Quiet sleep detection in preterm infants using deep convolutional neural networks

Convolutional neural networks can identify brain interactions involved in decoding spatial auditory attention

Human listeners have the ability to direct their attention to a single speaker in a multi-talker environment. The neural correlates of selective attention can be decoded from a single trial of electroencephalography (EEG) data. In this study, leveraging the source-reconstructed and anatomically-resolved EEG data as inputs, we sought to employ CNN as an interpretable model to uncover task-specific interactions between brain regions, rather than simply to utilize it as a black box decoder. To this end, our CNN model was specifically designed to learn pairwise interaction representations for 10 cortical regions from five-second inputs. By exclusively utilizing these features for decoding, our model was able to attain a median accuracy of 77.56% for within-participant and 65.14% for cross-participant classification. Through ablation analysis together with dissecting the features of the models and applying cluster analysis, we were able to discern the presence of alpha-band-dominated inter-hemisphere interactions, as well as alpha- and beta-band dominant interactions that were either hemisphere-specific or were characterized by a contrasting pattern between the right and left hemispheres. These interactions were more pronounced in parietal and central regions for within-participant decoding, but in parietal, central, and partly frontal regions for cross-participant decoding. These findings demonstrate that our CNN model can effectively utilize features known to be important in auditory attention tasks and suggest that the application of domain knowledge inspired CNNs on source-reconstructed EEG data can offer a novel computational framework for studying task-relevant brain interactions.

A Sequential End-to-End Neonatal Sleep Staging Model with Squeeze and Excitation Blocks and Sequential Multi-Scale Convolution Neural Networks

Automatic sleep staging offers a quick and objective assessment for quantitatively interpreting sleep stages in neonates. However, most of the existing studies either do not encompass any temporal information, or simply apply neural networks to exploit temporal information at the expense of high computational overhead and modeling ambiguity. This limits the application of these methods to multiple scenarios. In this paper, a sequential end-to-end sleep staging model, SeqEESleepNet, which is competent for parallelly processing sequential epochs and has a fast training rate to adapt to different scenarios, is proposed. SeqEESleepNet consists of a sequence epoch generation (SEG) module, a sequential multi-scale convolution neural network (SMSCNN) and squeeze and excitation (SE) blocks. The SEG module expands independent epochs into sequential signals, enabling the model to learn the temporal information between sleep stages. SMSCNN is a multi-scale convolution neural network that can extract both multi-scale features and temporal information from the signal. Subsequently, the followed SE block can reassign the weights of features through mapping and pooling. Experimental results exhibit that in a clinical dataset, the proposed method outperforms the state-of-the-art approaches, achieving an overall accuracy, F1-score, and Kappa coefficient of 71.8%, 71.8%, and 0.684 on a three-class classification task with a single channel EEG signal. Based on our overall results, we believe the proposed method could pave the way for convenient multi-scenario neonatal sleep staging methods.

The past, current, and future of neonatal intensive care units with artificial intelligence: a systematic review

Machine learning and deep learning are two subsets of artificial intelligence that involve teaching computers to learn and make decisions from any sort of data. Most recent developments in artificial intelligence are coming from deep learning, which has proven revolutionary in almost all fields, from computer vision to health sciences. The effects of deep learning in medicine have changed the conventional ways of clinical application significantly. Although some sub-fields of medicine, such as pediatrics, have been relatively slow in receiving the critical benefits of deep learning, related research in pediatrics has started to accumulate to a significant level, too. Hence, in this paper, we review recently developed machine learning and deep learning-based solutions for neonatology applications. We systematically evaluate the roles of both classical machine learning and deep learning in neonatology applications, define the methodologies, including algorithmic developments, and describe the remaining challenges in the assessment of neonatal diseases by using PRISMA 2020 guidelines. To date, the primary areas of focus in neonatology regarding AI applications have included survival analysis, neuroimaging, analysis of vital parameters and biosignals, and retinopathy of prematurity diagnosis. We have categorically summarized 106 research articles from 1996 to 2022 and discussed their pros and cons, respectively. In this systematic review, we aimed to further enhance the comprehensiveness of the study. We also discuss possible directions for new AI models and the future of neonatology with the rising power of AI, suggesting roadmaps for the integration of AI into neonatal intensive care units.

Automatic neonatal sleep stage classification: A comparative study

Sleep is an essential feature of living beings. For neonates, it is vital for their mental and physical development. Sleep stage cycling is an important parameter to assess neonatal brain and physical development. Therefore, it is crucial to administer newborn's sleep in the neonatal intensive care unit (NICU). Currently, Polysomnography (PSG) is used as a gold standard method for classifying neonatal sleep patterns, but it is expensive and requires a lot of human involvement. Over the last two decades, multiple researchers are working on automatic sleep stage classification algorithms using electroencephalography (EEG), electrocardiography (ECG), and video. In this study, we present a comprehensive review of existing algorithms for neonatal sleep, their limitations and future recommendations. Additionally, a brief comparison of the extracted features, classification algorithms and evaluation parameters is reported in the proposed study.

A convolutional neural network-based decision support system for neonatal quiet sleep detection

Sleep plays an important role in neonatal brain and physical development, making its detection and characterization important for assessing early-stage development. In this study, we propose an automatic and computationally efficient algorithm to detect neonatal quiet sleep (QS) using a convolutional neural network (CNN). Our study used 38-hours of electroencephalography (EEG) recordings, collected from 19 neonates at Fudan Children's Hospital in Shanghai, China (Approval No. (2020) 22). To train and test the CNN, we extracted 12 prominent time and frequency domain features from 9 bipolar EEG channels. The CNN architecture comprised two convolutional layers with pooling and rectified linear unit (ReLU) activation. Additionally, a smoothing filter was applied to hold the sleep stage for 3 minutes. Through performance testing, our proposed method achieved impressive results, with 94.07% accuracy, 89.70% sensitivity, 94.40% specificity, 79.82% F1-score and a 0.74 kappa coefficient when compared to human expert annotations. A notable advantage of our approach is its computational efficiency, with the entire training and testing process requiring only 7.97 seconds. The proposed algorithm has been validated using leave one subject out (LOSO) validation, which demonstrates its consistent performance across a diverse range of neonates. Our findings highlight the potential of our algorithm for real-time neonatal sleep stage classification, offering a fast and cost-effective solution. This research opens avenues for further investigations in early-stage development monitoring and the assessment of neonatal health.

Deep learning-based algorithm accurately classifies sleep stages in preadolescent children with sleep-disordered breathing symptoms and age-matched controls

Introduction

Visual sleep scoring has several shortcomings, including inter-scorer inconsistency, which may adversely affect diagnostic decision-making. Although automatic sleep staging in adults has been extensively studied, it is uncertain whether such sophisticated algorithms generalize well to different pediatric age groups due to distinctive EEG characteristics. The preadolescent age group (10-13-year-olds) is relatively understudied, and thus, we aimed to develop an automatic deep learning-based sleep stage classifier specifically targeting this cohort.

Methods

A dataset (n = 115) containing polysomnographic recordings of Icelandic preadolescent children with sleep-disordered breathing (SDB) symptoms, and age and sex-matched controls was utilized. We developed a combined convolutional and long short-term memory neural network architecture relying on electroencephalography (F4-M1), electrooculography (E1-M2), and chin electromyography signals. Performance relative to human scoring was further evaluated by analyzing intra- and inter-rater agreements in a subset (n = 10) of data with repeat scoring from two manual scorers.

Results

The deep learning-based model achieved an overall cross-validated accuracy of 84.1% (Cohen's kappa κ = 0.78). There was no meaningful performance difference between SDB-symptomatic (n = 53) and control subgroups (n = 52) [83.9% (κ = 0.78) vs. 84.2% (κ = 0.78)]. The inter-rater reliability between manual scorers was 84.6% (κ = 0.78), and the automatic method reached similar agreements with scorers, 83.4% (κ = 0.76) and 82.7% (κ = 0.75).

Conclusion

The developed algorithm achieved high classification accuracy and substantial agreements with two manual scorers; the performance metrics compared favorably with typical inter-rater reliability between manual scorers and performance reported in previous studies. These suggest that our algorithm may facilitate less labor-intensive and reliable automatic sleep scoring in preadolescent children.

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

OBJECTIVE

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

SIGNIFICANCE

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

The Sleep Well Baby project: an automated real-time sleep–wake state prediction algorithm in preterm infants

Study Objectives

Sleep is an important driver of early brain development. However, sleep is often disturbed in preterm infants admitted to the neonatal intensive care unit (NICU). We aimed to develop an automated algorithm based on routinely measured vital parameters to classify sleep–wake states of preterm infants in real-time at the bedside.

Methods

In this study, sleep–wake state observations were obtained in 1-minute epochs using a behavioral scale developed in-house while vital signs were recorded simultaneously. Three types of vital parameter data, namely, heart rate, respiratory rate, and oxygen saturation, were collected at a low-frequency sampling rate of 0.4 Hz. A supervised machine learning workflow was used to train a classifier to predict sleep–wake states. Independent training (n = 37) and validation datasets were validation n = 9) datasets were used. Finally, a setup was designed for real-time implementation at the bedside.

Results

The macro-averaged area-under-the-receiver-operator-characteristic (AUROC) of the automated sleep staging algorithm ranged between 0.69 and 0.82 for the training data, and 0.61 and 0.78 for the validation data. The algorithm provided the most accurate prediction for wake states (AUROC = 0.80). These findings were well validated on an independent sample (AUROC = 0.77).

Conclusions

With this study, to the best of our knowledge, a reliable, nonobtrusive, and real-time sleep staging algorithm was developed for the first time for preterm infants. Deploying this algorithm in the NICU environment may assist and adapt bedside clinical work based on infants’ sleep–wake states, potentially promoting the early brain development and well-being of preterm infants.

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

OBJECTIVE

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

METHODS

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

RESULTS

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

INTERPRETATION

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

Abdul Majeed A, Moni MA. Diagnosis of hearing deficiency using EEG based AEP signals: CWT and improved-VGG16 pipeline

Hearing deficiency is the world's most common sensation of impairment and impedes human communication and learning. Early and precise hearing diagnosis using electroencephalogram (EEG) is referred to as the optimum strategy to deal with this issue. Among a wide range of EEG control signals, the most relevant modality for hearing loss diagnosis is auditory evoked potential (AEP) which is produced in the brain's cortex area through an auditory stimulus. This study aims to develop a robust intelligent auditory sensation system utilizing a pre-train deep learning framework by analyzing and evaluating the functional reliability of the hearing based on the AEP response. First, the raw AEP data is transformed into time-frequency images through the wavelet transformation. Then, lower-level functionality is eliminated using a pre-trained network. Here, an improved-VGG16 architecture has been designed based on removing some convolutional layers and adding new layers in the fully connected block. Subsequently, the higher levels of the neural network architecture are fine-tuned using the labelled time-frequency images. Finally, the proposed method's performance has been validated by a reputed publicly available AEP dataset, recorded from sixteen subjects when they have heard specific auditory stimuli in the left or right ear. The proposed method outperforms the state-of-art studies by improving the classification accuracy to 96.87% (from 57.375%), which indicates that the proposed improved-VGG16 architecture can significantly deal with AEP response in early hearing loss diagnosis.

A Multi-Scale Activity Transition Network for Data Translation in EEG Signals Decoding

Electroencephalogram (EEG) is a non-invasive collection method for brain signals. It has broad prospects in brain-computer interface (BCI) applications. Recent advances have shown the effectiveness of the widely used convolutional neural network (CNN) in EEG decoding. However, some studies reveal that a slight disturbance to the inputs, e.g., data translation, can change CNN's outputs. Such instability is dangerous for EEG-based BCI applications because signals in practice are different from training data. In this study, we propose a multi-scale activity transition network (MSATNet) to alleviate the influence of the translation problem in convolution-based models. MSATNet provides an activity state pyramid consisting of multi-scale recurrent neural networks to capture the relationship between brain activities, which is a translation-invariant feature. In the experiment, Kullback-Leibler divergence is applied to measure the degree of translation. The comprehensive results demonstrate that our method surpasses the AUC of 0.0080, 0.0254, 0.0393 in 1, 5, and 10 KL divergence compared to competitors with various convolution structures.

A Deep Shared Multi-Scale Inception Network Enables Accurate Neonatal Quiet Sleep Detection with Limited EEG Channels

In this paper, we introduce a new variation of the Convolutional Neural Network Inception block, called Sinc, for sleep stage classification in premature newborn babies using electroencephalogram (EEG). In practice, there are many medical centres where only a limited number of EEG channels are recorded. Existing automated algorithms mainly use multi-channel EEGs which perform poorly when fewer numbers of channels are available. The proposed Sinc utilizes multi-scale analysis to place emphasis on the temporal EEG information to be less dependent on the number of EEG channels. In Sinc, we increase the receptive fields through Inception while by additionally sharing the filters that have similar receptive fields, overfitting is controlled and the number of trainable parameters dramatically reduced. To train and test this model, 96 longitudinal EEG recordings from 26 premature infants are used. The Sinc-based model significantly outperforms state-of-the-art neonatal quiet sleep detection algorithms, with mean Kappa 0.77 0.01 (with 8-channel EEG) and 0.75 0.01 (with a single bipolar channel EEG). This is the first study using Inception-based networks for EEG analysis that utilizes filter sharing to improve efficiency and trainability. The suggested network can successfully detect quiet sleep stages with even a single EEG channel making it more practical especially in the hospital setting where cerebral function monitoring is predominantly used.

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.

A Hybrid DCNN-SVM Model for Classifying Neonatal Sleep and Wake States Based on Facial Expressions in Video

Sleep is a natural phenomenon controlled by the central nervous system. The sleep-wake pattern, which functions as an essential indicator of neurophysiological organization in the neonatal period, has profound meaning in the prediction of cognitive diseases and brain maturity. In recent years, unobtrusive sleep monitoring and automatic sleep staging have been intensively studied for adults, but much less for neonates. This work aims to investigate a novel video-based unobtrusive method for neonatal sleep-wake classification by analyzing the behavioral changes in the neonatal facial region. A hybrid model is proposed to monitor the sleep-wake patterns of human neonates. The model combines two algorithms: deep convolutional neural network (DCNN) and support vector machine (SVM), where DCNN works as a trainable feature extractor and SVM as a classifier. Data was collected from nineteen Chinese neonates at the Children's Hospital of Fudan University, Shanghai, China. The classification results are compared with the gold standard of video-electroencephalography scored by pediatric neurologists. Validations indicate that the proposed hybrid DCNN-SVM model achieved reliable performances in classifying neonatal sleep and wake states in RGB video frames (with the face region detected), with an accuracy of 93.8 ± 2.2% and an F1-score 0.93 ± 0.3.

The effect of early procedural pain in preterm infants on the maturation of electroencephalogram and heart rate variability

ABSTRACT

Preterm infants show a higher incidence of cognitive, social, and behavioral problems, even in the absence of major medical complications during their stay in the neonatal intensive care unit (NICU). Several authors suggest that early-life experience of stress and procedural pain could impact cerebral development and maturation resulting in an altered development of cognition, behavior, or motor patterns in later life. However, it remains very difficult to assess this impact of procedural pain on physiological development. This study describes the maturation of electroencephalogram (EEG) signals and heart rate variability in a prospective cohort of 92 preterm infants (<34 weeks gestational age) during their NICU stay. We took into account the number of noxious, ie, skin-breaking, procedures they were subjected in the first 5 days of life, which corresponded to a median age of 31 weeks and 4 days. Using physiological signal modelling, this study shows that a high exposure to early procedural pain, measured as skin-breaking procedures, increased the level of discontinuity in both EEG and heart rate variability in preterm infants. These findings have also been confirmed in a subset of the most vulnerable preterm infants with a gestational age lower than 29 weeks. We conclude that a high level of early pain exposure in the NICU increases the level of functional dysmaturity, which can ultimately impact preterm infants' future developmental outcome.

EEG-based detection of the locus of auditory attention with convolutional neural networks

In a multi-speaker scenario, the human auditory system is able to attend to one particular speaker of interest and ignore the others. It has been demonstrated that it is possible to use electroencephalography (EEG) signals to infer to which speaker someone is attending by relating the neural activity to the speech signals. However, classifying auditory attention within a short time interval remains the main challenge. We present a convolutional neural network-based approach to extract the locus of auditory attention (left/right) without knowledge of the speech envelopes. Our results show that it is possible to decode the locus of attention within 1-2 s, with a median accuracy of around 81%. These results are promising for neuro-steered noise suppression in hearing aids, in particular in scenarios where per-speaker envelopes are unavailable.

EEG-based detection of the locus of auditory attention with convolutional neural networks

In a multi-speaker scenario, the human auditory system is able to attend to one particular speaker of interest and ignore the others. It has been demonstrated that it is possible to use electroencephalography (EEG) signals to infer to which speaker someone is attending by relating the neural activity to the speech signals. However, classifying auditory attention within a short time interval remains the main challenge. We present a convolutional neural network-based approach to extract the locus of auditory attention (left/right) without knowledge of the speech envelopes. Our results show that it is possible to decode the locus of attention within 1-2 s, with a median accuracy of around 81%. These results are promising for neuro-steered noise suppression in hearing aids, in particular in scenarios where per-speaker envelopes are unavailable.

A multiplex visibility graph motif‐based convolutional neural network for characterizing sleep stages using EEG signals

Sleep is an essential integrant in everyone’s daily life; therefore, it is an important but challenging problem to characterize sleep stages from electroencephalogram (EEG) signals. The network motif has been developed as a useful tool to investigate complex networks. In this study, we developed a multiplex visibility graph motif‐based convolutional neural network (CNN) for characterizing sleep stages using EEG signals and then introduced the multiplex motif entropy as the quantitative index to distinguish the six sleep stages. The independent samples t‐test shows that the multiplex motif entropy values have significant differences among the six sleep stages. Furthermore, we developed a CNN model and employed the multiplex motif sequence as the input of the model to classify the six sleep stages. Notably, the classification accuracy of the six‐state stage detection was 85.27%. Results demonstrated the effectiveness of the multiplex motif in characterizing the dynamic features underlying different sleep stages, whereby they further provide an essential strategy for future sleep‐stage detection research.

A perinatal stress calculator for the neonatal intensive care unit: an unobtrusive approach

OBJECTIVE

Early experience of pain and stress in the neonatal intensive care unit is known to have an effect on the neurodevelopment of the infant. However, an automated method to quantify the procedural pain or perinatal stress in premature patients does not exist.

APPROACH

In the current study, EEG and ECG data were collected for more than 3 hours from 136 patients in order to quantify stress exposure. Specifically, features extracted from the EEG and heart-rate variability in both quiet and non-quiet sleep segments were used to develop a subspace linear-discriminant analysis stress classifier.

MAIN RESULTS

The main novelty of the study lies in the absence of intrusive methods or pain elicitation protocols to develop the stress classifier. Three main findings can be reported. First, we developed different stress classifiers for the different age groups and stress intensities, obtaining an area under the curve in the range [0.78-0.93] for non-quiet sleep and [0.77-0.96] for quiet sleep. Second, a dysmature EEG was found in patients under stress. Third, an enhanced cortical connectivity and increased brain-heart communication was correlated with a higher stress load, while the autonomic activity did not seem to be associated to stress exposure.

SIGNIFICANCE

The results shed a light on the pain and stress processing in preterm neonates, suggesting that software tools to investigate dysmature EEG might be helpful to assess stress load in premature patients. These results could be the foundation to assess the impact of stress on infants' development and to tune preventive care.

Proposing a convolutional neural network for stress assessment by means of derived heart rate from functional near infrared spectroscopy

BACKGROUND

Stress is known as one of the major factors threatening human health. A large number of studies have been performed in order to either assess or relieve stress by analyzing the brain and heart-related signals.

METHOD

In this study, a method based on the Convolutional Neural Network (CNN) approach is proposed to assess stress induced by the Montreal Imaging Stress Task. The proposed model is trained on the heart rate signal derived from functional Near-Infrared Spectroscopy (fNIRS), which is referred to as HRF. In this regard, fNIRS signals of 20 healthy volunteers were recorded using a configuration of 23 channels located on the prefrontal cortex. The proposed deep learning system consists of two main parts where in the first part, the one-dimensional convolutional neural network is employed to build informative activation maps, and then in the second part, a stack of deep fully connected layers is used to predict the stress existence probability. Thereafter, the employed CNN method is compared with the Dense Neural Network, Support Vector Machine, and Random Forest regarding various classification metrics.

RESULTS

Results clearly showed the superiority of CNN over all other methods. Additionally, the trained HRF model significantly outperforms the model trained on the filtered fNIRS signals, where the HRF model could achieve 98.69 ± 0.45% accuracy, which is 10.09% greater than the accuracy obtained by the fNIRS model.

CONCLUSIONS

Employment of the proposed deep learning system trained on the HRF measurements leads to higher stress classification accuracy than the accuracy reported in the existing studies where the same experimental procedure has been done. Besides, the proposed method suggests better stability with lower variation in prediction. Furthermore, its low computational cost opens up the possibility to be applied in real-time monitoring of stress assessment.

Applying a data-driven approach to quantify EEG maturational deviations in preterms with normal and abnormal neurodevelopmental outcomes

Premature babies are subjected to environmental stresses that can affect brain maturation and cause abnormal neurodevelopmental outcome later in life. Better understanding this link is crucial to developing a clinical tool for early outcome estimation. We defined maturational trajectories between the Electroencephalography (EEG)-derived ‘brain-age’ and postmenstrual age (the age since the last menstrual cycle of the mother) from longitudinal recordings during the baby’s stay in the Neonatal Intensive Care Unit. Data consisted of 224 recordings (65 patients) separated for normal and abnormal outcome at 9–24 months follow-up. Trajectory deviations were compared between outcome groups using the root mean squared error (RMSE) and maximum trajectory deviation (δ^max). 113 features were extracted (per sleep state) to train a data-driven model that estimates brain-age, with the most prominent features identified as potential maturational and outcome-sensitive biomarkers. RMSE and δ^max showed significant differences between outcome groups (cluster-based permutation test, p < 0.05). RMSE had a median (IQR) of 0.75 (0.60–1.35) weeks for normal outcome and 1.35 (1.15–1.55) for abnormal outcome, while δ^max had a median of 0.90 (0.70–1.70) and 1.90 (1.20–2.90) weeks, respectively. Abnormal outcome trajectories were associated with clinically defined dysmature and disorganised EEG patterns, cementing the link between early maturational trajectories and neurodevelopmental outcome.

Neonatal sleep stage identification using long short-term memory learning system

Neonatal sleep analysis at the neonatal intensive care units (NICU) is critical for the diagnosis of any brain growth risks during the early stages of life. In this paper, an investigation is carried out on the use of a long short-term memory (LSTM) learning system in automatic sleep stage scoring in neonates. The developed algorithm automatically classifies sleep stages based on inputs from a single channel EEG recording. Up to this date, only a single study have developed an approach for automatic sleep stage scoring in neonatal sleep signals using deep neural network (DNN). A total of 5095 sleep stages signals acquired from EEG recordings of the University of Pittsburgh are used in this study. The sleep stages are annotated by a medical doctor from the Pediatric Neurology Department of Case Western Reserve University for three neonatal sleep stages including the awake (W), active sleep (AS), and quiet sleep (QS) stages on every 60-s epoch. The signals are pre-processed through normalization and filtering. The resulted signals are divided following 4-, 6-, and 10-fold cross-validation schemes. The training and classification process is done using a bi-directional LSTM network classifier built with pre-defined training parameters. At the end, the developed algorithm is evaluated along with a complete summary table that reports the results of this study and other state-of-the-art studies. The current study achieved high levels of Cohen's kappa (κ), accuracy, and F1 score with 91.37%, 96.81%, and 94.43%, respectively. Based on the confusion matrix, the overall true positives percentage reached 95.21%. The developed algorithm gave promising results in automatic sleep stage scoring in neonatal sleep signals. Future work include LSTM architecture and training parameters improvements to enhance the overall accuracy of the classifier.

A convolutional neural network outperforming state-of-the-art sleep staging algorithms for both preterm and term infants

OBJECTIVE

To classify sleep states using electroencephalogram (EEG) that reliably works over a wide range of preterm ages, as well as term age.

APPROACH

A convolutional neural network is developed to perform 2- and 4-class sleep classification in neonates. The network takes as input an 8-channel 30 s EEG segment and outputs the sleep state probabilities. Apart from simple downsampling of the input and smoothing of the output, the suggested network is an end-to-end algorithm that avoids the need for hand-crafted feature selection or complex pre/post processing steps. To train and test this method, 113 EEG recordings from 42 infants are used.

MAIN RESULTS

For quiet sleep detection (the 2-class problem), mean kappa between the network estimate and the ground truth annotated by EEG human experts is 0.76. The sensitivity and specificity are 90% and 88%, respectively. For 4-class classification, mean kappa is 0.64. The averaged sensitivity and specificity (1 versus all) respectively equal 72% and 91%. The results outperform current state-of-the-art methods for which kappa ranges from 0.66 to 0.70 in preterm and from 0.51 to 0.61 in term infants, based on training and testing using the same database.

SIGNIFICANCE

The proposed method has the highest reported accuracy for EEG sleep state classification for both preterm and term age neonates.

Decomposition of a Multiscale Entropy Tensor for Sleep Stage Identification in Preterm Infants

Established sleep cycling is one of the main hallmarks of early brain development in preterm infants, therefore, automated classification of the sleep stages in preterm infants can be used to assess the neonate’s cerebral maturation. Tensor algebra is a powerful tool to analyze multidimensional data and has proven successful in many applications. In this paper, a novel unsupervised algorithm to identify neonatal sleep stages based on the decomposition of a multiscale entropy tensor is presented. The method relies on the difference in electroencephalography(EEG) complexity between the neonatal sleep stages and is evaluated on a dataset of 97 EEG recordings. An average sensitivity, specificity, accuracy and area under the receiver operating characteristic curve of 0.80, 0.79, 0.79 and 0.87 was obtained if the rank of the tensor decomposition is selected based on the age of the infant.