Deep Learning for EEG Seizure Detection in Preterm Infants

Combining EEG Features and Convolutional Autoencoder for Neonatal Seizure Detection

Neonatal epilepsy is a common emergency phenomenon in neonatal intensive care units (NICUs), which requires timely attention, early identification, and treatment. Traditional detection methods mostly use supervised learning with enormous labeled data. Hence, this study offers a semi-supervised hybrid architecture for detecting seizures, which combines the extracted electroencephalogram (EEG) feature dataset and convolutional autoencoder, called Fd-CAE. First, various features in the time domain and entropy domain are extracted to characterize the EEG signal, which helps distinguish epileptic seizures subsequently. Then, the unlabeled EEG features are fed into the convolutional autoencoder (CAE) for training, which effectively represents EEG features by optimizing the loss between the input and output features. This unsupervised feature learning process can better combine and optimize EEG features from unlabeled data. After that, the pre-trained encoder part of the model is used for further feature learning of labeled data to obtain its low-dimensional feature representation and achieve classification. This model is performed on the neonatal EEG dataset collected at the University of Helsinki Hospital, which has a high discriminative ability to detect seizures, with an accuracy of 92.34%, precision of 93.61%, recall rate of 98.74%, and F1-score of 95.77%, respectively. The results show that unsupervised learning by CAE is beneficial to the characterization of EEG signals, and the proposed Fd-CAE method significantly improves classification performance.

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

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

Multiple Classification of Brain MRI Autism Spectrum Disorder by Age and Gender Using Deep Learning

The fact that the rapid and definitive diagnosis of autism cannot be made today and that autism cannot be treated provides an impetus to look into novel technological solutions. To contribute to the resolution of this problem through multiple classifications by considering age and gender factors, in this study, two quadruple and one octal classifications were performed using a deep learning (DL) approach. Gender in one of the four classifications and age groups in the other were considered. In the octal classification, classes were created considering gender and age groups. In addition to the diagnosis of ASD (Autism Spectrum Disorders), another goal of this study is to find out the contribution of gender and age factors to the diagnosis of ASD by making multiple classifications based on age and gender for the first time. Brain structural MRI (sMRI) scans of participators with ASD and TD (Typical Development) were pre-processed in the system originally designed for this purpose. Using the Canny Edge Detection (CED) algorithm, the sMRI image data was cropped in the data pre-processing stage, and the data set was enlarged five times with the data augmentation (DA) techniques. The most optimal convolutional neural network (CNN) models were developed using the grid search optimization (GSO) algorism. The proposed DL prediction system was tested with the five-fold cross-validation technique. Three CNN models were designed to be used in the system. The first of these models is the quadruple classification model created by taking gender into account (model 1), the second is the quadruple classification model created by taking into account age (model 2), and the third is the eightfold classification model created by taking into account both gender and age (model 3). ). The accuracy rates obtained for all three designed models are 80.94, 85.42 and 67.94, respectively. These obtained accuracy rates were compared with pre-trained models by using the transfer learning approach. As a result, it was revealed that age and gender factors were effective in the diagnosis of ASD with the system developed for ASD multiple classifications, and higher accuracy rates were achieved compared to pre-trained models.

Neuropsychology and Electroencephalography in Rural Children at Neurodevelopmental Risk: A Scoping Review

Children from rural areas face numerous possibilities of neurodevelopmental conditions that may compromise their well-being and optimal development. Neuropsychology and electroencephalography (EEG) have shown strong agreement in detecting correlations between these two variables and suggest an association with specific environmental and social risk factors. The present scoping review aims to describe studies reporting associations between EEG features and cognitive impairment in children from rural or vulnerable environments and describe the main risk factors influencing EEG abnormalities in these children. The method for this purpose was based on a string-based review from PubMed, EBSCOhost, and Web of Science, following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA). Qualitative and quantitative analyses were conducted from the outcomes that complied with the selected criteria. In total, 2280 records were identified; however, only 26 were eligible: 15 for qualitative and 11 for quantitative analysis. The findings highlight the significant literature on EEG and its relationship with cognitive impairment from studies in children with epilepsy and malnutrition. In general, there is evidence for the advantages of implementing EEG diagnosis and research techniques in children living under risk conditions. Specific associations between particular EEG features and cognitive impairment are described in the reviewed literature in children. Further research is needed to better describe and integrate the state of the art regarding EEG feature extraction.

Lightweight Seizure Detection Based on Multi-Scale Channel Attention

Epilepsy is one kind of neurological disease characterized by recurring seizures. Recurrent seizures can cause ongoing negative mental and cognitive damage to the patient. Therefore, timely diagnosis and treatment of epilepsy are crucial for patients. Manual electroencephalography (EEG) signals analysis is time and energy consuming, making automatic detection using EEG signals particularly important. Many deep learning algorithms have thus been proposed to detect seizures. These methods rely on expensive and bulky hardware, which makes them unsuitable for deployment on devices with limited resources due to their high demands on computer resources. In this paper, we propose a novel lightweight neural network for seizure detection using pure convolutions, which is composed of inverted residual structure and multi-scale channel attention mechanism. Compared with other methods, our approach significantly reduces the computational complexity, making it possible to deploy on low-cost portable devices for seizures detection. We conduct experiments on the CHB-MIT dataset and achieves 98.7% accuracy, 98.3% sensitivity and 99.1% specificity with 2.68[Formula: see text]M multiply-accumulate operations (MACs) and only 88[Formula: see text]K parameters.

Unsupervised domain adaptation for cross-patient seizure classification

Objective. Epileptic seizure is a chronic neurological disease affecting millions of patients. Electroencephalogram (EEG) is the gold standard in epileptic seizure classification. However, its low signal-to-noise ratio, strong non-stationarity, and large individual difference nature make it difficult to directly extend the seizure classification model from one patient to another. This paper considers multi-source unsupervised domain adaptation for cross-patient EEG-based seizure classification, i.e. there are multiple source patients with labeled EEG data, which are used to label the EEG trials of a new patient.Approach. We propose an source domain selection (SDS)-global domain adaptation (GDA)-target agent subdomain adaptation (TASA) approach, which includes SDS to filter out dissimilar source domains, GDA to align the overall distributions of the selected source domains and the target domain, and TASA to identify the most similar source domain to the target domain so that its labels can be utilized.Main results. Experiments on two public seizure datasets demonstrated that SDS-GDA-TASA outperformed 13 existing approaches in unsupervised cross-patient seizure classification.Significance. Our approach could save clinicians plenty of time in labeling EEG data for epilepsy patients, greatly increasing the efficiency of seizure diagnostics.

A Class-Imbalance Aware and Explainable Spatio-Temporal Graph Attention Network for Neonatal Seizure Detection

Seizures are the most prevalent clinical indication of neurological disorders in neonates. In this study, a class-imbalance aware and explainable deep learning approach based on Convolutional Neural Networks (CNNs) and Graph Attention Networks (GATs) is proposed for the accurate automated detection of neonatal seizures. The proposed model integrates the temporal information of EEG signals with the spatial information on the EEG channels through the graph representation of the multi-channel EEG segments. One-dimensional CNNs are used to automatically develop a feature set that accurately represents the differences between seizure and nonseizure epochs in the time domain. By employing GAT, the attention mechanism is utilized to emphasize the critical channel pairs and information flow among brain regions. GAT coefficients were then used to empirically visualize the important regions during the seizure and nonseizure epochs, which can provide valuable insight into the location of seizures in the neonatal brain. Additionally, to tackle the severe class imbalance in the neonatal seizure dataset using under-sampling and focal loss techniques are used. Overall, the final Spatio-Temporal Graph Attention Network (ST-GAT) outperformed previous benchmarked methods with a mean AUC of 96.6% and Kappa of 0.88, demonstrating its high accuracy and potential for clinical applications.

2D Wavelet-Scalogram Deep-Learning for Seizures Pattern Identification in the Post-Hypoxic-Ischemic EEG of Preterm Fetal Sheep

Neonatal seizures after an hypoxic-ischemic (HI) event in preterm newborns can contribute to neural injury and cause impaired brain development. Preterm neonatal seizures are often not detected or their occurrence underestimated. Therefore, there is a need to improve knowledge about preterm seizures that can help establish diagnostic tools for accurate identification of seizures and for determining morphological differences. We have previously shown the superior utility of deep-learning algorithms for the accurate identification and quantification of post-HI microscale epileptiform transients (e.g., gamma spikes and sharp waves) in preterm fetal sheep models; before the irreversible secondary phase of cerebral energy failure starts by the bursts of high-amplitude stereotypic evolving seizures (HAS) in the signal. We have previously developed successful deep-learning algorithms that accurately identify and quantify the micro-scale transients, during the latent phase. Building up on our deep-learning strategies, this work introduces a real-time deep-learning-based pattern fusion approach to identify HAS in the 256Hz sampled post-HI data from our preterm fetuses. Here, for the first time, we propose a 17-layer deep convolutional neural network (CNN) classifier fed with 2D wavelet-scalogram (WS) images of the EEG patterns for accurate seizure identification. The WS-CNN classifier was cross-validated over 1812 manually annotated EEG segments during ~6 to 48 hours post-HI recordings. The classifier accurately recognized HAS patterns with 97.19% overall accuracy (AUC = 0.96).Clinical relevance-The promising results from this preliminary work indicate the ability of the proposed WS-CNN pattern classifier to identify HI-related seizures in the neonatal preterm brain using 256Hz EEG; the frequency commonly used clinically for data collection.

An Evolutionary Attention-Based Network for Medical Image Classification

Deep learning has become a primary choice in medical image analysis due to its powerful representation capability. However, most existing deep learning models designed for medical image classification can only perform well on a specific disease. The performance drops dramatically when it comes to other diseases. Generalizability remains a challenging problem. In this paper, we propose an evolutionary attention-based network (EDCA-Net), which is an effective and robust network for medical image classification tasks. To extract task-related features from a given medical dataset, we first propose the densely connected attentional network (DCA-Net) where feature maps are automatically channel-wise weighted, and the dense connectivity pattern is introduced to improve the efficiency of information flow. To improve the model capability and generalizability, we introduce two types of evolution: intra- and inter-evolution. The intra-evolution optimizes the weights of DCA-Net, while the inter-evolution allows two instances of DCA-Net to exchange training experience during training. The evolutionary DCA-Net is referred to as EDCA-Net. The EDCA-Net is evaluated on four publicly accessible medical datasets of different diseases. Experiments showed that the EDCA-Net outperforms the state-of-the-art methods on three datasets and achieves comparable performance on the last dataset, demonstrating good generalizability for medical image classification.

Toward automated prediction of sudden unexpected death in epilepsy

Sudden unexpected death in epilepsy (SUDEP) is a devastating yet overlooked complication of epilepsy. The rare and complex nature of SUDEP makes it challenging to study. No prediction or prevention of SUDEP is currently available in a clinical setting. In the past decade, significant advances have been made in our knowledge of the pathophysiologic cascades that lead to SUDEP. In particular, studies of brain, heart, and respiratory functions in both human patients at the epilepsy monitoring unit and animal models during fatal seizures provide critical information to integrate computational tools for SUDEP prediction. The rapid advances in automated seizure detection and prediction algorithms provide a fundamental framework for their adaption in predicting SUDEP. If a SUDEP can be predicted, then there will be a potential for medical intervention to be administered, either by their caregivers or via an implanted device automatically delivering electrical stimulation or medication, and finally save lives from fatal seizures. This article presents recent developments of SUDEP studies focusing on the pathophysiologic basis of SUDEP and computational implications of machine learning techniques that can be adapted and extended for SUDEP prediction. This article also discusses some novel ideas for SUDEP prediction and rescue including principal component analysis and closed-loop intervention.

Application and potential of artificial intelligence in neonatal medicine

Neonatal care is becoming increasingly complex with large amounts of rich, routinely recorded physiological, diagnostic and outcome data. Artificial intelligence (AI) has the potential to harness this vast quantity and range of information and become a powerful tool to support clinical decision making, personalised care, precise prognostics, and enhance patient safety. Current AI approaches in neonatal medicine include tools for disease prediction and risk stratification, neurological diagnostic support and novel image recognition technologies. Key to the integration of AI in neonatal medicine is the understanding of its limitations and a standardised critical appraisal of AI tools. Barriers and challenges to this include the quality of datasets used, performance assessment, and appropriate external validation and clinical impact studies. Improving digital literacy amongst healthcare professionals and cross-disciplinary collaborations are needed to harness the full potential of AI to help take the next significant steps in improving neonatal outcomes for high-risk infants.

Both Cross-Patient and Patient-Specific Seizure Detection Based on Self-Organizing Fuzzy Logic

Automatic epilepsy detection is of great significance for the diagnosis and treatment of patients. Most detection methods are based on patient-specific models and have achieved good results. However, in practice, new patients do not have their own previous EEG data and therefore cannot be initially diagnosed. If the EEG data of other patients can be used to achieve cross-patient detection, and cross-patient and patient-specific experiments can be combined at the same time, this method will be more widely used. In this work, an EEG classification model based on a self-organizing fuzzy logic (SOF) classifier is proposed for both cross-patient and patient-specific seizure detection. After preprocessing, the features of the original EEG signal are extracted and sent to the SOF classifier. This classification model is free from predefined parameters or a prior assumption regarding the EEG data generation model and only stores the key meta-parameters in memory. Therefore, it is very suitable for large-scale EEG signals in cross-patient detection. Selecting different granularity and classification distance in two different experiments after post-processing will achieve the best results. Experiments were conducted using a long-term continuous scalp EEG database and the [Formula: see text]-mean of cross-patient and patient-specific detection reached 83.35% and 92.04%, respectively. A comparison with other methods shows that there is greater performance and generalizability with this method.

Transfer learning for non-image data in clinical research: A scoping review

BACKGROUND

Transfer learning is a form of machine learning where a pre-trained model trained on a specific task is reused as a starting point and tailored to another task in a different dataset. While transfer learning has garnered considerable attention in medical image analysis, its use for clinical non-image data is not well studied. Therefore, the objective of this scoping review was to explore the use of transfer learning for non-image data in the clinical literature.

METHODS AND FINDINGS

We systematically searched medical databases (PubMed, EMBASE, CINAHL) for peer-reviewed clinical studies that used transfer learning on human non-image data. We included 83 studies in the review. More than half of the studies (63%) were published within 12 months of the search. Transfer learning was most often applied to time series data (61%), followed by tabular data (18%), audio (12%) and text (8%). Thirty-three (40%) studies applied an image-based model to non-image data after transforming data into images (e.g. spectrograms). Twenty-nine (35%) studies did not have any authors with a health-related affiliation. Many studies used publicly available datasets (66%) and models (49%), but fewer shared their code (27%).

CONCLUSIONS

In this scoping review, we have described current trends in the use of transfer learning for non-image data in the clinical literature. We found that the use of transfer learning has grown rapidly within the last few years. We have identified studies and demonstrated the potential of transfer learning in clinical research in a wide range of medical specialties. More interdisciplinary collaborations and the wider adaption of reproducible research principles are needed to increase the impact of transfer learning in clinical research.

Hysteresis Modeling in Iron-Dominated Magnets Based on a Multi-Layered Narx Neural Network Approach

A full-fledged neural network modeling, based on a Multi-layered Nonlinear Autoregressive Exogenous Neural Network (NARX) architecture, is proposed for quasi-static and dynamic hysteresis loops, one of the most challenging topics for computational magnetism. This modeling approach overcomes drawbacks in attaining better than percent-level accuracy of classical and recent approaches for accelerator magnets, that combine hybridization of standard hysteretic models and neural network architectures. By means of an incremental procedure, different Deep Neural Network Architectures are selected, fine-tuned and tested in order to predict magnetic hysteresis in the context of electromagnets. Tests and results show that the proposed NARX architecture best fits the measured magnetic field behavior of a reference quadrupole at CERN. In particular, the proposed modeling framework leads to a percent error below 0.02% for the magnetic field prediction, thus outperforming state of the art approaches and paving a very promising way for future real time applications.

Considerations for Drug Dosing in Premature Infants

In premature infants, effective and safe drug therapy depends on optimal dose selection and requires a thorough understanding of the underlying disease(s) of these fragile infants as well as the pharmacokinetics and pharmacodynamics of the drugs selected to treat their diseases. Differences in gestational and postnatal age or weight are the major determinants of the observed variability in drug disposition and effect in these infants. This article presents an outline on how to translate the results of a population pharmacokinetic/pharmacodynamic study into rational dosing regimens, and how physiologically based pharmacokinetic modeling, electronic health records, and the abundantly available data of vital functions of premature infants during their stay in the neonatal intensive care unit for evaluation of their pharmacotherapy can be used to tailor the most safe and effective dose in these infants.

Grading hypoxic-ischemic encephalopathy in neonatal EEG with convolutional neural networks and quadratic time-frequency distributions

OBJECTIVE

To develop an automated system to classify the severity of hypoxic-ischaemic encephalopathy injury (HIE) in neonates from the background electroencephalogram (EEG).

METHOD

By combining a quadratic time{frequency distribution (TFD) with a convolutional neural network, we develop a system that classifies 4 EEG grades of HIE. The network learns directly from the two- dimensional TFD through 3 independent layers with convolution in the time, frequency, and time{frequency directions. Computationally efficient algorithms make it feasible to transform each 5 minute epoch to the time-frequency domain by controlling for oversampling to reduce both computation and computer memory. The system is developed on EEG recordings from 54 neonates. Then the system is validated on a large unseen dataset of 338 hours of EEG recordings from 91 neonates obtained across multiple international centres.

RESULTS

The proposed EEG HIE-grading system achieves a leave-one-subject-out testing accuracy of 88.9% and kappa of 0.84 on the development dataset. Accuracy for the large unseen test dataset is 69.5% (95% confidence interval, CI: 65.3 to 73.6%) and kappa of 0.54, which is a significant (P < 0.001) improvement over a state-of-the-art feature-based method with an accuracy of 56.8% (95% CI: 51.4 to 61.7%) and kappa of 0.39. Performance of the proposed system was unaffected when the number of channels in testing was reduced from 8 to 2|accuracy for large validation dataset remained at 69.5% (95% CI: 65.5 to 74.0%).

SIGNIFICANCE

The proposed system outperforms the state-of-the-art machine learning algorithms for EEG grade classification on a large multi-centre unseen dataset, indicating the potential to assist clinical decision making for neonates with HIE.