Reliability and accuracy of EEG interpretation for estimating age in preterm infants

Quantitative assessment of neurodevelopmental maturation: a comprehensive systematic literature review of artificial intelligence-based brain age prediction in pediatric populations

Introduction

Over the past few decades, numerous researchers have explored the application of machine learning for assessing children's neurological development. Developmental changes in the brain could be utilized to gauge the alignment of its maturation status with the child's chronological age. AI is trained to analyze changes in different modalities and estimate the brain age of subjects. Disparities between the predicted and chronological age can be viewed as a biomarker for a pathological condition. This literature review aims to illuminate research studies that have employed AI to predict children's brain age.

Methods

The inclusion criteria for this study were predicting brain age via AI in healthy children up to 12 years. The search term was centered around the keywords "pediatric," "artificial intelligence," and "brain age" and was utilized in PubMed and IEEEXplore. The selected literature was then examined for information on data acquisition methods, the age range of the study population, pre-processing, methods and AI techniques utilized, the quality of the respective techniques, model explanation, and clinical applications.

Results

Fifty one publications from 2012 to 2024 were included in the analysis. The primary modality of data acquisition was MRI, followed by EEG. Structural and functional MRI-based studies commonly used publicly available datasets, while EEG-based studies typically relied on self-recruitment. Many studies utilized pre-processing pipelines provided by toolkit suites, particularly in MRI-based research. The most frequently used model type was kernel-based learning algorithms, followed by convolutional neural networks. Overall, prediction accuracy may improve when multiple acquisition modalities are used, but comparing studies is challenging. In EEG, the prediction error decreases as the number of electrodes increases. Approximately one-third of the studies used explainable artificial intelligence methods to explain the model and chosen parameters. However, there is a significant clinical translation gap as no study has tested their model in a clinical routine setting.

Discussion

Further research should test on external datasets and include low-quality routine images for MRI. T2-weighted MRI was underrepresented. Furthermore, different kernel types should be compared on the same dataset. Implementing modern model architectures, such as convolutional neural networks, should be the next step in EEG-based research studies.

Resting state electroencephalographic brain activity in neonates can predict age and is indicative of neurodevelopmental outcome

OBJECTIVE

Electroencephalography (EEG) can be used to estimate neonates' biological brain age. Discrepancies between postmenstrual age and brain age, termed the brain age gap, can potentially quantify maturational deviation. Existing brain age EEG models are not well suited to clinical cot-side use for estimating neonates' brain age gap due to their dependency on relatively large data and pre-processing requirements.

METHODS

We trained a deep learning model on resting state EEG data from preterm neonates with normal neurodevelopmental Bayley Scale of Infant and Toddler Development (BSID) outcomes, using substantially reduced data requirements. We subsequently tested this model in two independent datasets from two clinical sites.

RESULTS

In both test datasets, using only 20 min of resting-state EEG activity from a single channel, the model generated accurate age predictions: mean absolute error = 1.03 weeks (p-value = 0.0001) and 0.98 weeks (p-value = 0.0001). In one test dataset, where 9-month follow-up BSID outcomes were available, the average neonatal brain age gap in the severe abnormal outcome group was significantly larger than that of the normal outcome group: difference in mean brain age gap = 0.50 weeks (p-value = 0.04).

CONCLUSIONS

These findings demonstrate that the deep learning model generalises to independent datasets from two clinical sites, and that the model's brain age gap magnitudes differ between neonates with normal and severe abnormal follow-up neurodevelopmental outcomes.

SIGNIFICANCE

The magnitude of neonates' brain age gap, estimated using only 20 min of resting state EEG data from a single channel, can encode information of clinical neurodevelopmental value.

The Use of Midazolam as an Antiseizure Medication in Neonatal Seizures: Single Center Experience and Literature Review

BACKGROUND

Existing therapeutic alternatives for neonatal crises have expanded in recent decades, but no consensus has been reached on protocols based on neonatal seizures. In particular, little is known about the use of midazolam in newborns.

AIM

The aim of our study is to evaluate the response to midazolam, the appearance of side effects, and their impact on therapeutic decisions.

METHODS

This is a STROBE-conformed retrospective observational study of 10 patients with neonatal seizures unresponsive to common antiseizure drugs, admitted to San Marco University Hospital's neonatal intensive care (Catania, Italy) from September 2015 to October 2022. In our database search, 36 newborns were treated with midazolam, but only ten children met the selection criteria for this study.

RESULTS

Response was assessed both clinically and electrographic. Only 4 patients at the end of the treatment showed a complete electroclinical response; they were full-term infants with a postnatal age greater than 7 days. Non-responders and partial responders are all premature (4/10) or full-term neonates who started therapy in the first days of life (< 7th day) (2/10).

CONCLUSION

Neonatal seizures in preterm show a lower response rate to midazolam than seizures in full-term infants, with poorer prognosis. Liver and renal function and central nervous system development are incomplete in premature infants and the first days of life. In this study, we show that midazolam, a short-acting benzodiazepine, appears to be most effective in full-term infants and after 7 days of life.

Bedside tracking of functional autonomic age in preterm infants

BACKGROUND

Preterm birth predisposes infants to adverse outcomes that, without early intervention, impacts their long-term health. To assist bedside monitoring, we developed a tool to track the autonomic maturation of the preterm by assessing heart rate variability (HRV) changes during intensive care.

METHODS

Electrocardiogram (ECG) recordings were longitudinally recorded in 67 infants (26-38 weeks postmenstrual age (PMA)). Supervised machine learning was used to generate a functional autonomic age (FAA), by combining 50 computed HRV features from successive 5-minute ECG epochs (median of 23 epochs per infant). Performance of the FAA was assessed by correlation to PMA, clinical outcomes and the infant's functional brain age (FBA), an index of maturation derived from the electroencephalogram.

RESULTS

The FAA was strongly correlated to PMA (r = 0.86, 95% CI: 0.83-0.93) with a mean absolute error (MAE) of 1.66 weeks and also accurately estimated FBA (MAE = 1.58 weeks, n = 54 infants). The relationship between PMA and FAA was not confounded by neurodevelopmental outcome (p = 0.18, n = 45), sex (p = 0.88, n = 56), patent ductus arteriosus (p = 0.08, n = 56), IVH (p = 0.63, n = 56) or body weight at birth (p = 0.95, n = 56).

CONCLUSIONS

The FAA, an index derived from the ubiquitous ECG signal, offers direct avenues towards estimating autonomic maturation at the bedside during intensive care monitoring.

IMPACT

The development of a tool to track functional autonomic age in preterm infants based on heart rate variability features in the electrocardiogram provides a rapid and specialized view of autonomic maturation at the bedside. Functional autonomic age is linked closely to postmenstrual age and central nervous system function response, as determined by its relationship to functional brain age from the electroencephalogram. Tracking functional autonomic age during neonatal intensive care unit monitoring offers a unique insight into cardiovascular health in infants born extremely preterm and their maturational trajectories to term age.

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.

Amplitude-integrated EEG recorded at 32 weeks postconceptional age. Correlation with MRI at term

OBJECTIVE

The study aims to establish the role of late aEEG (scored by Burdjalov) in predicting brain maturation as well as abnormalities evaluated at term equivalent age (TEA) by brain MRI.

METHODS

91 infants born before 30 wks gestation underwent an aEEG monitoring at 32 wks postconceptional age (PCA). aEEG, was correlated with TEA MRI, scored by Kidokoro.

RESULTS

A significant correlation between the aEEG score and the MRI scores was found. The same results were obtained for the aEEG continuity score; cyclicity and bandwidth scores were associated with grey matter and cerebellar MRI items. Moreover, a correlation between aEEG and cEEG recorded both at 32 and 40 wks PCA, was found.

CONCLUSIONS

aEEG monitoring can be predictive of MRI findings at TEA, suggesting that it could be implemented as a useful tool to support ultrasound to help identify neonates who will benefit from early intervention services.

A practical approach toward interpretation of amplitude integrated electroencephalography in preterm infants

The developing preterm brain is vulnerable to injury, especially during periods of clinical instability; therefore, monitoring the brain may provide important information on brain health. Over the last 2 decades, a growing body of literature has been reported on preterm amplitude integrated electroencephalography (aEEG) with regards to normative data and associations with adverse outcomes. Despite this, the use of aEEG for preterm infants remains mostly a research tool with limited clinical applicability. In this article, we review the literature on normal and abnormal aEEG patterns in preterm infants and propose a stepwise clinical algorithm for aEEG assessment at the bedside that takes into account assessment of maturation and identification of pathological patterns.

CONCLUSION

This algorithm may be used by clinicians at the bedside for interpretation to integrate it in clinical practice for neurological surveillance of preterm infants.

WHAT IS KNOWN

• Studies have reported normative data on aEEG in preterm infants for different gestational ages. • Burst suppression pattern and absent sleep-wake cycling have been described to be associated with brain pathology and adverse outcomes in preterm infants.

WHAT IS NEW

• We have synthesized aEEG characteristics in preterm infants across the spectrum of prematurity reported in the literature. • We present a stepwise approach for clinically applicable interpretation of aEEG in preterm infants.

Functional brain maturation and sleep organisation in neonates with congenital heart disease

OBJECTIVE

Neonates with Congenital Heart Disease (CHD) have structural delays in brain development. To evaluate whether functional brain maturation and sleep-wake physiology is also disturbed, the Functional Brain Age (FBA) and sleep organisation on EEG during the neonatal period is investigated.

METHODS

We compared 15 neonates with CHD who underwent multichannel EEG with healthy term newborns of the same postmenstrual age, including subgroup analysis for d-Transposition of the Great Arteries (d-TGA) (n = 8). To estimate FBA, a prediction tool using quantitative EEG features as input, was applied. Second, the EEG was automatically classified into the 4 neonatal sleep stages. Neonates with CHD underwent neurodevelopmental testing using the Bayley Scale of Infant Development-III at 24 months.

RESULTS

Preoperatively, the FBA was delayed in CHD infants and more so in d-TGA infants. The FBA was positively correlated with motor scores. Sleep organisation was significantly altered in neonates with CHD. The duration of the sleep cycle and the proportion of Active Sleep Stage 1 was decreased, again more marked in the d-TGA infants. Neonates with d-TGA spent less time in High Voltage Slow Wave Sleep and more in Tracé Alternant compared to healthy terms. Both FBA and sleep organisation normalised postoperatively. The duration of High Voltage Slow Wave Sleep remained positively correlated with motor scores in d-TGA infants.

INTERPRETATION

Altered early brain function and sleep is present in neonates with CHD. These results are intruiging, as inefficient neonatal sleep has been linked with adverse long-term outcome. Identifying how these rapid alterations in brain function are mitigated through improvements in cerebral oxygenation, surgery, drugs and nutrition may have relevance for clinical practice and outcome.

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.