Quantitative approach to early neonatal EEG visual analysis in hypoxic-ischemic encephalopathy severity: Bridging the gap between eyes and machine

Early automated classification of neonatal hypoxic-ischemic encephalopathy - An aid to the decision to use therapeutic hypothermia

OBJECTIVE

The study aimed to address the challenge of early assessment of neonatal hypoxic-ischemic encephalopathy (HIE) severity to identify candidates for therapeutic hypothermia (TH). The objective was to develop an automated classification model for neonatal EEGs, enabling accurate HIE severity assessment 24/7.

METHODS

EEGs recorded within 6 h of life after perinatal anoxia were visually graded into 3 severity groups (HIE French Classification) and quantified using 6 qEEG markers measuring amplitude, continuity and frequency content. Machine learning models were developed on a dataset of 90 EEGs and validated on an independent dataset of 60 EEGs.

RESULTS

The selected model achieved an overall accuracy of 80.6% in the development phase and 80% in the validation phase. Notably, the model accurately identified 28 out of 30 children for whom TH was indicated after visual EEG analysis, with only 2 cases (moderate EEG abnormalities) not recommended for cooling.

CONCLUSIONS

The combination of clinically relevant qEEG markers led to the development of an effective automated EEG classification model, particularly suited for the post-anoxic latency phase. This model successfully discriminated neonates requiring TH.

SIGNIFICANCE

The proposed model has potential as a bedside clinical decision support tool for TH.

Advances in Electroencephalographic Biomarkers of Neonatal Hypoxic Ischemic Encephalopathy

Electroencephalography (EEG) is a key objective biomarker of newborn brain function, delivering critical, cotside insights to aid the management of encephalopathy. Access to continuous EEG is limited, forcing reliance on subjective clinical assessments. In hypoxia ischaemia, the primary cause of encephalopathy, alterations in EEG patterns correlate with. injury severity and evolution. As HIE evolves, causing secondary neuronal death, EEG can track injury progression, informing neuroprotective strategies, seizure management and prognosis. Despite its value, challenges with interpretation and lack of on site expertise has limited its broader adoption. Technological advances, particularly in digital EEG and machine learning, are enhancing real-time analysis. This will allow EEG to expand its role in HIE diagnosis, management and outcome prediction.

Quantitative EEG and prediction of outcome in neonatal encephalopathy: a review

Electroencephalogram (EEG) is an important biomarker for neonatal encephalopathy (NE) and has significant predictive value for brain injury and neurodevelopmental outcomes. Quantitative analysis of EEG involves the representation of complex EEG data in an objective, reproducible and scalable manner. Quantitative EEG (qEEG) can be derived from both a limited channel EEG (as available during amplitude integrated EEG) and multi-channel conventional EEG. It has the potential to enable bedside clinicians to monitor and evaluate details of cortical function without the necessity of continuous expert input. This is particularly useful in NE, a dynamic and evolving condition. In these infants, continuous, detailed evaluation of cortical function at the bedside is a valuable aide to management especially in the current era of therapeutic hypothermia and possible upcoming neuroprotective therapies. This review discusses the role of qEEG in newborns with NE and its use in informing monitoring and therapy, along with its ability to predict imaging changes and short and long-term neurodevelopmental outcomes. IMPACT: Quantitative representation of EEG data brings the evaluation of continuous brain function, from the neurophysiology lab to the NICU bedside and has a potential role as a biomarker for neonatal encephalopathy. Clinical and research applications of quantitative EEG in the newborn are rapidly evolving and a wider understanding of its utility is valuable. This overview summarizes the role of quantitative EEG at different timepoints, its relevance to management and its predictive value for short- and long-term outcomes in neonatal encephalopathy.

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.

A Comparison of Automatically Extracted Quantitative EEG Features for Seizure Risk Stratification in Neonatal Encephalopathy

PURPOSE

Seizures occur in up to 40% of neonates with neonatal encephalopathy. Earlier identification of seizures leads to more successful seizure treatment, but is often delayed because of limited availability of continuous EEG monitoring. Clinical variables poorly stratify seizure risk, and EEG use to stratify seizure risk has previously been limited by need for manual review and artifact exclusion. The goal of this study is to compare the utility of automatically extracted quantitative EEG (qEEG) features for seizure risk stratification.

METHODS

We conducted a retrospective analysis of neonates with moderate-to-severe neonatal encephalopathy who underwent therapeutic hypothermia at a single center. The first 24 hours of EEG underwent automated artifact removal and qEEG analysis, comparing qEEG features for seizure risk stratification.

RESULTS

The study included 150 neonates and compared the 36 (23%) with seizures with those without. Absolute spectral power best stratified seizure risk with area under the curve ranging from 63% to 71%, followed by range EEG lower and upper margin, median and SD of the range EEG lower margin. No features were significantly more predictive in the hour before seizure onset. Clinical examination was not associated with seizure risk.

CONCLUSIONS

Automatically extracted qEEG features were more predictive than clinical examination in stratifying neonatal seizure risk during therapeutic hypothermia. qEEG represents a potential practical bedside tool to individualize intensity and duration of EEG monitoring and decrease time to seizure recognition. Future work is needed to refine and combine qEEG features to improve risk stratification.

Quantitative EEG features during the first day correlate to clinical outcome in perinatal asphyxia

OBJECTIVE

To assess whether computational electroencephalogram (EEG) measures during the first day of life correlate to clinical outcomes in infants with perinatal asphyxia with or without hypoxic-ischemic encephalopathy (HIE).

METHODS

We analyzed four-channel EEG monitoring data from 91 newborn infants after perinatal asphyxia. Altogether 42 automatically computed amplitude- and synchrony-related EEG features were extracted as 2-hourly average at very early (6 h) and early (24 h) postnatal age; they were correlated to the severity of HIE in all infants, and to four clinical outcomes available in a subcohort of 40 newborns: time to full oral feeding (nasogastric tube NGT), neonatal brain MRI, Hammersmith Infant Neurological Examination (HINE) at three months, and Griffiths Scales at two years.

RESULTS

At 6 h, altogether 14 (33%) EEG features correlated significantly to the HIE grade ([r]= 0.39-0.61, p < 0.05), and one feature correlated to NGT ([r]= 0.50). At 24 h, altogether 13 (31%) EEG features correlated significantly to the HIE grade ([r]= 0.39-0.56), six features correlated to NGT ([r]= 0.36-0.49) and HINE ([r]= 0.39-0.61), while no features correlated to MRI or Griffiths Scales.

CONCLUSIONS

Our results show that the automatically computed measures of early cortical activity may provide outcome biomarkers for clinical and research purposes.

IMPACT

The early EEG background and its recovery after perinatal asphyxia reflect initial severity of encephalopathy and its clinical recovery, respectively. Computational EEG features from the early hours of life show robust correlations to HIE grades and to early clinical outcomes. Computational EEG features may have potential to be used as cortical activity biomarkers in early hours after perinatal asphyxia.

Macroperiodic Oscillations: A Potential Novel Biomarker of Outcome in Neonatal Encephalopathy

PURPOSE

Neonatal encephalopathy (NE) is a common cause of neurodevelopmental morbidity. Tools to accurately predict outcomes after therapeutic hypothermia remain limited. We evaluated a novel EEG biomarker, macroperiodic oscillations (MOs), to predict neurodevelopmental outcomes.

METHODS

We conducted a secondary analysis of a randomized controlled trial of neonates with moderate-to-severe NE who underwent standardized clinical examination, magnetic resonance (MR) scoring, video EEG, and neurodevelopmental assessment with Bayley III evaluation at 18 to 24 months. A non-NE cohort of neonates was also assessed for the presence of MOs. The relationship between clinical examination, MR score, MOs, and neurodevelopmental assessment was analyzed.

RESULTS

The study included 37 neonates with 24 of whom survived and underwent neurodevelopmental assessment (70%). The strength of MOs correlated with severity of clinical encephalopathy. MO strength and spread significantly correlated with Bayley III cognitive percentile ( P = 0.017 and 0.046). MO strength outperformed MR score in predicting a combined adverse outcome of death or disability ( P = 0.019, sensitivity 100%, specificity 77% vs. P = 0.079, sensitivity 100%, specificity 59%).

CONCLUSIONS

MOs are an EEG-derived, quantitative biomarker of neurodevelopmental outcome that outperformed a comprehensive validated MRI injury score and a detailed systematic discharge examination in this small cohort. Future work is needed to validate MOs in a larger cohort and elucidate the underlying pathophysiology of MOs.

Deep Learning for Generalized EEG Seizure Detection after Hypoxia-Ischemia-Preclinical Validation

Brain maturity and many clinical treatments such as therapeutic hypothermia (TH) can significantly influence the morphology of neonatal EEG seizures after hypoxia-ischemia (HI), and so there is a need for generalized automatic seizure identification. This study validates efficacy of advanced deep-learning pattern classifiers based on a convolutional neural network (CNN) for seizure detection after HI in fetal sheep and determines the effects of maturation and brain cooling on their accuracy. The cohorts included HI-normothermia term (n = 7), HI-hypothermia term (n = 14), sham-normothermia term (n = 5), and HI-normothermia preterm (n = 14) groups, with a total of >17,300 h of recordings. Algorithms were trained and tested using leave-one-out cross-validation and k-fold cross-validation approaches. The accuracy of the term-trained seizure detectors was consistently excellent for HI-normothermia preterm data (accuracy = 99.5%, area under curve (AUC) = 99.2%). Conversely, when the HI-normothermia preterm data were used in training, the performance on HI-normothermia term and HI-hypothermia term data fell (accuracy = 98.6%, AUC = 96.5% and accuracy = 96.9%, AUC = 89.6%, respectively). Findings suggest that HI-normothermia preterm seizures do not contain all the spectral features seen at term. Nevertheless, an average 5-fold cross-validated accuracy of 99.7% (AUC = 99.4%) was achieved from all seizure detectors. This significant advancement highlights the reliability of the proposed deep-learning algorithms in identifying clinically translatable post-HI stereotypic seizures in 256Hz recordings, regardless of maturity and with minimal impact from hypothermia.

Serum biomarkers of hypoxic-ischemic brain injury

Brain injury is a multifaceted condition arising from nonspecific damage to nervous tissue. The resulting cognitive developmental impairments reverberate through patients' lives, affecting their families, and even the broader economic landscape. The significance of early brain injury detection lies in its potential to stave off severe consequences and enhance the effectiveness of tailored therapeutic interventions. While established methods like neuroimaging and neurophysiology serve as valuable diagnostic tools, their demanding nature restricts their accessibility, particularly in scenarios such as small hospitals, nocturnal or weekend shifts, and cases involving unstable patients. Hence, there is a pressing need for more accessible and efficient diagnostic avenues. Among the spectrum of brain injuries, hypoxic-ischemic encephalopathy stands out as a predominant affliction in the pediatric population. Diagnosing brain injuries in newborns presents challenges due to the subjective nature of assessments like Apgar scores and the inherent uncertainty in neurological examinations. In this context, methods like magnetic resonance and ultrasound hold recommendations for more accurate diagnosis. Recognizing the potential of serum biomarkers derived from blood samples, this paper underscores their promise as a more expedient and resource-efficient means of assessing brain injuries. The review compiles current insights into serum biomarkers, drawing from experiments conducted on animal models as well as human brain pathologies. The authors aim to elucidate specific characteristics, temporal profiles, and the available corpus of experimental and clinical data for serum biomarkers specific to brain injuries. These include neuron-specific enolase (NSE), ubiquitin carboxy-terminal hydrolase L1 (UCH-L1), S100 calcium-binding protein beta (S100B), glial fibrillary acidic protein (GFAP), and high-mobility-group-protein-box-1 (HMGB1). This comprehensive endeavor contributes to advancing the understanding of brain injury diagnostics and potential avenues for therapeutic intervention.

Fetal brain response to worsening acidosis: an experimental study in a fetal sheep model of umbilical cord occlusions

Perinatal anoxia remains an important public health problem as it can lead to hypoxic-ischaemic encephalopathy (HIE) and cause significant neonatal mortality and morbidity. The mechanisms of the fetal brain's response to hypoxia are still unclear and current methods of in utero HIE prediction are not reliable. In this study, we directly analysed the brain response to hypoxia in fetal sheep using in utero EEG. Near-term fetal sheep were subjected to progressive hypoxia induced by repeated umbilical cord occlusions (UCO) at increasing frequency. EEG changes during and between UCO were analysed visually and quantitatively, and related with gasometric and haemodynamic data. EEG signal was suppressed during occlusions and progressively slowed between occlusions with the increasing severity of the occlusions. Per-occlusion EEG suppression correlated with per-occlusion bradycardia and increased blood pressure, whereas EEG slowing and amplitude decreases correlated with arterial hypotension and respiratory acidosis. The suppression of the EEG signal during cord occlusion, in parallel with cardiovascular adaptation could correspond to a rapid cerebral adaptation mechanism that may have a neuroprotective role. The progressive alteration of the signal with the severity of the occlusions would rather reflect the cerebral hypoperfusion due to the failure of the cardiovascular adaptation mechanisms.

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.

Use of EEG in neonatal hypoxic-ischemic encephalopathy: A French survey of current practice and perspective for improving health care

OBJECTIVES

Controlled therapeutic hypothermia (CTH) is a standard of care in the management of neonatal hypoxic-ischemic encephalopathy HIE in newborns after 36 weeks of gestational age (WGA) in France. The electroencephalogram (EEG) plays a major role in HIE diagnosis and follow-up. We conducted a French national survey on the current use of EEG in newborn undergoing CTH.

METHODS

Between July and October 2021, an email survey was sent to the heads of the Neonatal intensive care units (NICUs) in metropolitan and overseas French departments and territories.

RESULTS

Out of 67, 56 (83%) of NICUs responded. All of them performed CTH in children born after 36 WGA with clinical and biological criteria of moderate to severe HIE. 82% of the NICUs used conventional EEG (cEEG) before 6 h of life (H6), prior to CTH being performed, to inform decisions about its use. However, half of the 56 NICUs had limited access after regular working hours. 51 of the 56 centers (91%) used cEEG, either short-lasting or continuous monitoring during cooling, while 5 centers conducted only amplitude EEG (aEEG). Only 4 of 56 centers (7%) used cEEG systematically both prior to CTH and for continuous monitoring under CTH.

DISCUSSION

The use of cEEG in the management of neonatal HIE was widespread in NICUs, but with significant disparities when considering 24-hour access. The introduction of a centralized neurophysiological on-call system grouping several NICUs would be of major interest for most centers which do not have the facility of EEG outside working hours.

Partial wavelet coherence as a robust method for assessment of neurovascular coupling in neonates with hypoxic ischemic encephalopathy

In neonates with hypoxic ischemic encephalopathy, the computation of wavelet coherence between electroencephalogram (EEG) power and regional cerebral oxygen saturation (rSO2) is a promising method for the assessment of neurovascular coupling (NVC), which in turn is a promising marker for brain injury. However, instabilities in arterial oxygen saturation (SpO2) limit the robustness of previously proposed methods. Therefore, we propose the use of partial wavelet coherence, which can eliminate the influence of SpO2. Furthermore, we study the added value of the novel NVC biomarkers for identification of brain injury compared to traditional EEG and NIRS biomarkers. 18 neonates with HIE were monitored for 72 h and classified into three groups based on short-term MRI outcome. Partial wavelet coherence was used to quantify the coupling between C3-C4 EEG bandpower (2-16 Hz) and rSO2, eliminating confounding effects of SpO2. NVC was defined as the amount of significant coherence in a frequency range of 0.25-1 mHz. Partial wavelet coherence successfully removed confounding influences of SpO2 when studying the coupling between EEG and rSO2. Decreased NVC was related to worse MRI outcome. Furthermore, the combination of NVC and EEG spectral edge frequency (SEF) improved the identification of neonates with mild vs moderate and severe MRI outcome compared to using EEG SEF alone. Partial wavelet coherence is an effective method for removing confounding effects of SpO2, improving the robustness of automated assessment of NVC in long-term EEG-NIRS recordings. The obtained NVC biomarkers are more sensitive to MRI outcome than traditional rSO2 biomarkers and provide complementary information to EEG biomarkers.

The prognostic value of neonatal conventional-EEG monitoring in hypoxic-ischemic encephalopathy during therapeutic hypothermia

AIM

To determine the prognostic value of conventional electroencephalography (EEG) monitoring in neonatal hypoxic-ischemic encephalopathy (HIE).

METHOD

In this multicentre retrospective study, 95 full-term neonates (mean of 39.3wks gestational age [SD  1.4], 36 [38%] females, 59 [62%] males) with HIE (2013-2016) undergoing therapeutic hypothermia were divided between favourable or adverse outcomes. Background EEG activity (French classification scale: 0-1-2-3-4-5) and epileptic seizure burden (epileptic seizure scale: 0-1-2) were graded for seven 6-hour periods. Conventional EEG monitoring was investigated by principal component analysis (PCA), with clustering methods to extract prognostic biomarkers of development at 2 years and infant death.

RESULTS

Eighty-one per cent of infants with an adverse outcome had a French classification scale equal to or greater than 3 after H48 (100% at H6-12). The H6-12 epileptic seizure scale was equal to or greater than 1 for 39%, increased to 52% at H30-36 and then remained equal to or greater than 1 for 39% after H48. Forty-five per cent of infants with a favourable outcome had a H6-12 French classification scale equal to or greater than 3, which dropped to 5% after H48; 13% had a H6-12 epileptic seizure scale equal to or greater than 1 but no seizures after H48. Clustering methods based on PCA showed the high efficiency (96%) of conventional EEG monitoring for outcome prediction and allowed the definition of three prognostic EEG biomarkers: H6-78 French classification scale mean, H6-78 French classification scale slope, and H30-78 epileptic seizure scale mean.

INTERPRETATION

Early lability and recovery of physiological features is prognostic of a favourable outcome. Seizure onset from the second day should also be considered to accurately predict neurodevelopment in HIE and support the importance of conventional EEG monitoring in HIE in infants cooled with therapeutic hypothermia.

WHAT THIS PAPER ADDS

Comprehensive analysis showed the high prognostic efficiency (96%) of conventional electroencephalography (EEG) monitoring. Prognostic EEG biomarkers consist of the grade of background EEG activity, its evolution, and the mean seizure burden. Persistent seizures (H48) without an improvement in background EEG activity were consistently associated with an adverse outcome.

Feasibility of EEG Phase-Amplitude Coupling to Stratify Encephalopathy Severity in Neonatal HIE Using Short Time Window

Goal: It is challenging to clinically discern the severity of neonatal hypoxic ischemic encephalopathy (HIE) within hours after birth in time for therapeutic decision-making for hypothermia. The goal of this study was to determine the shortest duration of the EEG based PAC index to provide real-time guidance for clinical decision-making for neonates with HIE. Methods: Neonates were recruited from a single-center Level III NICU between 2017 and 2019. A time-dependent, PAC-frequency-averaged index, tPACm, was calculated to characterize intrinsic coupling between the amplitudes of 12−30 Hz and the phases of 1−2 Hz oscillation from 6-h EEG data at electrode P3 during the first day of life, using different sizes of moving windows including 10 s, 20 s, 1 min, 2 min, 5 min, 10 min, 20 min, 30 min, 60 min, and 120 min. Time-dependent receiver operating characteristic (ROC) curves were generated to examine the performance of the accurate window tPACm as a neurophysiologic biomarker. Results: A total of 33 neonates (mild-HIE, n = 15 and moderate/severe HIE, n = 18) were enrolled. Mixed effects models demonstrated that tPACm between the two groups was significantly different with window time segments of 3−120 min. By observing the estimates of group differences in tPACm across different window sizes, we found 20 min was the shortest window size to optimally distinguish the two groups (p < 0.001). Time-varying ROC showed significant average area-under-the-curve of 0.82. Conclusions: We demonstrated the feasibility of using tPACm with a 20 min EEG time window to differentiate the severity of HIE and facilitate earlier diagnosis and treatment initiation.

Comparative analysis of background EEG activity based on MRI findings in neonatal hypoxic-ischemic encephalopathy: a standardized, low-resolution, brain electromagnetic tomography (sLORETA) study

Background

It is important to assess the degree of brain injury and predict long-term outcomes in neonates diagnosed with hypoxic-ischemic encephalopathy (HIE). However, routine studies, including magnetic resonance imaging (MRI) and conventional encephalography (EEG) or amplitude-integrated EEG (aEEG), have their own limitations in terms of availability and accuracy of evaluation. Recently, quantitative EEG (qEEG) has been shown to improve the predictive reliability of neonatal HIE and has been further refined with brain mapping techniques.

Methods

We investigated background EEG activities in 29 neonates with HIE who experienced therapeutic hypothermia, via qEEG using a distributed source model. MRI images were evaluated and classified into two groups (normal-to-mild injury vs moderate-to-severe injury), based on a scoring system. Non-parametric statistical analysis using standardized low-resolution brain electromagnetic tomography was performed to compare the current density distribution of four frequency bands (delta, theta, alpha, and beta) between the two groups.

Results

Electrical neuronal activities were significantly lower in the moderate-to-severe injury group compared with the normal-to-mild injury group. Background EEG activities in moderate-to-severe HIE were most significantly reduced in the temporal and parietal lobes. Quantitative EEG also revealed a decrease in background activity at all frequency bands, with a maximum in decrease in the delta component. The maximum difference in current density was found in the inferior parietal lobule of the right parietal lobe for the delta frequency band.

Conclusions

Our study demonstrated quantitative and topographical changes in EEG in moderate-to-severe neonatal HIE. They also suggest possible implementation and evaluation of conventional EEG and aEEG in neonatal HIE. The findings have implications as biomarkers in the assessment of neonatal HIE.