Challenges of Developing Robust AI for Intrapartum Fetal Heart Rate Monitoring

Background: CTG remains the only non-invasive tool available to the maternity team for continuous monitoring of fetal well-being during labour. Despite widespread use and investment in staff training, difficulty with CTG interpretation continues to be identified as a problem in cases of fetal hypoxia, which often results in permanent brain injury. Given the recent advances in AI, it is hoped that its application to CTG will offer a better, less subjective and more reliable method of CTG interpretation. Objectives: This mini-review examines the literature and discusses the impediments to the success of AI application to CTG thus far. Prior randomised control trials (RCTs) of CTG decision support systems are reviewed from technical and clinical perspectives. A selection of novel engineering approaches, not yet validated in RCTs, are also reviewed. The review presents the key challenges that need to be addressed in order to develop a robust AI tool to identify fetal distress in a timely manner so that appropriate intervention can be made. Results: The decision support systems used in three RCTs were reviewed, summarising the algorithms, the outcomes of the trials and the limitations. Preliminary work suggests that the inclusion of clinical data can improve the performance of AI-assisted CTG. Combined with newer approaches to the classification of traces, this offers promise for rewarding future development.

Bag of Patterns for Nearest Neighbour Neonatal EEG Recall

Clinical neurophysiologists often find it difficult to recall rare EEG patterns despite the fact that this information could be diagnostic and help with treatment intervention. Traditional search methods may take time to retrieve the archived EEGs that could provide the meaning or cause of the specific pattern, which is undesirable as time can be critical for sick neonates. If neurophysiologists had the ability to quickly recall similar patterns, the prior occurrence of the pattern may help make an earlier diagnosis. This paper presents a system that may be used to assist a clinical neurophysiologist in the recall of neonatal EEG patterns. This paper compares two brute force approaches for the task of neonatal EEG recall and looks at the performance accuracy, speed and memory requirements. This system was tested on six different neonatal EEG pattern types with 430 events in total and the results are presented in this paper.

An Approximate Nearest Neighbour System For Neonatal EEG Recall

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

Altered Expression of Umbilical Cord Blood Levels of miR-181b and Its Downstream Target mUCH-L1 in Infants with Moderate and Severe Neonatal Hypoxic-Ischaemic Encephalopathy

Hypoxic-ischaemic encephalopathy (HIE) remains one of the leading causes of neurological disability worldwide. No blood biomarker capable of early detection and classification of injury severity in HIE has been identified. This study aimed to investigate the potential of miRNA-181b (miR-181b) and its downstream target, ubiquitin C-terminal hydrolase-L1 (UCH-L1), to predict the severity of HIE. Full-term infants with perinatal asphyxia were recruited at birth and observed for the development of HIE, along with healthy controls. Levels of miR-181b and messenger UCH-L1 (mUCH-L1) in umbilical cord blood were determined using qRT-PCR. In total, 131 infants; 40 control, 50 perinatal asphyxia without HIE (PA) and 41 HIE, recruited across two separate cohorts (discovery and validation) were included in this study. Significant and consistent downregulation of miR-181b was observed in infants with moderate/severe HIE compared to all other groups in both cohorts: discovery 0.25 (0.16-0.32) vs 0.61 (0.26-1.39), p = 0.027 and validation 0.33 (0.15-1.78) vs 1.2 (0.071-2.09), p = 0.035. mUCH-L1 showed increased expression in infants with HIE in both cohorts. The expression ratio of miR-181b to mUCH-L1 was reduced in those infants with moderate/severe HIE in both cohorts: discovery cohort 0.23 (0.06-0.44) vs 1.59 (0.46-2.54), p = 0.01 and validation cohort 0.41 (0.10-0.81) vs 1.38 (0.59-2.56) in all other infants, p = 0.009. We have validated consistent patterns of altered expression in miR-181b/mUCH-L1 in moderate/severe neonatal HIE which may have the potential to guide therapeutic intervention in HIE.

Mild hypoxic ischaemic encephalopathy and long term neurodevelopmental outcome - A systematic review

AIMS

Hypoxic ischaemic encephalopathy (HIE) remains a significant cause of long term neurodisability despite therapeutic hypothermia (TH). Infants with mild HIE, representing 50% of those with HIE, are perceived as low risk and are currently not eligible for TH [1]. This review examines the available evidence of outcome in term infants with mild HIE.

METHODS

Medline, Embase and Cochrane Clinical Trials databases were searched in March 2017. Studies with well-defined HIE grading at birth and standardised neurodevelopmental assessment at ≥18 months were included. Abnormal outcome was defined as death, cerebral palsy or standardised neurodevelopmental test score more than 1 standard deviation below the mean.

RESULT

Twenty studies were included. Abnormal outcome was reported in 86/341 (25%) of infants. There was insufficient evidence to examine the effect of TH on outcome.

CONCLUSION

A significant proportion of infants with mild HIE have abnormal outcome at follow up.

Downstream mRNA Target Analysis in Neonatal Hypoxic-Ischaemic Encephalopathy Identifies Novel Marker of Severe Injury: a Proof of Concept Paper

Human microRNA miR-374a is downregulated in the umbilical cord blood (UCB) of infants with hypoxic-ischaemic encephalopathy (HIE). The downstream targets of this microRNA (miRNA) are unclear, but one putative target is the activin-A receptor type IIb (ACVR2B). ACVR2B is required for activin-A function and previous reports have shown alterations of activin-A levels in neonatal HIE. Our aim was to investigate the expression of the potential downstream targets of miR-374a, activin-A and ACVR2B, at birth in a cohort of full-term infants with perinatal asphyxia (PA) only, and those with PA who developed clinical and electrographic HIE. UCB was drawn and processed immediately after delivery. Levels of serum activin-A were measured using ELISA. mRNA levels of ACVR2B in whole blood were quantified using qRT-PCR. Outcome was assessed at 3 years of age using standardised developmental assessment. In total, 171 infants were enrolled: 88 healthy controls, 56 PA and 27 HIE. A statistically significant elevation of median (IQR) ACVR2B was detected in infants with severe HIE compared to moderate/mild HIE, PA and control groups (3.3 (2.94-3.67) vs. 0.91 (0.55-1.21) vs. 0.88 (0.57-1.38) vs. 0.84 (0.74-1.24), p values = 0.04, 0.027 and 0.025, respectively). Although serum activin-A levels were elevated in infants with severe HIE, this elevation did not reach significance. ACVR2B may be a potential novel marker of HIE severity. This is the first study to examine the relationship between activin-A, its receptor AVCR2B and potentially upstream miRNA miR-374a in a cohort of carefully categorised and phenotyped infants. We have shown that miRNA analysis, combined with downstream target exploration, may yield novel biomarkers for the prediction of HIE severity.

Artefact detection in neonatal EEG

Artefact detection is an important component of any automated EEG analysis. It is of particular importance in analyses such as sleep state detection and EEG grading where there is no null state. We propose a general artefact detection system (GADS) based on the analysis of the neonatal EEG. This system aims to detect both major and minor artefacts (a distinction based primarily on amplitude). As a result, a two-stage system was constructed based on 14 features extracted from EEG epochs at multiple time scales: [2, 4, 16, 32]s. These features were combined in a support vector machine (SVM) in order to determine the presence of absence of artefact. The performance of the GADS was estimated using a leave-one-out cross-validation applied to a database of hour long recordings from 51 neonates. The median AUC was 1.00 (IQR: 0.95-1.00) for the detection of major artefacts and 0.89 (IQR: 0.83-0.95) for the detection of minor artefacts.

Application of audio fingerprinting to neonatal EEG

A clinical neurophysiologist must recognize patterns in EEG signals to evaluate the health of a patient's brain activity. Rare or unusual patterns may take time to correctly identify. The ability to automatically assist this recall would be beneficial in ensuring that appropriate measures could be taken in a timely fashion. Audio fingerprinting is a method used to identify songs using only a snippet of the song. Fingerprints are extracted from a sub-section of the song and matched against a database of previously computed fingerprints. In this paper, a fingerprint quantization technique is implemented on neonatal EEG data to attempt to identify sections of EEG data when only seeing a sub-section of the data. The impact of signal distortions is investigated and results from a database of one hour recordings from 40 newborns are presented.

In-depth performance analysis of an EEG based neonatal seizure detection algorithm

•

A novel method for in-depth analysis of neonatal seizure detection algorithms is proposed.

•

The analysis estimated how seizure features are exploited by automated detectors.

•

This method led to significant improvement of the ANSeR algorithm.

Objective

To describe a novel neurophysiology based performance analysis of automated seizure detection algorithms for neonatal EEG to characterize features of detected and non-detected seizures and causes of false detections to identify areas for algorithmic improvement.

Methods

EEGs of 20 term neonates were recorded (10 seizure, 10 non-seizure). Seizures were annotated by an expert and characterized using a novel set of 10 criteria.

ANSeR seizure detection algorithm (SDA) seizure annotations were compared to the expert to derive detected and non-detected seizures at three SDA sensitivity thresholds. Differences in seizure characteristics between groups were compared using univariate and multivariate analysis. False detections were characterized.

Results

The expert detected 421 seizures. The SDA at thresholds 0.4, 0.5, 0.6 detected 60%, 54% and 45% of seizures. At all thresholds, multivariate analyses demonstrated that the odds of detecting seizure increased with 4 criteria: seizure amplitude, duration, rhythmicity and number of EEG channels involved at seizure peak. Major causes of false detections included respiration and sweat artefacts or a highly rhythmic background, often during intermediate sleep.

Conclusion

This rigorous analysis allows estimation of how key seizure features are exploited by SDAs.

Significance

This study resulted in a beta version of ANSeR with significantly improved performance.

Stream computing for biomedical signal processing: A QRS complex detection case-study

Recent developments in "Big Data" have brought significant gains in the ability to process large amounts of data on commodity server hardware. Stream computing is a relatively new paradigm in this area, addressing the need to process data in real time with very low latency. While this approach has been developed for dealing with large scale data from the world of business, security and finance, there is a natural overlap with clinical needs for physiological signal processing. In this work we present a case study of streams processing applied to a typical physiological signal processing problem: QRS detection from ECG data.

Early Cord Metabolite Index and Outcome in Perinatal Asphyxia and Hypoxic-Ischaemic Encephalopathy

BACKGROUND

A 1H-NMR-derived metabolomic index based on early umbilical cord blood alterations of succinate, glycerol, 3-hydroxybutyrate and O-phosphocholine has shown potential for the prediction of hypoxic-ischaemic encephalopathy (HIE) severity.

OBJECTIVE

To evaluate whether this metabolite score can predict 3-year neurodevelopmental outcome in infants with perinatal asphyxia and HIE, compared with current standard biochemical and clinical markers.

METHODS

From September 2009 to June 2011, infants at risk of perinatal asphyxia were recruited from a single maternity hospital. Cord blood was drawn and biobanked at delivery. Neonates were monitored for development of encephalopathy both clinically and electrographically. Neurodevelopmental outcome was assessed at 36-42 months using the Bayley Scales of Infant and Toddler Development, ed. III (BSID-III). Death and cerebral palsy were also considered as abnormal end points.

RESULTS

Thirty-one infants had both metabolomic analysis and neurodevelopmental outcome at 36-42 months. No child had a severely abnormal BSID-III result. The metabolite index significantly correlated with outcome (ρ2 = 0.30, p < 0.01), which is robust to predict both severe outcome (area under the receiver operating characteristic curve: 0.92, p < 0.01) and intact survival (0.80, p = 0.01). There was no correlation between the index score and performance in the individual BSID-III subscales (cognitive, language, motor).

CONCLUSIONS

The metabolite index outperformed other standard biochemical markers at birth for prediction of outcome at 3 years, but was not superior to EEG or the Sarnat score.

Robustness of time frequency distribution based features for automated neonatal EEG seizure detection

In this paper we examined the robustness of a feature-set based on time-frequency distributions (TFDs) for neonatal EEG seizure detection. This feature-set was originally proposed in literature for neonatal seizure detection using a support vector machine (SVM). We tested the performance of this feature-set with a smoothed Wigner-Ville distribution and modified B distribution as the underlying TFDs. The seizure detection system using time-frequency signal and image processing features from the TFD of the EEG signal using modified B distribution was able to achieve a median receiver operator characteristic area of 0.96 (IQR 0.91-0.98) tested on a large clinical dataset of 826 h of EEG data from 18 full-term newborns with 1389 seizures. The mean AUC was 0.93.

Overcoming the practical challenges of electroencephalography for very preterm infants in the neonatal intensive care unit

Aim

Long‐term electroencephalogram (EEG) recording is increasingly being used in the neonatal period, but application and maintenance of the EEG electrodes is challenging, especially in preterm infants. This study proposes a practical method of electrode application that can be used in the neonatal intensive care unit (NICU).

Methods

EEG recording in preterm infants of <32 weeks of gestational age is often challenging and requires careful preparation and strict adherence to NICU protocols. An effective technique for EEG application in preterm infants is to use prepackaged, sterile, disposable, flat‐surfaced EEG electrodes. The use of these electrodes in combination with a continuous positive airway pressure hat provides good security for electrodes and good quality EEG recordings. It also limits the handling of the infant, while strictly adhering to infection control policies.

Results

Long‐term monitoring for >72 h has been achieved using this technique. Important steps to consider are efficient preparation of the recording machine and materials, careful electrode application and infection control.

Conclusion

A fast and effective method of EEG electrode placement is required for neonatal EEG monitoring. The practical techniques described in this article outline a reliable method of EEG electrode placement, suitable for even extremely preterm infants.

Normative levels of Interleukin 16 in umbilical cord blood

OBJECTIVES

The need for early and accurate prediction of outcome in hypoxic-ischaemic encephalopathy (HIE) remains critical. We have previously demonstrated that Interleukin 16 (IL-16) is raised in the umbilical cord blood (UCB) of infants with moderate and severe HIE and has the potential to be developed as a predictive biomarker. Normal reference ranges for IL-16 in UCB have not been previously described. The aim of this study was to determine normative levels of IL-16 in full term neonates using UCB following uncomplicated deliveries and to examine the effect of labour on cord IL-16 values.

DESIGN AND METHODS

Full term infants were recruited as part of an ongoing birth cohort study, the Cork BASELINE Birth Cohort Study. All had UCB drawn and bio-banked at -80°C, within 3hours of birth. Samples for this experiment were chosen from this population based cohort study to represent uncomplicated pre-labour caesarean sections and spontaneous vaginal deliveries. Analysis was performed on plasma EDTA, using ELISA Quantikine® (R&D Systems, Europe).

RESULTS

Samples were analysed from 48 infants with two modes of delivery; spontaneous vaginal delivery (n=12 male, n=12 female) and elective caesarean section (n=12 male, n=12 female). The range of all samples was normally distributed between 87.0 and 114.6pg/ml. Overall mean (SD) for IL-16 was 102.9 (21.5) pg/ml. Levels were not affected by spontaneous vaginal delivery or gender.

CONCLUSION

For the first time we have described the expected range of cord plasma IL-16 levels in healthy term infants following pre-labour and post-labour delivery.

Association of nucleated red blood cells and severity of encephalopathy in normothermic and hypothermic infants

AIM

To determine whether hypothermia alters the discriminative ability of postnatal nucleated red blood cells (NRBCs) to distinguish between mild and moderate/severely encephalopathic infants.

METHODS

A prospective cohort study recruited full-term neonates with hypoxic ischaemic encephalopathy (HIE) from 2003 to 2012 (prehypothermic and hypothermic eras). The NRBC count was analysed in the first 24 h in all infants and compared between normothermic and hypothermic cohorts. The severity of encephalopathy was categorized using both clinical Sarnat score and continuous multichannel EEG.

RESULTS

Eighty-six infants with HIE were included: in the normothermic group, 19 were clinically mild, 24 moderate/severe; in the hypothermic group, 22 were mild, 21 moderate/severe encephalopathy. NRBC count discriminated between mild and moderate/severe Sarnat scores in the normothermic group (p = 0.03) but not in the hypothermic group (p = 0.9). This change was due to a decrease in NRBCs among moderately encephalopathic infants in the hypothermic cohort.

CONCLUSION

Postnatal NRBCs distinguished between mild and moderate/severe encephalopathy in normothermic infants but not in infants undergoing therapeutic hypothermia. We advise caution when using postnatal blood samples to study diagnostic biomarkers for HIE without first analysing the potential impact of hypothermia upon these markers.

An automated system for grading EEG abnormality in term neonates with hypoxic-ischaemic encephalopathy

Automated analysis of the neonatal EEG has the potential to assist clinical decision making for neonates with hypoxic-ischaemic encephalopathy. This paper proposes a method of automatically grading the degree of abnormality in an hour long epoch of neonatal EEG. The automated grading system (AGS) was based on a multi-class linear classifier grading of short-term epochs of EEG which were converted into a long-term grading of EEG using a majority vote operation. The features used in the AGS were summary measurements of two sub-signals extracted from a quadratic time-frequency distribution: the amplitude modulation and instantaneous frequency. These sub-signals were based on a model of EEG as a multiplication of a coloured random process with a slowly varying pseudo-periodic waveform and may be related to macroscopic neurophysiological function. The 4 grade AGS had a classification accuracy of 83% compared to human annotation of the EEG (level of agreement, κ = 0.76). Features estimated on the developed sub-signals proved more effective at grading the EEG than measures based solely on the EEG and the incorporation of additional sub-grades based on EEG states into the AGS also improved performance.

The use of conventional EEG for the assessment of hypoxic ischaemic encephalopathy in the newborn: a review

Neonatal hypoxic ischaemic encephalopathy continues to be one of the leading causes of morbidity and mortality among neonates around the globe. With the advent of therapeutic hypothermia, the need to accurately classify the severity of injury in the early neonatal period is of great importance. As clinical measures cannot always accurately estimate the severity early enough for treatment to be initiated, clinicians have become more dependent on conventional and amplitude integrated EEG. Despite this, there is currently no single agreed classification scheme for the neonatal EEG in hypoxic ischaemic encephalopathy. In this review we discuss classification schemes of neonatal background EEG, published over the past 35 years, highlighting the urgent need for a universal visual analysis scheme.

Nucleated red blood cells and early EEG: predicting Sarnat stage and two year outcome

AIMS

Hypoxic Ischaemic Encephalopathy (HIE) causes characteristic changes of the electroencephalogram (EEG), and a raised Nucleated Red Blood Cell (NRBC) count compared to controls. We wished to examine whether combining these markers could improve their ability to predict HIE severity in the first 24h.

METHODS

Term infants with HIE were recruited. NRBC count and continuous multi-channel EEG were recorded within the first 24h. Neurological assessment was carried out at 24 months. A control population with NRBC counts in the first 24h was recruited.

RESULTS

44 infants with HIE and 43 control infants were recruited. Of the HIE population 39 completed a 2 year follow-up. The median NRBC count differed significantly between the controls and those with HIE (3/100 WBC [range of 0-11] vs 12.3/100 WBC [0-240]) (p<0.001). Within the HIE population the median NRBC count was significantly greater in infants with moderate/severe HIE than mild (16/100 WBC [range of 0-240] vs 8/100 WBC [1-23]) (p=0.016), and among infants with abnormal outcome compared to normal (21.3/100 WBC [1-239.8] vs 8.3/100 WBC [0-50])(p=0.03). The predictive ability of EEG changed with time post-delivery, therefore results are given at both 12 and 24h of age. At both time points the combined marker had a stronger correlation than EEG alone; with HIE severity (12h: r=0.661 vs r=0.622), (24h: r=0.645 vs r=0.598), and with outcome at 2 years (12h: r=0.756 vs r=0.652), (24h: r=0.802 vs r=0.746).

CONCLUSION

Combining early EEG and NRBC count to predict HIE severity and neurological outcome, improved the predictive ability of either in isolation.

Performance assessment for EEG-based neonatal seizure detectors

Objective

This study discusses an appropriate framework to measure system performance for the task of neonatal seizure detection using EEG. The framework is used to present an extended overview of a multi-channel patient-independent neonatal seizure detection system based on the Support Vector Machine (SVM) classifier.

Methods

The appropriate framework for performance assessment of neonatal seizure detectors is discussed in terms of metrics, experimental setups, and testing protocols. The neonatal seizure detection system is evaluated in this framework. Several epoch-based and event-based metrics are calculated and curves of performance are reported. A new metric to measure the average duration of a false detection is proposed to accompany the event-based metrics. A machine learning algorithm (SVM) is used as a classifier to discriminate between seizure and non-seizure EEG epochs. Two post-processing steps proposed to increase temporal precision and robustness of the system are investigated and their influence on various metrics is shown. The resulting system is validated on a large clinical dataset of 267 h.

Results

In this paper, it is shown how a complete set of metrics and a specific testing protocol are necessary to extensively describe neonatal seizure detection systems, objectively assess their performance and enable comparison with existing alternatives. The developed system currently represents the best published performance to date with an ROC area of 96.3%. The sensitivity and specificity were ∼90% at the equal error rate point. The system was able to achieve an average good detection rate of ∼89% at a cost of 1 false detection per hour with an average false detection duration of 2.7 min.

Conclusions

It is shown that to accurately assess the performance of EEG-based neonatal seizure detectors and to facilitate comparison with existing alternatives, several metrics should be reported and a specific testing protocol should be followed. It is also shown that reporting only event-based metrics can be misleading as they do not always reflect the true performance of the system.

Significance

This is the first study to present a thorough method for performance assessment of EEG-based seizure detection systems. The evaluated SVM-based seizure detection system can greatly assist clinical staff, in a neonatal intensive care unit, to interpret the EEG.

Gaussian mixture models for classification of neonatal seizures using EEG

A real-time neonatal seizure detection system is proposed based on a Gaussian mixture model classifier. The system includes feature transformation techniques and classifier output postprocessing. The detector was evaluated on a database of 20 patients with 330 h of recordings. A detailed analysis of the choice of parameters for the detector is provided. A mean good detection rate of 79% was obtained with only 0.5 false detections per hour. A thorough review of all misclassified events was performed, from which a number of patterns causing false detections were identified.

Predicting the neurodevelopmental outcome in newborns with hypoxic-ischaemic injury

The prediction of outcome in newborns with hypoxic ischemic encephalopathy (HIE) is a problematic task. Here, the ability of a combination of clinical, heart rate and EEG measures to predict outcome at 2 years is investigated. One hour of EEG and ECG recordings were obtained from newborns 24 hours after birth. Each newborn was reassessed at 24 months to investigate their neurodevelopmental outcome. From the EEG and ECG recordings, a set of 12 features was extracted. To classify each baby's outcome this data, along with clinical information was fed to a support vector machine. On a per patient basis an ROC area of 0.768 was achieved with 73.68% of newborns being assigned the correct outcome. Overall, this system presents a promising step towards the use of multimodal data for the prediction of neurodevelopmental outcome in newborns with HIE.

Characterisation of heart rate changes and their correlation with EEG during neonatal seizures

The effect of seizures on instantaneous HR (iHR) in 12 neonates is investigated here. HR can be readily extracted from the ECG and can be employed as an additional signal in seizure detection algorithms. The change in instantaneous HR and its correlation with the change in RMS EEG amplitude were examined. Two methods were employed to classify significant iHR changes. Significant correlation (p 0.05) during seizure was observed in 100% of patients (83.33% of seizures). Overall, significant iHR changes (classified by either method) were found in 83% of patients (50% of seizures). It was found that a markedly higher iHR was observed in patients whose seizures were not classified as having significant iHR changes.

Persistent lactic acidosis in neonatal hypoxic-ischaemic encephalopathy correlates with EEG grade and electrographic seizure burden

BACKGROUND

Predicting at birth which infants with perinatal hypoxic-ischaemic injury will progress to significant encephalopathy remains a challenge.

OBJECTIVE

To determine whether lactic acidosis at birth in asphyxiated neonates could predict the grade of EEG encephalopathy by examining the relationship between time taken for the normalisation of lactate, severity of encephalopathy and seizure burden.

METHODS

Continuous early video-EEG monitoring was performed in babies at risk for hypoxic-ischaemic encephalopathy. Encephalopathy was graded from the EEG data. Total seizure burden (seconds) was calculated for each baby. Initial blood gas measurements of pH, base deficit and lactate were taken within 30 minutes of delivery. Time to normal serum lactate was determined in hours from birth for each infant.

RESULTS

All 50 term infants had raised initial serum lactate (median (lower, upper quartiles) 11.7 (10.2, 14.9)). There were no significant differences between the initial serum lactate, pH and base deficit in infants with normal/mildly abnormal (n = 24), moderately abnormal (n = 14), severely abnormal (n = 5) and inactive EEGs (n = 7). Time to normal lactate varied significantly with EEG grade (median (lower, upper quartile) 6.0 (4.1, 9.5) for mild/normal EEG, 13.5 (6.8, 23.5) moderate EEG, 41.5 (30.0, 55.5) severe group, 12.0 (8.1, 21.5) inactive group; p<0.001). Time to normal lactate correlated significantly with EEG seizure burden (seconds; R = 0.446, p = 0.002). Mean (SD) time to normal lactate was 10.0 (7.2) hours in infants who did not have seizures and 27.3 (19.0) hours in the 13 infants with electrographic seizures (p = 0.002).

CONCLUSIONS

Serum lactate levels in the first 30 minutes of life do not predict the severity of the ensuing encephalopathy. In contrast, sustained lactic acidosis is associated with severe encephalopathy on EEG and correlates with seizure burden.

Defining the gap between electrographic seizure burden, clinical expression and staff recognition of neonatal seizures

BACKGROUND

Neonatal seizures are often subclinical, making accurate diagnosis difficult.

OBJECTIVE

To describe the clinical manifestations of electrographic seizures recorded on continuous video-EEG, and to compare this description with the recognition of clinical seizures by experienced neonatal staff.

METHODS

Term infants, at risk of seizures, were monitored by continuous 12-channel video-EEG from <6 hours of birth for up to 72 hours. All clinical seizures were recorded by experienced neonatal staff on individual seizure charts. Video-EEG recordings were subsequently analysed. The number, duration and clinical expression of electrographic seizures were calculated (in seconds), and compared with the seizures clinically suspected by the neonatal staff.

RESULTS

Of 51 infants enrolled, nine had electrographic seizures. A further three had clinically suspected seizures, without associated electrographic abnormality. Of the total 526 electrographic seizures, 179 (34%) had clinical manifestations evident on the simultaneous video recording. The clinical seizure activity corresponded to 18.8% of the total electrographic seizure burden. Overdiagnosis also occurred frequently. Of the 177 clinically suspected seizure episodes documented by staff, 48 (27%) had corresponding electrographic evidence of seizure activity Thus, only 9% (48/526) of electrographic seizures were accompanied by clinical manifestations, which were identified and documented by neonatal staff.

CONCLUSION

Only one-third of neonatal EEG seizures displays clinical signs on simultaneous video recordings. Moreover, two-thirds of these clinical manifestations are unrecognised, or misinterpreted by experienced neonatal staff. In the recognition and management of neonatal seizures clinical diagnosis alone is not enough.

A comparison of quantitative EEG features for neonatal seizure detection

OBJECTIVE

This study was undertaken to identify the best performing quantitative EEG features for neonatal seizures detection from a test set of 21.

METHODS

Each feature was evaluated on 1-min, artefact-free segments of seizure and non-seizure neonatal EEG recordings. The potential utility of each feature for neonatal seizure detection was determined using receiver operating characteristic analysis and repeated measures t-tests. A performance estimate of the feature set was obtained using a cross-fold validation and combining all features together into a linear discriminant classifier model.

RESULTS

Significant differences between seizure and non-seizure segments were found in 19 features for 17 patients. The best performing features for this application were the RMS amplitude, the line length and the number of local maxima and minima. An estimate of the patient independent classifier performance yielded a sensitivity of 81.08% and specificity of 82.23%.

CONCLUSIONS

The individual performances of 21 quantitative EEG features in detecting electrographic seizure in the neonate were compared and numerically quantified. Combining all features together into a classifier model led to superior performance than that provided by any individual feature taken alone.

SIGNIFICANCE

The results documented in this study may provide a reference for the optimum quantitative EEG features to use in developing and enhancing neonatal seizure detection algorithms.

Seizure detection in neonates: Improved classification through supervised adaptation

The goal of neonatal seizure detection is the development of a patient independent system to alert staff in the neonatal intensive care unit of ongoing seizures. This study demonstrates the potential in adapting a patient independent classifier using patient specific data. Supervised adaptation is investigated using the basic gradient descent algorithm and least mean squares procedures. An increase in mean ROC area of 3% is obtained for the best performing learning algorithm, yielding an increase in mean accuracy of 7.7% compared to the patient independent algorithm.

Automated single channel seizure detection in the neonate

Neonatal seizures are the most common neurological emergency in the neonatal period and are associated with poor long-term outcome. EEG is considered the gold standard for identification of all neonatal seizures, reducing the number of EEG electrodes required would reduce patient handling and allow faster acquisition of data. A method for automated neonatal seizure detection based on two carefully chosen cerebral scalp electrodes but trained using multi-channel EEG is presented. The algorithm was developed and tested using a multi-channel EEG dataset containing 411 seizures from 251.9 hours of EEG recorded from 17 full-term neonates. Automated seizure detection using a variety of bipolar channel derivations was investigated. Channel C3-C4 yielded correct detection of 90.77% of seizures with a false detection rate of 9.43%. This compares favourably with a multi-channel seizure detection method which detected 81.03% of seizures with a false detection rate of 3.82%.

Automated estimation of sedation depth from the EEG

A method is presented for the automatic determination of a patient's level of sedation from the EEG. Six bipolar channels of EEG recorded from 12 adult patients sedated with low-dose propofol (2, 6-disopropylphenol) were used to develop a linear discriminant based system for depth of sedation monitoring using a number of quantitative EEG measures. A cross fold validation estimate of the performance of the algorithm as a patient independent system yielded a sensitivity of 74.70% and a specificity of 81.67%. It is hoped that the methodology reported here could lead to fully automated systems for depth of sedation monitoring.

The relationship between the onset of electrographic seizure activity after birth and the time of cerebral injury in utero

In the fetal lamb model of hypoxic-ischaemic injury, the insult is followed by EEG depression, after which seizures emerge at 7-13 hours. We explored the relationship between the emergence of electrographic seizures and our estimate of the time of the cerebral injury in nine babies who underwent continuous video-EEG monitoring from soon after birth. Babies with prelabour insults had their first seizures before 12 hours of age, whereas those whose insult was peripartum had seizure onset at 18-20 hours of age. EEG seizure onset time could have important clinical and medico-legal applications, and be related to the time or severity of the insult, or both.

Second-line anticonvulsant treatment of neonatal seizures: a video-EEG monitoring study

The authors conducted a randomized trial of second-line anticonvulsant treatments for neonates. The response to treatment was assessed using continuous video-EEG because the clinical diagnosis of seizure in neonates is known to be unreliable. Of 27 neonates with EEG-confirmed seizures, 5 were excluded because of protocol violations, and 11 responded to phenobarbitone in a dose of 40 mg/kg as first line. Three of five neonates treated with lignocaine responded. Six neonates were treated with benzodiazepines as second line: None responded, and their neurodevelopmental outcome was poor.

Non-expert use of the cerebral function monitor for neonatal seizure detection

BACKGROUND

The cerebral function monitor (CFM) is widely used to detect neonatal seizures, but there are very few studies comparing it with simultaneous electroencephalography (EEG).

OBJECTIVE

To determine the accuracy of non-expert use of the CFM and to assess interobserver agreement of CFM seizure detection.

PATIENTS

Babies admitted to the neonatal intensive care unit at King's College Hospital who were at high risk of seizure and had video-EEG monitoring.

METHODS

Video-EEG was used to detect seizures. Each baby had CFM recordings at speeds of 6, 15, and 30 cm/h during the EEG. Four neonatologists, trained in CFM seizure recognition, independently rated one hour CFM samples at three speeds from each baby. Interobserver agreement was quantified using Cohen's kappa.

RESULTS

CFM traces from 19 babies with EEG seizures and 21 babies without EEG seizures were analysed. Overall non-expert interpretation of the CFM performed poorly as a seizure detector compared with simultaneous EEG (sensitivities 38% at 6 cm/h; 54% at 15 cm/h; 55% at 30 cm/h). Although babies with seizures were more likely to be correctly classified at higher speeds (p = 0.02), babies without seizures were also more likely to be misclassified (p < 0.001). Agreement between observers was not good at any speed (kappa values from 0.01 to 0.39). The observers usually detected generalised seizures but often missed seizures that were focal, low amplitude, or lasted less than one minute.

CONCLUSION

Approximately half of all neonatal seizures may be missed using CFM alone. Neonatal seizures need to be diagnosed, characterised, and quantified first using EEG. The CFM may then be useful for long term monitoring.

Phenobarbitone, neonatal seizures, and video-EEG

AIMS

To evaluate the effectiveness of phenobarbitone as an anticonvulsant in neonates.

METHODS

An observational study using video-EEG telemetry. Video-EEG was obtained before treatment was started, for an hour after treatment was given, two hours after treatment was given, and again between 12 and 24 hours after treatment was given. Patients were recruited from all babies who required phenobarbitone (20-40 mg/kg intravenously over 20 minutes) for suspected clinical seizures and had EEG monitoring one hour before and up to 24 hours after the initial dose. An EEG seizure discharge was defined as a sudden repetitive stereotyped discharge lasting for at least 10 seconds. Neonatal status epilepticus was defined as continuous seizure activity for at least 30 minutes. Seizures were categorised as EEG seizure discharges only (electrographic), or as EEG seizure discharges with accompanying clinical manifestations (electroclinical). Surviving babies were assessed at one year using the Griffiths neurodevelopmental score.

RESULTS

Fourteen babies were studied. Four responded to phenobarbitone; these had normal or moderately abnormal EEG background abnormalities and outcome was good. In the other 10 babies electrographic seizures increased after treatment, whereas electroclinical seizures reduced. Three babies were treated with second line anticonvulsants, of whom two responded. One of these had a normal neurodevelopmental score at one year, but the outcome for the remainder of the whole group was poor.

CONCLUSION

Phenobarbitone is often ineffective as a first line anticonvulsant in neonates with seizures in whom the background EEG is significantly abnormal.

Early serial EEG in hypoxic ischaemic encephalopathy

OBJECTIVES

To perform early serial EEGs in infants with hypoxic ischaemic encephalopathy (HIE) and compare the findings with neurodevelopmental outcome.

METHODS

Nine full-term neonates with HIE had simultaneous video-EEG polygraphic studies within 8 h of birth. The EEG was repeated at 12-24 h intervals. All surviving infants had a neurodevelopmental assessment at 1 year.

RESULTS

Two infants had a normal or mildly abnormal EEG within 8 h of birth and neurodevelopmental outcome was normal. Seven infants had severely depressed background activity in the first 8 h of life. In 3 infants the EEG activity recovered within 12-24 h showing continuous activity with no or only minor abnormalities. All these infants had a normal outcome. The remaining 4 infants, who also had an initially inactive recording, subsequently developed severe background abnormalities. At follow-up, two infants had died and the remainder developed major neurological sequelae.

CONCLUSIONS

Early EEG is an excellent prognostic indicator for a favourable outcome if normal within the first 8 h of life and for a poor outcome if the background activity continues to be inactive or grossly abnormal beyond 8-12 h of life. However, an inactive or very depressed EEG within the first 8 h of life can be associated with good outcome if the EEG activity recovers within 12 h.

Dynamic cerebral autoregulation in sick newborn infants

The sick newborn infant is vulnerable to brain injury and impaired cerebral autoregulation is thought to contribute to this. Coherent averaging is a method of measuring the dynamic cerebral autoregulatory response that is particularly suitable for neonates. We used this method in combination with a measure of the gradient of the cerebral blood flow velocity (CBFV) response following transient blood pressure (BP) peaks to study dynamic autoregulation in infants undergoing intensive care. Term and preterm infants at high risk of neurologic injury were compared with a control group of infants, also undergoing intensive care. Simultaneous video-EEG, CBFV (using transcranial Doppler), and arterial blood pressure measurements were obtained intermittently during a study period of at least 2 h. Cerebral autoregulatory response curves were constructed for high risk and control groups. Intact cerebral autoregulation produces a characteristic response consisting of a brief period when CBFV follows arterial blood pressure but quickly returns to baseline value. An impaired autoregulatory response shows CBFV mirroring the arterial blood pressure curve closely. Thirteen high-risk infants, who also had seizures (10 term and 3 preterm) and 12 control infants (6 term and 6 preterm) were studied. Autoregulation was absent in high-risk term and preterm infants. It was also absent in preterm control infants. Term, neurologically healthy infants undergoing intensive care have an intact autoregulatory response. The constant passive response seen in high-risk infants may reflect the severity of the underlying neurologic disease.

Outcome of electroclinical, electrographic, and clinical seizures in the newborn infant

Three seizure types have been described in the neonate: electroclinical, electrographic, and clinical only. Controversy still exists about whether the episodic abnormal movements seen in some infants, which are not accompanied by simultaneous ictal discharges on the EEG, are true seizures. Twenty-four infants with seizures were studied, 17 had purely electrographic and/or electroclinical seizures, seven had clinical-only seizures; six of these seven had clonic seizures, without facial manifestations or autonomic change. The three seizure types were investigated using video-EEG and a Griffiths neurodevelopmental assessment was performed in each seizure group. Of the seven infants with clinical-only seizures, six had clonic seizures with a normal background EEG, neuroimaging studies and neurodevelopmental follow-up assessment were normal in five. In the remaining 17 infants with electrographic and/or electroclinical seizures, seizure discharges were often associated with ocular phenomena, apnoea, or tonic posturing, and the background EEG was abnormal in all but one subject. Neurodevelopmental follow-up assessments revealed a poor outcome (14 of 17) in this group. In otherwise healthy infants, purely clonic seizures involving only the limbs may be a benign phenomenon and an EEG should be obtained to avoid unnecessary treatment. Infants with seizures superimposed on an abnormal background EEG pattern had a poor outcome.

Cerebral blood flow velocity during neonatal seizures

AIM

To determine if cerebral blood flow velocity increases during all types of neonatal seizure, and whether the effect is due solely to an increase in blood pressure, transmitted to the cerebral circulation when autoregulation is impaired.

METHODS

Seizures were diagnosed in 11 high risk neonates using cotside 16 channel video-EEG polygraphy. EEG, cerebral blood flow velocity (CBFV) using transcranial Doppler ultrasound, and arterial blood pressure (ABP) measurements were made. At least two 5-10 minute epochs of simultaneous measurements were performed on each infant. These epochs were then reviewed to eliminate artefacts, and one minute data periods containing a clear seizure onset were created. Each period contained 20 seconds before the seizure. Data periods without seizures from the same infants were also analysed and compared with seizure periods.

RESULTS

Four infants had purely electrographic seizures-without clinical manifestations. Six infants had electroclinical seizures. One infant displayed both seizure types. A random effects linear regression analysis was used to determine the effect of seizures on CBFV and ABP. A significant increase was found in mean CBFV in those periods containing seizures. The mean percentage change in velocity for all infants was 15.6%. Three infants showed a significant increase in mean ABP after seizures but the overall increase in ABP for all infants was not significant.

CONCLUSION

Electroclinical and electrographic neonatal seizures produce an increase in CBFV. In some infants the increase is not associated with an increase in blood pressure. These preliminary results suggest that electrographic seizures are associated with disturbed cerebral metabolism. Treatment of neonatal seizures until electrographic seizure activity is abolished may improve outcome for these infants.