the presence of missing data confound HRV measures, particularly spectral measures.

Charting infants' motor development at home using a wearable system: validation and comparison to physical growth charts

BACKGROUND

Early neurodevelopmental care and research are in urgent need of practical methods for quantitative assessment of early motor development. Here, performance of a wearable system in early motor assessment was validated and compared to developmental tracking of physical growth charts.

METHODS

Altogether 1358 h of spontaneous movement during 226 recording sessions in 116 infants (age 4-19 months) were analysed using a multisensor wearable system. A deep learning-based automatic pipeline quantified categories of infants' postures and movements at a time scale of seconds. Results from an archived cohort (dataset 1, N = 55 infants) recorded under partial supervision were compared to a validation cohort (dataset 2, N = 61) recorded at infants' homes by the parents. Aggregated recording-level measures including developmental age prediction (DAP) were used for comparison between cohorts. The motor growth was also compared with respective DAP estimates based on physical growth data (length, weight, and head circumference) obtained from a large cohort (N = 17,838 infants; age 4-18 months).

FINDINGS

Age-specific distributions of posture and movement categories were highly similar between infant cohorts. The DAP scores correlated tightly with age, explaining 97-99% (94-99% CI 95) of the variance at the group average level, and 80-82% (72-88%) of the variance in the individual recordings. Both the average motor and the physical growth measures showed a very strong fit to their respective developmental models (R² = 0.99). However, single measurements showed more modality-dependent variation that was lowest for motor (σ = 1.4 [1.3-1.5 CI 95] months), length (σ = 1.5 months), and combined physical (σ = 1.5 months) measurements, and it was clearly higher for the weight (σ = 1.9 months) and head circumference (σ = 1.9 months) measurements. Longitudinal tracking showed clear individual trajectories, and its accuracy was comparable between motor and physical measures with longer measurement intervals.

INTERPRETATION

A quantified, transparent and explainable assessment of infants' motor performance is possible with a fully automated analysis pipeline, and the results replicate across independent cohorts from out-of-hospital recordings. A holistic assessment of motor development provides an accuracy that is comparable with the conventional physical growth measures. A quantitative measure of infants' motor development may directly support individual diagnostics and care, as well as facilitate clinical research as an outcome measure in early intervention trials.

FUNDING

This work was supported by the Finnish Academy (314602, 335788, 335872, 332017, 343498), Finnish Pediatric Foundation (Lastentautiensäätiö), Aivosäätiö, Sigrid Jusélius Foundation, and HUS Children's Hospital/HUS diagnostic center research funds.

Comparison of End-to-End Neural Network Architectures and Data Augmentation Methods for Automatic Infant Motility Assessment Using Wearable Sensors

Infant motility assessment using intelligent wearables is a promising new approach for assessment of infant neurophysiological development, and where efficient signal analysis plays a central role. This study investigates the use of different end-to-end neural network architectures for processing infant motility data from wearable sensors. We focus on the performance and computational burden of alternative sensor encoder and time series modeling modules and their combinations. In addition, we explore the benefits of data augmentation methods in ideal and nonideal recording conditions. The experiments are conducted using a dataset of multisensor movement recordings from 7-month-old infants, as captured by a recently proposed smart jumpsuit for infant motility assessment. Our results indicate that the choice of the encoder module has a major impact on classifier performance. For sensor encoders, the best performance was obtained with parallel two-dimensional convolutions for intrasensor channel fusion with shared weights for all sensors. The results also indicate that a relatively compact feature representation is obtainable for within-sensor feature extraction without a drastic loss to classifier performance. Comparison of time series models revealed that feedforward dilated convolutions with residual and skip connections outperformed all recurrent neural network (RNN)-based models in performance, training time, and training stability. The experiments also indicate that data augmentation improves model robustness in simulated packet loss or sensor dropout scenarios. In particular, signal- and sensor-dropout-based augmentation strategies provided considerable boosts to performance without negatively affecting the baseline performance. Overall, the results provide tangible suggestions on how to optimize end-to-end neural network training for multichannel movement sensor data.

Application of the ILAE Neonatal Seizure Framework to an international panel of medical personnel

OBJECTIVE

The International League Against Epilepsy (ILAE) Neonatal Seizure Framework was tested by medical personnel.

METHODS

Attendees at the 2016 ILAE European Congress on Epileptology in Prague, the International Video-EEG Course in Pediatric Epilepsies in Madrid 2017, and a local meeting in Utrecht, The Netherlands, were introduced to the proposed ILAE neonatal classification system with teaching videos covering the seven types of clinical seizures in the proposed neonatal classification system. Five test digital video recordings of EEG-confirmed motor neonatal seizures were then shown and classified by the rater based on their knowledge of the proposed ILAE Neonatal Seizure Framework. A multirater Kappa statistic was used to assess agreement between observers and the true diagnosis.

RESULTS

The responses of 194 raters were obtained. There was no single predominant classification system that was currently used by the raters. Using the ILAE framework, 78-93% of raters correctly identified the clinical seizure type for each neonate; the overall inter-rater agreement (Kappa statistic) was 0.67. The clonic motor seizure type was most frequently identified (93% of the time; Kappa = 0.870). EEG technicians correctly identified all presented motor seizure types more frequently than any other group (accuracy = 0.9).

SIGNIFICANCE

The ILAE Neonatal Seizure Framework was judged by most raters to be better than other systems for the classification of clinical seizures. Among all seizure types presented, clonic seizures appeared to be the easiest to accurately identify. Average accuracy across the five seizure types was 84.5%. These data suggest that the ILAE neonatal seizure classification may be used by all healthcare professionals to accurately identify the predominant clinical seizure type.

A Bedside Method for Measuring Effects of a Sedative Drug on Cerebral Function in Newborn Infants

BACKGROUND

Data on the cerebral effects of analgesic and sedative drugs are needed for the development of safe and effective treatments during neonatal intensive care. Electroencephalography (EEG) is an objective, but interpreter-dependent method for monitoring cortical activity. Quantitative computerized analyses might reveal EEG changes otherwise not detectable.

METHODS

EEG registrations were retrospectively collected from 21 infants (mean 38.7 gestational weeks; range 27-42) who received dexmedetomidine during neonatal care. The registrations were transformed into computational features and analyzed visually, and with two computational measures quantifying relative and absolute changes in power (range EEG; rEEG) and cortico-cortical synchrony (activation synchrony index; ASI), respectively.

RESULTS

The visual assessment did not reveal any drug effects. In rEEG analyses, a negative correlation was found between the baseline and the referential frontal (rho = 0.612, p = 0.006) and parietal (rho = -0.489, p = 0.035) derivations. The change in ASI was negatively correlated to baseline values in the interhemispheric (rho = -0.753; p = 0.001) and frontal comparisons (rho = -0.496; p = 0.038).

CONCLUSION

Cerebral effects of dexmedetomidine as determined by EEG in newborn infants are related to cortical activity prior to DEX administration, indicating that higher brain activity levels (higher rEEG) during baseline links to a more pronounced reduction by DEX. The computational measurements indicate drug effects on both overall cortical activity and cortico-cortical communication. These effects were not evident in visual analysis.

Neuromonitoring in neonatal critical care part I: neonatal encephalopathy and neonates with possible seizures

The blooming of neonatal neurocritical care over the last decade reflects substantial advances in neuromonitoring and neuroprotection. The most commonly used brain monitoring tools in the neonatal intensive care unit (NICU) are amplitude integrated EEG (aEEG), full multichannel continuous EEG (cEEG), and near-infrared spectroscopy (NIRS). While some published guidelines address individual tools, there is no consensus on consistent, efficient, and beneficial use of these modalities in common NICU scenarios. This work reviews current evidence to assist decision making for best utilization of neuromonitoring modalities in neonates with encephalopathy or with possible seizures. Neuromonitoring approaches in extremely premature and critically ill neonates are discussed separately in the companion paper. IMPACT: Neuromonitoring techniques hold promise for improving neonatal care. For neonatal encephalopathy, aEEG can assist in screening for eligibility for therapeutic hypothermia, though should not be used to exclude otherwise eligible neonates. Continuous cEEG, aEEG and NIRS through rewarming can assist in prognostication. For neonates with possible seizures, cEEG is the gold standard for detection and diagnosis. If not available, aEEG as a screening tool is superior to clinical assessment alone. The use of seizure detection algorithms can help with timely seizures detection at the bedside.

An automated bedside measure for monitoring neonatal cortical activity: a supervised deep learning-based electroencephalogram classifier with external cohort validation

BACKGROUND

Electroencephalogram (EEG) monitoring is recommended as routine in newborn neurocritical care to facilitate early therapeutic decisions and outcome predictions. EEG's larger-scale implementation is, however, hindered by the shortage of expertise needed for the interpretation of spontaneous cortical activity, the EEG background. We developed an automated algorithm that transforms EEG recordings to quantified interpretations of EEG background and provides simple intuitive visualisations in patient monitors.

METHODS

In this method-development and proof-of-concept study, we collected visually classified EEGs from infants recovering from birth asphyxia or stroke. We used unsupervised learning methods to explore latent EEG characteristics, which guided the supervised training of a deep learning-based classifier. We assessed the classifier performance using cross-validation and an external validation dataset. We constructed a novel measure of cortical function, brain state of the newborn (BSN), from the novel EEG background classifier and a previously published sleep-state classifier. We estimated clinical utility of the BSN by identification of two key items in newborn brain monitoring, the onset of continuous cortical activity and sleep-wake cycling, compared with the visual interpretation of the raw EEG signal and the amplitude-integrated (aEEG) trend.

FINDINGS

We collected 2561 h of EEG from 39 infants (gestational age 35·0-42·1 weeks; postnatal age 0-7 days). The external validation dataset included 105 h of EEG from 31 full-term infants. The overall accuracy of the EEG background classifier was 92% in the whole cohort (95% CI 91-96; range 85-100 for individual infants). BSN trend values were closely related to the onset of continuous EEG activity or sleep-wake cycling, and BSN levels showed robust difference between aEEG categories. The temporal evolution of the BSN trends showed early diverging trajectories in infants with severely abnormal outcomes.

INTERPRETATION

The BSN trend can be implemented in bedside patient monitors as an EEG interpretation that is intuitive, transparent, and clinically explainable. A quantitative trend measure of brain function might harmonise practices across medical centres, enable wider use of brain monitoring in neurocritical care, and might facilitate clinical intervention trials.

FUNDING

European Training Networks Funding Scheme, the Academy of Finland, Finnish Pediatric Foundation (Lastentautiensäätiö), Aivosäätiö, Sigrid Juselius Foundation, HUS Children's Hospital, HUS Diagnostic Center, National Health and Medical Research Council of Australia.

Intelligent wearable allows out-of-the-lab tracking of developing motor abilities in infants

Background

Early neurodevelopmental care needs better, effective and objective solutions for assessing infants’ motor abilities. Novel wearable technology opens possibilities for characterizing spontaneous movement behavior. This work seeks to construct and validate a generalizable, scalable, and effective method to measure infants’ spontaneous motor abilities across all motor milestones from lying supine to fluent walking.

Methods

A multi-sensor infant wearable was constructed, and 59 infants (age 5–19 months) were recorded during their spontaneous play. A novel gross motor description scheme was used for human visual classification of postures and movements at a second-level time resolution. A deep learning -based classifier was then trained to mimic human annotations, and aggregated recording-level outputs were used to provide posture- and movement-specific developmental trajectories, which enabled more holistic assessments of motor maturity.

Results

Recordings were technically successful in all infants, and the algorithmic analysis showed human-equivalent-level accuracy in quantifying the observed postures and movements. The aggregated recordings were used to train an algorithm for predicting a novel neurodevelopmental measure, Baba Infant Motor Score (BIMS). This index estimates maturity of infants’ motor abilities, and it correlates very strongly (Pearson’s r = 0.89, p < 1e-20) to the chronological age of the infant.

Conclusions

The results show that out-of-hospital assessment of infants’ motor ability is possible using a multi-sensor wearable. The algorithmic analysis provides metrics of motility that are transparent, objective, intuitively interpretable, and they link strongly to infants’ age. Such a solution could be automated and scaled to a global extent, holding promise for functional benchmarking in individualized patient care or early intervention trials.

Assessment of an infant’s motor abilities is a key part of regular health checks of infant development. However, there is shortage of methods that would allow objective and user-friendly tracking of infant motor abilities. We describe a system that measures infant’s posture and movement with sensors that are attached to the clothing. Movement signals are analyzed with a deep learning algorithm to predict maturity of motor abilities. The accuracy of analysis is comparable to human assessments. This system could enable early diagnosis of developmental delays, and it can be used to assess motor development in clinical trials.

Airaksinen et al. describe an infant wearable system that accurately quantifies key aspects of infant motor ability and uses deep learning algorithms to analyze movement signals. Motor ability age and maturation can be predicted, with the predictions correlating with other clinical and parental assessments.

Cortical networks show characteristic recruitment patterns after somatosensory stimulation by pneumatically evoked repetitive hand movements in newborn infants

Controlled assessment of functional cortical networks is an unmet need in the clinical research of noncooperative subjects, such as infants. We developed an automated, pneumatic stimulation method to actuate naturalistic movements of an infant’s hand, as well as an analysis pipeline for assessing the elicited electroencephalography (EEG) responses and related cortical networks. Twenty newborn infants with perinatal asphyxia were recruited, including 7 with mild-to-moderate hypoxic–ischemic encephalopathy (HIE). Statistically significant corticokinematic coherence (CKC) was observed between repetitive hand movements and EEG in all infants, peaking near the contralateral sensorimotor cortex. CKC was robust to common sources of recording artifacts and to changes in vigilance state. A wide recruitment of cortical networks was observed with directed phase transfer entropy, also including areas ipsilateral to the stimulation. The extent of such recruited cortical networks was quantified using a novel metric, Spreading Index, which showed a decrease in 4 (57%) of the infants with HIE. CKC measurement is noninvasive and easy to perform, even in noncooperative subjects. The stimulation and analysis pipeline can be fully automated, including the statistical evaluation of the cortical responses. Therefore, the CKC paradigm holds great promise as a scientific and clinical tool for controlled assessment of functional cortical networks.

Networks of cortical activity in infants with epilepsy

Epilepsy in infancy links to a significant risk of neurodevelopmental delay, calling for a better understanding of its underlying mechanisms. Here, we studied cortical activity networks in infants with early-onset epilepsy to identify network properties that could preempt infants’ neurodevelopmental course.

We studied high-density (64 channel) EEG during non-REM (N2) sleep in N = 49 infants at one year of age after being diagnosed with epilepsy during their first year of life. We computed frequency-specific networks in the cortical source space for two intrinsic brain modes: amplitude-amplitude and phase-phase correlations.

Cortical activity networks of all frequency bands and connectivity modes were compared between the syndrome groups, as well as between three categories of neurocognitive development. The group differences were studied at three spatial levels: global, regional, and individual connections. Cortical mechanisms related to infant epilepsy were further compared to physiological networks using an automatic spindle detection algorithm.

Our results show that global connectivity does not significantly differ between epilepsy syndromes; however, it co-varies with neurocognitive development. The largest network differences were observed at the lowest (&lt;1 Hz) and mid-range (10-15 Hz) frequency bands. An algorithmic removal of sleep spindles from the data reduced the strength of the mid-range frequency network only partially. The centrocentral and frontocentral networks at the spindle frequencies were found to be strongest in infants with a persistent age-typical neurocognitive performance, while their low-frequency (&lt; 1 Hz) networks were weaker for both amplitude-amplitude (P = 0.008, effect size = 0.61) and phase-phase correlations (P = 0.02, effect size = 0.54) at low (&lt; 1 Hz). However, subjects with persistent mild neurocognitive delay from 1 to 2 years of age had higher amplitude-amplitude (P = 0.02, effect size = 0.73) and phase-phase (P = 0.06, effect size = 0.59) at low frequencies than those that deteriorated from mild to severely delayed from 1 to 2 years of age.

Our findings suggest that cortical activity networks reflect the underlying clinical course of infants’ epilepsy, and measures of spectrally and spatially resolved networks might become useful in better understanding infantile epilepsy as a network disease.

The relationship between interhemispheric synchrony, morphine and microstructural development of the corpus callosum in extremely preterm infants

The primary aim of this study is to examine whether bursting interhemispheric synchrony (bIHS) in the first week of life of infants born extremely preterm, is associated with microstructural development of the corpus callosum (CC) on term equivalent age magnetic resonance imaging scans. The secondary aim is to address the effects of analgesics such as morphine, on bIHS in extremely preterm infants. A total of 25 extremely preterm infants (gestational age [GA] < 28 weeks) were monitored with the continuous two-channel EEG during the first 72 h and after 1 week from birth. bIHS was analyzed using the activation synchrony index (ASI) algorithm. Microstructural development of the CC was assessed at ~ 30 and ~ 40 weeks of postmenstrual age (PMA) using fractional anisotropy (FA) measurements. Multivariable regression analyses were used to assess the primary and secondary aim. Analyses were adjusted for important clinical confounders: morphine, birth weight z-score, and white matter injury score. Due to the reduced sample size, only the most relevant variables, according to literature, were included. ASI was not significantly associated with FA of the CC at 30 weeks PMA and at 40 weeks PMA (p > .5). ASI was positively associated with the administration of morphine (p < .05). Early cortical synchrony may be affected by morphine and is not associated with the microstructural development of the CC. More studies are needed to evaluate the long-term effects of neonatal morphine treatment to optimize sedation in this high-risk population.

Sleep State Trend (SST), a bedside measure of neonatal sleep state fluctuations based on single EEG channels

OBJECTIVE

To develop and validate an automated method for bedside monitoring of sleep state fluctuations in neonatal intensive care units.

METHODS

A deep learning-based algorithm was designed and trained using 53 EEG recordings from a long-term (a)EEG monitoring in 30 near-term neonates. The results were validated using an independent dataset from 30 polysomnography recordings. In addition, we constructed Sleep State Trend (SST), a bedside-ready means for visualizing classifier outputs.

RESULTS

The accuracy of quiet sleep detection in the training data was 90%, and the accuracy was comparable (85-86 %) in all bipolar derivations available from the 4-electrode recordings. The algorithm generalized well to a polysomnography dataset, showing 81% overall accuracy despite different signal derivations. SST allowed an intuitive, clear visualization of the classifier output.

CONCLUSIONS

Fluctuations in sleep states can be detected at high fidelity from a single EEG channel, and the results can be visualized as a transparent and intuitive trend in the bedside monitors.

SIGNIFICANCE

The Sleep State Trend (SST) may provide caregivers and clinical studies a real-time view of sleep state fluctuations and its cyclicity.

Asymmetry in sleep spindles and motor outcome in infants with unilateral brain injury

AIM

To determine whether interhemispheric difference in sleep spindles in infants with perinatal unilateral brain injury could link to a pathological network reorganization that underpins the development of unilateral cerebral palsy (CP).

METHOD

This was a multicentre retrospective study of 40 infants (19 females, 21 males) with unilateral brain injury. Sleep spindles were detected and quantified with an automated algorithm from electroencephalograph records performed at 2 months to 5 months of age. The clinical outcomes after 18 months were compared to spindle power asymmetry (SPA) between hemispheres in different brain regions.

RESULTS

We found a significantly increased SPA in infants who later developed unilateral CP (n=13, with the most robust interhemispheric difference seen in the central spindles. The best individual-level prediction of unilateral CP was seen in the centro-occipital spindles with an overall accuracy of 93%. An empiric cut-off level for SPA at 0.65 gave a positive predictive value of 100% and a negative predictive value of 93% for later development of unilateral CP.

INTERPRETATION

Our data suggest that automated analysis of interhemispheric SPA provides a potential biomarker of unilateral CP at a very early age. This holds promise for guiding the early diagnostic process in infants with a perinatally identified brain injury.

WHAT THIS PAPER ADDS

Unilateral perinatal brain injury may affect the development of electroencephalogram (EEG) sleep spindles. Interhemispheric asymmetry in sleep spindles can be quantified with automated EEG analysis. Spindle power asymmetry can be a potential biomarker of unilateral cerebral palsy.

Developing Disposable EEG Cap for Infant Recordings at the Neonatal Intensive Care Unit

Long-term EEG monitoring in neonatal intensive care units (NICU) is challenged with finding solutions for setting up and maintaining a sufficient recording quality with limited technical experience. The current study evaluates different solutions for the skin-electrode interface and develops a disposable EEG cap for newborn infants. Several alternative materials for the skin-electrode interface were compared to the conventional gel and paste: conductive textiles (textured and woven), conductive Velcro, sponge, super absorbent hydrogel (SAH), and hydro fiber sheets (HF). The comparisons included the assessment of dehydration and recordings of signal quality (skin interphase impedance and powerline (50 Hz) noise) for selected materials. The test recordings were performed using snap electrodes integrated into a forearm sleeve or a forehead band along with skin-electrode interfaces to mimic an EEG cap with the aim of long-term biosignal recording on unprepared skin. In the hydration test, conductive textiles and Velcro performed poorly. While the SAH and HF remained sufficiently hydrated for over 24 h in an incubator-mimicking environment, the sponge material was dehydrated during the first 12 h. Additionally, the SAH was found to have a fragile structure and was electrically prone to artifacts after 12 h. In the electrical impedance and recording comparisons of muscle activity, the results for thick-layer HF were comparable to the conventional gel on unprepared skin. Moreover, the mechanical instability measured by 1-2 Hz and 1-20 Hz normalized relative power spectrum density was comparable with clinical EEG recordings using subdermal electrodes. The results together suggest that thick-layer HF at the skin-electrode interface is an effective candidate for a preparation-free, long-term recording, with many advantages, such as long-lasting recording quality, easy use, and compatibility with sensitive infant skin contact.

Facilitating early parent-infant emotional connection improves cortical networks in preterm infants

Exposure to environmental adversities during early brain development, such as preterm birth, can affect early brain organization. Here, we studied whether development of cortical activity networks in preterm infants may be improved by a multimodal environmental enrichment via bedside facilitation of mother-infant emotional connection. We examined functional cortico-cortical connectivity at term age using high-density electroencephalography recordings in infants participating in a randomized controlled trial of Family Nurture Intervention (FNI). Our results identify several large-scale, frequency-specific network effects of FNI, most extensively in the alpha frequency in fronto-central cortical regions. The connectivity strength in this network was correlated to later neurocognitive performance, and it was comparable to healthy term-born infants rather than the infants receiving standard care. These findings suggest that preterm neurodevelopmental care can be improved by a biologically driven environmental enrichment, such as early facilitation of direct human connection.

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.

Visual field defects after vigabatrin treatment during infancy: retrospective population-based study

AIM

To investigate the prevalence of vigabatrin-attributed visual field defect (VAVFD) in infantile spasms and the utility of optical coherence tomography (OCT) in detecting vigabatrin-related damage.

METHOD

We examined visual fields by Goldmann or Octopus perimetry and the thickness of peripapillary retinal nerve fiber layer (RNFL) with spectral-domain OCT at school age or adolescence.

RESULTS

Out of 88 patients (38 females, mean age at study 15y, SD 4y 3mo, range 6y 4mo-23y 3mo [n=65] or deceased [n=21] or moved abroad [n=2]) exposed to vigabatrin in infancy, 28 were able to perform formal visual field testing. Two had visual field defect from structural causes. We found mild VAVFD in four patients and severe VAVFD in one patient. Median vigabatrin treatment duration for those with normal visual field was 11 months compared to 19 months for those with VAVFD (p=0.04). OCT showed concomitant attenuated RNFL in three children with VAVFD, and was normal in one. The temporal half of the peripapillary RNFL was significantly thinner in the VAVFD group compared to the normal visual field group.

INTERPRETATION

The overall prevalence of VAVFD is lower after exposure in infancy compared to 52% which has been reported after exposure in adulthood. The risk increases with longer treatment duration. Further studies should identify infants particularly susceptible to VAVFD and clarify the role of OCT.

Cortical Cross-Frequency Coupling Is Affected by in utero Exposure to Antidepressant Medication

Up to five percent of human infants are exposed to maternal antidepressant medication by serotonin reuptake inhibitors (SRI) during pregnancy, yet the SRI effects on infants’ early neurodevelopment are not fully understood. Here, we studied how maternal SRI medication affects cortical frequency-specific and cross-frequency interactions estimated, respectively, by phase-phase correlations (PPC) and phase-amplitude coupling (PAC) in electroencephalographic (EEG) recordings. We examined the cortical activity in infants after fetal exposure to SRIs relative to a control group of infants without medical history of any kind. Our findings show that the sleep-related dynamics of PPC networks are selectively affected by in utero SRI exposure, however, those alterations do not correlate to later neurocognitive development as tested by neuropsychological evaluation at two years of age. In turn, phase-amplitude coupling was found to be suppressed in SRI infants across multiple distributed cortical regions and these effects were linked to their neurocognitive outcomes. Our results are compatible with the overall notion that in utero drug exposures may cause subtle, yet measurable changes in the brain structure and function. Our present findings are based on the measures of local and inter-areal neuronal interactions in the cortex which can be readily used across species, as well as between different scales of inspection: from the whole animals to in vitro preparations. Therefore, this work opens a framework to explore the cellular and molecular mechanisms underlying neurodevelopmental SRI effects at all translational levels.

Profile of minor neurological findings after perinatal asphyxia

Aim

To characterise the spectrum of findings in sequential neurological examinations, general movements (GM) assessment and magnetic resonance imaging (MRI) of infants with perinatal asphyxia.

Methods

The prospective cohort study of term infants with perinatal asphyxia treated at Helsinki University Hospital's neonatal units in 2016–2020 used Hammersmith Neonatal Neurological Examination (HNNE) and brain MRI at 2 weeks and Hammersmith Infant Neurological Examination (HINE) and GM assessment at 3 months of age.

Results

Analysis included 50 infants: 33 displaying perinatal asphyxia without hypoxic‐ischaemic encephalopathy (HIE), seven with HIE1 and 10 with HIE2. Of the infants with atypical HNNE findings, 24/25 perinatal asphyxia without HIE cases, 5/6 HIE1 cases and all 10 HIE2 cases showed atypical findings in the HINE. The HINE identified atypical spontaneous movements significantly more often in infants with white matter T2 hyperintensity.

Conclusion

In this cohort, most infants with perinatal asphyxia, with or without HIE, presented atypical neurological findings in sequential examinations. The profile of neurological findings for children with perinatal asphyxia without HIE resembled that of children with HIE. White matter T2 hyperintensity was associated with atypical spontaneous movements in the HINE and was a frequent MRI finding also in perinatal asphyxia without HIE.

Ensemble Learning Using Individual Neonatal Data for Seizure Detection

Objective: Sharing medical data between institutions is difficult in practice due to data protection laws and official procedures within institutions. Therefore, most existing algorithms are trained on relatively small electroencephalogram (EEG) data sets which is likely to be detrimental to prediction accuracy. In this work, we simulate a case when the data can not be shared by splitting the publicly available data set into disjoint sets representing data in individual institutions. Methods and procedures: We propose to train a (local) detector in each institution and aggregate their individual predictions into one final prediction. Four aggregation schemes are compared, namely, the majority vote, the mean, the weighted mean and the Dawid-Skene method. The method was validated on an independent data set using only a subset of EEG channels. Results: The ensemble reaches accuracy comparable to a single detector trained on all the data when sufficient amount of data is available in each institution. Conclusion: The weighted mean aggregation scheme showed best performance, it was only marginally outperformed by the Dawid–Skene method when local detectors approach performance of a single detector trained on all available data. Clinical impact: Ensemble learning allows training of reliable algorithms for neonatal EEG analysis without a need to share the potentially sensitive EEG data between institutions.

Phase-Based Cortical Synchrony Is Affected by Prematurity

Inter-areal synchronization by phase–phase correlations (PPCs) of cortical oscillations mediates many higher neurocognitive functions, which are often affected by prematurity, a globally prominent neurodevelopmental risk factor. Here, we used electroencephalography to examine brain-wide cortical PPC networks at term-equivalent age, comparing human infants after early prematurity to a cohort of healthy controls. We found that prematurity affected these networks in a sleep state-specific manner, and the differences between groups were also frequency-selective, involving brain-wide connections. The strength of synchronization in these networks was predictive of clinical outcomes in the preterm infants. These findings show that prematurity affects PPC networks in a clinically significant manner, suggesting early functional biomarkers of later neurodevelopmental compromise that may be used in clinical or translational studies after early neonatal adversity.

Recording activity in proximal muscle networks with surface EMG in assessing infant motor development

OBJECTIVE

To develop methods for recording and analysing infant's proximal muscle activations.

METHODS

Surface electromyography (sEMG) of truncal muscles was recorded in three months old infants (N = 18) during spontaneous movement and controlled postural changes. The infants were also divided into two groups according to motor performance. We developed an efficient method for removing dynamic cardiac artefacts to allow i) accurate estimation of individual muscle activations, as well as ii) quantitative characterization of muscle networks.

RESULTS

The automated removal of cardiac artefacts allowed quantitation of truncal muscle activity, which showed predictable effects during postural changes, and there were differences between high and low performing infants.The muscle networks showed consistent change in network density during spontaneous movements between supine and prone position. Moreover, activity correlations in individual pairs of back muscles linked to infant́s motor performance.

CONCLUSIONS

The hereby developed sEMG analysis methodology is feasible and may disclose differences between high and low performing infants. Analysis of the muscle networks may provide novel insight to central control of motility.

SIGNIFICANCE

Quantitative analysis of infant's muscle activity and muscle networks holds promise for an objective neurodevelopmental assessment of motor system.

An openly available wearable, a diaper cover, monitors infant's respiration and position during rest and sleep

AIM

To describe and test the accuracy of respiratory rate assessment in long-term surveillance using an open-source infant wearable, NAPping PAnts (NAPPA).

METHODS

We recorded 24 infants aged 1-9 months using our newly developed infant wearable that is a diaper cover with an integrated programmable electronics with accelerometer and gyroscope sensors. The sensor collects child's respiration rate (RR), activity and body posture in 30-s epochs, to be downloaded afterwards into a mobile phone application. An automated RR quality measure was also implemented using autocorrelation function, and the accuracy of RR estimate was compared with a reference obtained from the simultaneously recorded capnography signal that was part of polysomnography recordings.

RESULTS

Altogether 88 h 27 min of data were recorded, and 4147 epochs (39% of all data) were accepted after quality detection. The median of patient wise mean absolute errors in RR estimates was 1.5 breaths per minute (interquartile range 1.1-2.6 bpm), and the Blandt-Altman analysis indicated an RR bias of 0.0 bpm with the 95% limits of agreement of -5.7-5.7 bpm.

CONCLUSION

Long-term monitoring of RR and posture can be done with reasonable accuracy in out-of-hospital settings using NAPPA, an openly available infant wearable.

Impact of In Utero Exposure to Antiepileptic Drugs on Neonatal Brain Function

In utero brain development underpins brain health across the lifespan but is vulnerable to physiological and pharmacological perturbation. Here, we show that antiepileptic medication during pregnancy impacts on cortical activity during neonatal sleep, a potent indicator of newborn brain health. These effects are evident in frequency-specific functional brain networks and carry prognostic information for later neurodevelopment. Notably, such effects differ between different antiepileptic drugs that suggest neurodevelopmental adversity from exposure to antiepileptic drugs and not maternal epilepsy per se. This work provides translatable bedside metrics of brain health that are sensitive to the effects of antiepileptic drugs on postnatal neurodevelopment and carry direct prognostic value.

Automated detection of artefacts in neonatal EEG with residual neural networks

BACKGROUND AND OBJECTIVE

To develop a computational algorithm that detects and identifies different artefact types in neonatal electroencephalography (EEG) signals.

METHODS

As part of a larger algorithm, we trained a Residual Deep Neural Network on expert human annotations of EEG recordings from 79 term infants recorded in a neonatal intensive care unit (112 h of 18-channel recording). The network was trained using 10 fold cross validation in Matlab. Artefact types included: device interference, EMG, movement, electrode pop, and non-cortical biological rhythms. Performance was assessed by prediction statistics and further validated on a separate independent dataset of 13 term infants (143 h of 3-channel recording). EEG pre-processing steps, and other post-processing steps such as averaging probability over a temporal window, were also included in the algorithm.

RESULTS

The Residual Deep Neural Network showed high accuracy (95%) when distinguishing periods of clean, artefact-free EEG from any kind of artefact, with a median accuracy for individual patient of 91% (IQR: 81%-96%). The accuracy in identifying the five different types of artefacts ranged from 57%-92%, with electrode pop being the hardest to detect and EMG being the easiest. This reflected the proportion of artefact available in the training dataset. Misclassification as clean was low for each artefact type, ranging from 1%-11%. The detection accuracy was lower on the validation set (87%). We used the algorithm to show that EEG channels located near the vertex were the least susceptible to artefact.

CONCLUSION

Artefacts can be accurately and reliably identified in the neonatal EEG using a deep learning algorithm. Artefact detection algorithms can provide continuous bedside quality assessment and support EEG review by clinicians or analysis algorithms.

Building an Open Source Classifier for the Neonatal EEG Background: A Systematic Feature-Based Approach From Expert Scoring to Clinical Visualization

Neonatal brain monitoring in the neonatal intensive care units (NICU) requires a continuous review of the spontaneous cortical activity, i.e., the electroencephalograph (EEG) background activity. This needs development of bedside methods for an automated assessment of the EEG background activity. In this paper, we present development of the key components of a neonatal EEG background classifier, starting from the visual background scoring to classifier design, and finally to possible bedside visualization of the classifier results. A dataset with 13,200 5-minute EEG epochs (8–16 channels) from 27 infants with birth asphyxia was used for classifier training after scoring by two independent experts. We tested three classifier designs based on 98 computational features, and their performance was assessed with respect to scoring system, pre- and post-processing of labels and outputs, choice of channels, and visualization in monitor displays. The optimal solution achieved an overall classification accuracy of 97% with a range across subjects of 81–100%. We identified a set of 23 features that make the classifier highly robust to the choice of channels and missing data due to artefact rejection. Our results showed that an automated bedside classifier of EEG background is achievable, and we publish the full classifier algorithm to allow further clinical replication and validation studies.

Detrended fluctuation analysis in the presurgical evaluation of parietal lobe epilepsy patients

OBJECTIVE

To examine the usability of long-range temporal correlations (LRTCs) in non-invasive localization of the epileptogenic zone (EZ) in refractory parietal lobe epilepsy (RPLE) patients.

METHODS

We analyzed 10 RPLE patients who had presurgical MEG and underwent epilepsy surgery. We quantified LRTCs with detrended fluctuation analysis (DFA) at four frequency bands for 200 cortical regions estimated using individual source models. We correlated individually the DFA maps to the distance from the resection area and from cortical locations of interictal epileptiform discharges (IEDs). Additionally, three clinical experts inspected the DFA maps to visually assess the most likely EZ locations.

RESULTS

The DFA maps correlated with the distance to resection area in patients with type II focal cortical dysplasia (FCD) (p<0.05), but not in other etiologies. Similarly, the DFA maps correlated with the IED locations only in the FCD II patients. Visual analysis of the DFA maps showed high interobserver agreement and accuracy in FCD patients in assigning the affected hemisphere and lobe.

CONCLUSIONS

Aberrant LRTCs correlate with the resection areas and IED locations.

SIGNIFICANCE

This methodological pilot study demonstrates the feasibility of approximating cortical LRTCs from MEG that may aid in the EZ localization and provide new non-invasive insight into the presurgical evaluation of epilepsy.

The ILAE classification of seizures and the epilepsies: Modification for seizures in the neonate. Position paper by the ILAE Task Force on Neonatal Seizures

Seizures are the most common neurological emergency in the neonatal period and in contrast to those in infancy and childhood, are often provoked seizures with an acute cause and may be electrographic-only. Hence, neonatal seizures may not fit easily into classification schemes for seizures and epilepsies primarily developed for older children and adults. A Neonatal Seizures Task Force was established by the International League Against Epilepsy (ILAE) to develop a modification of the 2017 ILAE Classification of Seizures and Epilepsies, relevant to neonates. The neonatal classification framework emphasizes the role of electroencephalography (EEG) in the diagnosis of seizures in the neonate and includes a classification of seizure types relevant to this age group. The seizure type is determined by the predominant clinical feature. Many neonatal seizures are electrographic-only with no evident clinical features; therefore, these are included in the proposed classification. Clinical events without an EEG correlate are not included. Because seizures in the neonatal period have been shown to have a focal onset, a division into focal and generalized is unnecessary. Seizures can have a motor (automatisms, clonic, epileptic spasms, myoclonic, tonic), non-motor (autonomic, behavior arrest), or sequential presentation. The classification allows the user to choose the level of detail when classifying seizures in this age group.

Towards multimodal brain monitoring in asphyxiated newborns with amplitude-integrated EEG and simultaneous somatosensory evoked potentials

BACKGROUND

Somatosensory evoked potentials (SEPs) offer an additional bedside tool for outcome prediction after perinatal asphyxia.

AIMS

To assess the reliability of SEPs recorded with bifrontoparietal amplitude-integrated electroencephalography (aEEG) brain monitoring setup for outcome prediction in asphyxiated newborns undergoing therapeutic hypothermia.

STUDY DESIGN

Retrospective observational single-center study.

SUBJECTS

27 consecutive asphyxiated full- or near-term newborns (25 under hypothermia) that underwent median nerve aEEG-SEPs as part of their clinical evaluation at the neonatal intensive care unit of Helsinki University Hospital.

OUTCOME MEASURES

aEEG-SEP classification (present, absent or unreliable) was compared to classification of SEPs recorded with a full EEG montage (EEG-SEP), and outcome determined from medical records at approximately 12-months-age. Unfavorable outcome included death, cerebral palsy, or severe epilepsy.

RESULTS

The aEEG-SEP and EEG-SEP classifications were concordant in 21 of the 22 newborns with both recordings available. All five newborns with bilaterally absent aEEG-SEPs had absent EEG-SEPs and the four with outcome information available had an unfavorable outcome (one was lost to follow-up). Of the newborns with aEEG-SEPs present, all with follow-up exams available had bilaterally present EEG-SEPs and a favorable outcome (one was lost to follow-up). One newborn with unilaterally absent aEEG-SEP at 25 h of age had bilaterally present EEG-SEPs on the next day, and a favorable outcome.

CONCLUSIONS

aEEG-SEPs recorded during therapeutic hypothermia on the first postnatal days are reliable for assessing brain injury severity. Adding SEP into routine aEEG brain monitoring offers an additional tool for very early outcome prediction after birth asphyxia.

An Open Source Classifier for Bed Mattress Signal in Infant Sleep Monitoring

Objective

To develop a non-invasive and clinically practical method for a long-term monitoring of infant sleep cycling in the intensive care unit.

Methods

Forty three infant polysomnography recordings were performed at 1–18 weeks of age, including a piezo element bed mattress sensor to record respiratory and gross-body movements. The hypnogram scored from polysomnography signals was used as the ground truth in training sleep classifiers based on 20,022 epochs of movement and/or electrocardiography signals. Three classifier designs were evaluated in the detection of deep sleep (N3 state): support vector machine (SVM), Long Short-Term Memory neural network, and convolutional neural network (CNN).

Results

Deep sleep was accurately identified from other states with all classifier variants. The SVM classifier based on a combination of movement and electrocardiography features had the highest performance (AUC 97.6%). A SVM classifier based on only movement features had comparable accuracy (AUC 95.0%). The feature-independent CNN resulted in roughly comparable accuracy (AUC 93.3%).

Conclusion

Automated non-invasive tracking of sleep state cycling is technically feasible using measurements from a piezo element situated under a bed mattress.

Significance

An open source infant deep sleep detector of this kind allows quantitative, continuous bedside assessment of infant’s sleep cycling.