Automatic classification of background EEG activity in healthy and sick neonates

Preoperative Prediction of Catheter Ablation Outcome in Persistent Atrial Fibrillation Patients through Spectral Organization Analysis of the Surface Fibrillatory Waves

Catheter ablation (CA) is a commonly used treatment for persistent atrial fibrillation (AF). Since its medium/long-term success rate remains limited, preoperative prediction of its outcome is gaining clinical interest to optimally select candidates for the procedure. Among predictors based on the surface electrocardiogram, the dominant frequency (DF) and harmonic exponential decay (γ) of the fibrillatory waves (f-waves) have reported promising but clinically insufficient results. Hence, the main goal of this work was to conduct a broader analysis of the f-wave harmonic spectral structure to improve CA outcome prediction through several entropy-based measures computed on different frequency bands. On a database of 151 persistent AF patients under radio-frequency CA and a follow-up of 9 months, the newly introduced parameters discriminated between patients who relapsed to AF and those who maintained SR at about 70%, which was statistically superior to the DF and approximately similar to γ. They also provided complementary information to γ through different combinations in multivariate models based on lineal discriminant analysis and report classification performance improvement of about 5%. These results suggest that the presence of larger harmonics and a proportionally smaller DF peak is associated with a decreased probability of AF recurrence after CA.

Review of Machine and Deep Learning Techniques in Epileptic Seizure Detection using Physiological Signals and Sentiment Analysis

Epilepsy is one of the significant neurological disorders affecting nearly 65 million people worldwide. The repeated seizure is characterized as epilepsy. Different algorithms were proposed for efficient seizure detection using intracranial and surface EEG signals. In the last decade, various machine learning techniques based on seizure detection approaches were proposed. This paper discusses different machine learning and deep learning techniques for seizure detection using intracranial and surface EEG signals. A wide range of machine learning techniques such as support vector machine (SVM) classifiers, artificial neural network (ANN) classifier, and deep learning techniques such as a convolutional neural network (CNN) classifier, long-short term memory (LSTM) network for seizure detection are compared in this paper. The effectiveness of time-domain features, frequency domain features, and time-frequency domain features are discussed along with different machine learning techniques. Along with EEG, other physiological signals such as electrocardiogram are used to enhance seizure detection accuracy which are discussed in this paper. In recent years deep learning techniques based on seizure detection have found good classification accuracy. In this paper, an LSTM deep learning-network-based approach is implemented for seizure detection and compared with state-of-the-art methods. The LSTM based approach achieved 96.5% accuracy in seizure-nonseizure EEG signal classification. Apart from analyzing the physiological signals, sentiment analysis also has potential to detect seizure. Impact Statement- This review paper gives a summary of different research work related to epileptic seizure detection using machine learning and deep learning techniques. Manual seizure detetion is time consuming and requires expertise. So the artificial intelligence techniques such as machine learning and deep learning techniques are used for automatic seizure detection. Different physiological signals are used for seizure detection. Different researchers are working on developing automatic seizure detection using EEG, ECG, accelerometer, sentiment analysis. There is a need for a review paper that can discuss previous techniques and give further research direction. We have discussed different techniques for seizure detection with an accuracy comparison table. It can help the researcher to get an overview of both surface and intracranial EEG-based seizure detection approaches. The new researcher can easily compare different models and decide the model they want to start working on. A deep learning model is discussed to give a practical application of seizure detection. Sentiment analysis is another dimension of seizure detection and summerizing it will give a new prospective to the reader.

LiCl-induced sickness modulates rat gustatory cortical responses

Gustatory cortex (GC), a structure deeply involved in the making of consumption decisions, presumably performs this function by integrating information about taste, experiences, and internal states related to the animal’s health, such as illness. Here, we investigated this assertion, examining whether illness is represented in GC activity, and how this representation impacts taste responses and behavior. We recorded GC single-neuron activity and local field potentials (LFPs) from healthy rats and rats made ill (via LiCl injection). We show (consistent with the extant literature) that the onset of illness-related behaviors arises contemporaneously with alterations in 7 to 12 Hz LFP power at approximately 12 min following injection. This process was accompanied by reductions in single-neuron taste response magnitudes and discriminability, and with enhancements in palatability-relatedness—a result reflecting the collapse of responses toward a simple “good-bad” code visible in the entire sample, but focused on a specific subset of GC neurons. Overall, our data show that a state (illness) that profoundly reduces consumption changes basic properties of the sensory cortical response to tastes, in a manner that can easily explain illness’ impact on consumption.

Sickness is an internal state that impacts consumption, and so could be expected to influence the neural processing of tastes. This study shows that onset of illness changes basic properties of gustatory cortical network processing and taste responses, such that activity comes more purely to reflect the "goodness" or "badness" of tastes.

Precision Medicine in Neonates: A Tailored Approach to Neonatal Brain Injury

Despite advances in neonatal care to prevent neonatal brain injury and neurodevelopmental impairment, predicting long-term outcome in neonates at risk for brain injury remains difficult. Early prognosis is currently based on cranial ultrasound (CUS), MRI, EEG, NIRS, and/or general movements assessed at specific ages, and predicting outcome in an individual (precision medicine) is not yet possible. New algorithms based on large databases and machine learning applied to clinical, neuromonitoring, and neuroimaging data and genetic analysis and assays measuring multiple biomarkers (omics) can fulfill the needs of modern neonatology. A synergy of all these techniques and the use of automatic quantitative analysis might give clinicians the possibility to provide patient-targeted decision-making for individualized diagnosis, therapy, and outcome prediction. This review will first focus on common neonatal neurological diseases, associated risk factors, and most common treatments. After that, we will discuss how precision medicine and machine learning (ML) approaches could change the future of prediction and prognosis in this field.

Review of sleep-EEG in preterm and term neonates

Neonatal sleep is a crucial state that involves endogenous driven brain activity, important for neuronal survival and guidance of brain networks. Sequential EEG-sleep analysis in preterm infants provides insights into functional brain integrity and can document deviations of the biologically pre-programmed process of sleep ontogenesis during the neonatal period. Visual assessment of neonatal sleep-EEG, with integration of both cerebral and non-cerebral measures to better define neonatal state, is still considered the gold standard. Electrographic patterns evolve over time and are gradually time locked with behavioural characteristics which allow classification of quiet sleep and active sleep periods during the last 10weeks of gestation. Near term age, the neonate expresses a short ultradian sleep cycle, with two distinct active and quiet sleep, as well as brief periods of transitional or indeterminate sleep. Qualitative assessment of neonatal sleep is however challenged by biological and environmental variables that influence the expression of EEG-sleep patterns and sleep organization. Developing normative EEG-sleep data with the aid of automated analytic methods, can further improve our understanding of extra-uterine brain development and state organization under stressful or pathological conditions. Based on those developmental biomarkers of normal and abnormal brain function, research can be conducted to support and optimise sleep in the NICU, with the ultimate goal to improve therapeutic interventions and neurodevelopmental outcome.

EEG-Based Brain-Computer Interface for Decoding Motor Imagery Tasks within the Same Hand Using Choi-Williams Time-Frequency Distribution

This paper presents an EEG-based brain-computer interface system for classifying eleven motor imagery (MI) tasks within the same hand. The proposed system utilizes the Choi-Williams time-frequency distribution (CWD) to construct a time-frequency representation (TFR) of the EEG signals. The constructed TFR is used to extract five categories of time-frequency features (TFFs). The TFFs are processed using a hierarchical classification model to identify the MI task encapsulated within the EEG signals. To evaluate the performance of the proposed approach, EEG data were recorded for eighteen intact subjects and four amputated subjects while imagining to perform each of the eleven hand MI tasks. Two performance evaluation analyses, namely channel- and TFF-based analyses, are conducted to identify the best subset of EEG channels and the TFFs category, respectively, that enable the highest classification accuracy between the MI tasks. In each evaluation analysis, the hierarchical classification model is trained using two training procedures, namely subject-dependent and subject-independent procedures. These two training procedures quantify the capability of the proposed approach to capture both intra- and inter-personal variations in the EEG signals for different MI tasks within the same hand. The results demonstrate the efficacy of the approach for classifying the MI tasks within the same hand. In particular, the classification accuracies obtained for the intact and amputated subjects are as high as 88.8% and 90.2%, respectively, for the subject-dependent training procedure, and 80.8% and 87.8%, respectively, for the subject-independent training procedure. These results suggest the feasibility of applying the proposed approach to control dexterous prosthetic hands, which can be of great benefit for individuals suffering from hand amputations.

The Potential Application of Multiscale Entropy Analysis of Electroencephalography in Children with Neurological and Neuropsychiatric Disorders

Electroencephalography (EEG) is frequently used in functional neurological assessment of children with neurological and neuropsychiatric disorders. Multiscale entropy (MSE) can reveal complexity in both short and long time scales and is more feasible in the analysis of EEG. Entropy-based estimation of EEG complexity is a powerful tool in investigating the underlying disturbances of neural networks of the brain. Most neurological and neuropsychiatric disorders in childhood affect the early stage of brain development. The analysis of EEG complexity may show the influences of different neurological and neuropsychiatric disorders on different regions of the brain during development. This article aims to give a brief summary of current concepts of MSE analysis in pediatric neurological and neuropsychiatric disorders. Studies utilizing MSE or its modifications for investigating neurological and neuropsychiatric disorders in children were reviewed. Abnormal EEG complexity was shown in a variety of childhood neurological and neuropsychiatric diseases, including autism, attention deficit/hyperactivity disorder, Tourette syndrome, and epilepsy in infancy and childhood. MSE has been shown to be a powerful method for analyzing the non-linear anomaly of EEG in childhood neurological diseases. Further studies are needed to show its clinical implications on diagnosis, treatment, and outcome prediction.

An Automated Quiet Sleep Detection Approach in Preterm Infants as a Gateway to Assess Brain Maturation

Sleep state development in preterm neonates can provide crucial information regarding functional brain maturation and give insight into neurological well being. However, visual labeling of sleep stages from EEG requires expertise and is very time consuming, prompting the need for an automated procedure. We present a robust method for automated detection of preterm sleep from EEG, over a wide postmenstrual age (PMA = gestational age + postnatal age) range, focusing first on Quiet Sleep (QS) as an initial marker for sleep assessment. Our algorithm, CLuster-based Adaptive Sleep Staging (CLASS), detects QS if it remains relatively more discontinuous than non-QS over PMA. CLASS was optimized on a training set of 34 recordings aged 27–42 weeks PMA, and performance then assessed on a distinct test set of 55 recordings of the same age range. Results were compared to visual QS labeling from two independent raters (with inter-rater agreement Kappa = 0. 93), using Sensitivity, Specificity, Detection Factor (DF = proportion of visual QS periods correctly detected by CLASS) and Misclassification Factor (MF = proportion of CLASS-detected QS periods that are misclassified). CLASS performance proved optimal across recordings at 31–38 weeks (median DF = 1.0, median MF 0–0.25, median Sensitivity 0.93–1.0, and median Specificity 0.80–0.91 across this age range), with minimal misclassifications at 35–36 weeks (median MF = 0). To illustrate the potential of CLASS in facilitating clinical research, normal maturational trends over PMA were derived from CLASS-estimated QS periods, visual QS estimates, and nonstate specific periods (containing QS and non-QS) in the EEG recording. CLASS QS trends agreed with those from visual QS, with both showing stronger correlations than nonstate specific trends. This highlights the benefit of automated QS detection for exploring brain maturation.

Automated electroencephalographic discontinuity in cooled newborns predicts cerebral MRI and neurodevelopmental outcome

BACKGROUND AND HYPOTHESIS

Prolonged electroencephalographic (EEG) discontinuity has been associated with poor neurodevelopmental outcomes after perinatal asphyxia but its predictive value in the era of therapeutic hypothermia (TH) is unknown. In infants undergoing TH for hypoxic-ischaemic encephalopathy (HIE) prolonged EEG discontinuity is associated with cerebral tissue injury on MRI and adverse neurodevelopmental outcome.

METHOD

Retrospective study of term neonates from three UK centres who received TH for perinatal asphyxia, had continuous two channel amplitude-integrated EEG with EEG for a minimum of 48 h, brain MRI within 6 weeks of birth and neurodevelopmental outcome data at a median age of 24 months. Mean discontinuity was calculated using a novel automated algorithm designed for analysis of the raw EEG signal.

RESULTS

Of 49 eligible infants, 17 (35%) had MR images predictive of death or severe neurodisability (unfavourable outcome) and 29 (59%) infants had electrographic seizures. In multivariable logistic regression, mean discontinuity at 24 h and 48 h (both p=0.01), and high seizure burden (p=0.05) were associated with severe cerebral tissue injury on MRI. A mean discontinuity >30 s/min-long epoch, had a specificity and positive predictive value of 100%, sensitivity of 71% and a negative predictive value of 88% for unfavourable neurodevelopmental outcome at a 10 µV threshold.

CONCLUSIONS

In addition to seizure burden, excessive EEG discontinuity is associated with increased cerebral tissue injury on MRI and is predictive of abnormal neurodevelopmental outcome in infants treated with TH. The high positive predictive value of EEG discontinuity at 24 h may be valuable in selecting newborns with HIE for adjunctive treatments.

Improving Reliability of Monitoring Background EEG Dynamics in Asphyxiated Infants

The goal of this study is to develop an automated algorithm to quantify background electroencephalography (EEG) dynamics in term neonates with hypoxic ischemic encephalopathy. The recorded EEG signal is adaptively segmented and the segments with low amplitudes are detected. Next, depending on the spatial distribution of the low-amplitude segments, the first part of the algorithm detects (dynamic) interburst intervals (dIBIs) and performs well on the relatively artifact-free EEG periods and well-defined burst-suppression EEG periods. However, on testing the algorithm on EEG recordings of more than 48 h per neonate, a significant number of misclassified and dubious detections were encountered. Therefore, as the next step, we applied machine learning classifiers to differentiate between definite dIBI detections and misclassified ones. The developed algorithm achieved a true positive detection rate of 98%, 97%, 88%, and 95% for four duration-related dIBI groups that we subsequently defined. We benchmarked our algorithm with an expert diagnostic interpretation of EEG periods (1 h long) and demonstrated its effectiveness in clinical practice. We show that the detection algorithm effectively discriminates challenging cases encountered within mild and moderate background abnormalities. The dIBI detection algorithm improves identification of neonates with good clinical outcome as compared to the classification based on the classical burst-suppression interburst interval.

Objective differentiation of neonatal EEG background grades using detrended fluctuation analysis

A quantitative and objective assessment of background electroencephalograph (EEG) in sick neonates remains an everyday clinical challenge. We studied whether long range temporal correlations quantified by detrended fluctuation analysis (DFA) could be used in the neonatal EEG to distinguish different grades of abnormality in the background EEG activity. Long-term EEG records of 34 neonates were collected after perinatal asphyxia, and their background was scored in 1 h epochs (8 h in each neonate) as mild, moderate or severe. We applied DFA on 15 min long, non-overlapping EEG epochs (n = 1088) filtered from 3 to 8 Hz. Our formal feasibility study suggested that DFA exponent can be reliably assessed in only part of the EEG epochs, and in only relatively short time scales (10-60 s), while it becomes ambiguous if longer time scales are considered. This prompted further exploration whether paradigm used for quantifying multifractal DFA (MF-DFA) could be applied in a more efficient way, and whether metrics from MF-DFA paradigm could yield useful benchmark with existing clinical EEG gradings. Comparison of MF-DFA metrics showed a significant difference between three visually assessed background EEG grades. MF-DFA parameters were also significantly correlated to interburst intervals quantified with our previously developed automated detector. Finally, we piloted a monitoring application of MF-DFA metrics and showed their evolution during patient recovery from asphyxia. Our exploratory study showed that neonatal EEG can be quantified using multifractal metrics, which might offer a suitable parameter to quantify the grade of EEG background, or to monitor changes in brain state that take place during long-term brain monitoring.

Line length as a robust method to detect high-activity events: automated burst detection in premature EEG recordings

OBJECTIVE

EEG is a valuable tool for evaluation of brain maturation in preterm babies. Preterm EEG constitutes of high voltage burst activities and more suppressed episodes, called interburst intervals (IBIs). Evolution of background characteristics provides information on brain maturation and helps in prediction of neurological outcome. The aim is to develop a method for automated burst detection.

METHODS

Thirteen polysomnography recordings were used, collected at preterm postmenstrual age of 31.4 (26.1-34.4)weeks. We developed a burst detection algorithm based on the feature line length and compared it with manual scorings of clinical experts and other published methods.

RESULTS

The line length-based algorithm is robust (84.27% accuracy, 84.00% sensitivity, 85.70% specificity). It is not critically dependent on the number of measurement channels, because two channels still provide 82% accuracy. Furthermore, it approximates well clinically relevant features, such as median IBI duration 5.45 (4.00-7.11)s, maximum IBI duration 14.02 (8.73-18.80)s and burst percentage 48.89 (35.45-60.12)%, with a median deviation of respectively 0.65s, 1.96s and 6.55%.

CONCLUSION

Automated assessment of long-term preterm EEG is possible and its use will optimize EEG interpretation in the NICU.

SIGNIFICANCE

This study takes a first step towards fully automatic analysis of the preterm brain.

Automated EEG inter-burst interval detection in neonates with mild to moderate postasphyxial encephalopathy

EEG inter-burst interval (IBI) and its evolution is a robust parameter for grading hypoxic encephalopathy and prognostication in newborns with perinatal asphyxia. We present a reliable algorithm for the automatic detection of IBIs. This automated approach is based on adaptive segmentation of EEG, classification of segments and use of temporal profiles to describe the global distribution of EEG activity. A pediatric neurologist has blindly scored data from 8 newborns with perinatal postasphyxial encephalopathy varying from mild to severe. 15 minutes of EEG have been scored per patient, thus totaling 2 hours of EEG that was used for validation. The algorithm shows good detection accuracy and provides insight into challenging cases that are difficult to detect.

Textile electrodes for EEG recording--a pilot study

The overall aim of our research is to develop a monitoring system for neonatal intensive care units. Long-term EEG monitoring in newborns require that the electrodes don't harm the sensitive skin of the baby, an especially relevant feature for premature babies. Our approach to EEG monitoring is based on several electrodes distributed over the head of the baby, and since the weight of the head always will be on some of them, any type of hard electrode will inevitably cause a pressure-point that can irritate the skin. Therefore, we propose the use of soft conductive textiles as EEG electrodes, primarily for neonates, but also for other kinds of unobtrusive long-term monitoring. In this paper we have tested two types of textile electrodes on five healthy adults and compared them to standard high quality electrodes. The acquired signals were compared with respect to morphology, frequency distribution, spectral coherence, correlation and power line interference sensitivity, and the signals were found to be similar in most respects. The good measurement performance exhibited by the textile electrodes indicates that they are feasible candidates for EEG recording, opening the door for long-term EEG monitoring applications.

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.

Automating the analysis of EEG recordings from prematurely-born infants: a Bayesian approach

OBJECTIVE

To implement an automated analysis of EEG recordings from prematurely-born infants and thus provide objective, reproducible results.

METHODS

Bayesian probability theory is employed to compute the posterior probability for developmental features of interest in EEG recordings. Currently, these features include smooth delta waves (0.5-1.5Hz, >100μV), delta brushes (delta portion: 0.5-1.5Hz, >100μV; "brush" portion: 8-22Hz, <75μV), and interburst intervals (<10μV), though the approach taken can be generalized to identify other EEG features of interest.

RESULTS

When compared with experienced electroencephalographers, the algorithm had a true positive rate between 72% and 79% for the identification of delta waves (smooth or "brush") and interburst intervals, which is comparable to the inter-rater reliability. When distinguishing between smooth delta waves and delta brushes, the algorithm's true positive rate was between 53% and 88%, which is slightly less than the inter-rater reliability.

CONCLUSION

Bayesian probability theory can be employed to consistently identify features of EEG recordings from premature infants.

SIGNIFICANCE

The identification of features in EEG recordings provides a first step towards the automated analysis of EEG recordings from premature infants.

Optimal channel selection for analysis of EEG-sleep patterns of neonates

This paper extends our previous work on automated detection and classification of neonate EEG sleep stages. In [19] we adapted and integrated a range of computational, mathematical and statistical tools for the analysis of neonatal electroencephalogram (EEG) sleep recordings with the aim of facilitating the assessment of neonatal brain maturation and dismaturity by studying the structure and temporal patterns of their sleep. That work relied on algorithms using a single channel of EEG. The present paper builds on our previous work by incorporating a larger selection of EEG channels that capture both the spatial distribution and temporal patterns of EEG during sleep. Using a multivariate analysis approach, we obtain the "optimal" selection of the EEG channels and characteristics that are most suitable for EEG sleep state separation.

EEG signal description with spectral-envelope-based speech recognition features for detection of neonatal seizures

In this paper, features which are usually employed in automatic speech recognition (ASR) are used for the detection of seizures in newborn EEG. In particular, spectral envelope-based features, composed of spectral powers and their spectral derivatives are compared to the established feature set which has been previously developed for EEG analysis. The results indicate that the ASR features which model the spectral derivatives, either full-band or localized in frequency, yielded a performance improvement, in comparison to spectral-power-based features. Indeed it is shown here that they perform reasonably well in comparison with the conventional EEG feature set. The contribution of the ASR features was analyzed here using the support vector machines (SVM) recursive feature elimination technique. It is shown that the spectral derivative features consistently appear among the top-rank features. The study shows that the ASR features should be given a high priority when dealing with the description of the EEG signal.

Prognostic capacity of automated quantification of suppression time in the EEG of post-asphyctic full-term neonates

AIM

To evaluate the prognostic capacity of a new method for automatic quantification of the length of suppression time in the electroencephalogram (EEG) of a group of asphyxiated newborn infants.

METHODS

Twenty-one full-term newborn infants who had been resuscitated for severe birth asphyxia were studied. Eight channel continuous EEG was recorded for prolonged time periods during the first days of life. Artefact detection or rejection was not applied to the signals. The signals were fed through a pretrained classifier and then segmented into burst and suppression periods. Total suppression length per hour was calculated. All surviving patients were followed with structured neurodevelopmental assessments to at least 18 months of age.

RESULTS

The patients who developed neurodevelopmental disability or died had significant suppression periods in their EEG during the first days of life while the patients who had a normal follow-up had no or negligible amount of suppression.

CONCLUSIONS

This new method for automatic quantification of suppression periods in the raw, neonatal EEG discriminates infants with good from those with poor outcome.

Modeling electroencephalography waveforms with semi-supervised deep belief nets: fast classification and anomaly measurement

Clinical electroencephalography (EEG) records vast amounts of human complex data yet is still reviewed primarily by human readers. Deep belief nets (DBNs) are a relatively new type of multi-layer neural network commonly tested on two-dimensional image data but are rarely applied to times-series data such as EEG. We apply DBNs in a semi-supervised paradigm to model EEG waveforms for classification and anomaly detection. DBN performance was comparable to standard classifiers on our EEG dataset, and classification time was found to be 1.7-103.7 times faster than the other high-performing classifiers. We demonstrate how the unsupervised step of DBN learning produces an autoencoder that can naturally be used in anomaly measurement. We compare the use of raw, unprocessed data--a rarity in automated physiological waveform analysis--with hand-chosen features and find that raw data produce comparable classification and better anomaly measurement performance. These results indicate that DBNs and raw data inputs may be more effective for online automated EEG waveform recognition than other common techniques.