GraphSleepFormer: a multi-modal graph neural network for sleep staging in OSA patients

Objective.Obstructive sleep apnea (OSA) is a prevalent sleep disorder. Accurate sleep staging is one of the prerequisites in the study of sleep-related disorders and the evaluation of sleep quality. We introduce a novel GraphSleepFormer (GSF) network designed to effectively capture global dependencies and node characteristics in graph-structured data.Approach.The network incorporates centrality coding and spatial coding into its architecture. It employs adaptive learning of adjacency matrices for spatial encoding between channels located on the head, thereby encoding graph structure information to enhance the model's representation and understanding of spatial relationships. Centrality encoding integrates the degree matrix into node features, assigning varying degrees of attention to different channels. Ablation experiments demonstrate the effectiveness of these encoding methods. The Shapley Additive Explanations (SHAP) method was employed to evaluate the contribution of each channel in sleep staging, highlighting the necessity of using multimodal data.Main results.We trained our model on overnight polysomnography data collected from 28 OSA patients in a clinical setting and achieved an overall accuracy of 80.10%. GSF achieved performance comparable to state-of-the-art methods on two subsets of the ISRUC database.Significance.The GSF Accurately identifies sleep periods, providing a critical basis for diagnosing and treating OSA, thereby contributing to advancements in sleep medicine.

Explainable AI-driven scalogram analysis and optimized transfer learning for sleep apnea detection with single-lead electrocardiograms

Sleep apnea, a fatal sleep disorder causing repetitive respiratory cessation, requires immediate intervention due to neuropsychological issues. However, existing approaches such as polysomnography, considered the most reliable and accurate test to detect sleep apnea, frequently require multichannel ECG recordings and advanced feature extraction algorithms, significantly restricting their wider application. Deep learning has recently emerged as a viable method for detecting sleep apnea. Our study describes a unique method for detecting sleep apnea utilizing single-lead ECG signals and deep learning techniques. In our proposed method, we have employed the continuous wavelet transform to convert electrocardiogram (ECG) signals into scalograms, which allows us to capture both the time and frequency domains. To enhance the classification performance, we have implemented an optimized pre-trained GoogLeNet architecture as a transfer learning model. In this study, we have analyzed the PhysioNet Apnea ECG dataset, UCDDB dataset and the MIT-BIH polysomnographic dataset for training and evaluation for per-segment classification, to demonstrate the effectiveness of our approach. In our experiments, the proposed model achieves remarkable results, with an accuracy of 93.85%, sensitivity of 93.42%, specificity of 94.30%, and F1 score of 93.83% for the Apnea ECG dataset in per-segment classification. Our model excels on the UCDDB dataset with 87.20% accuracy, 80.99% sensitivity, 93.39% specificity, and an 86.34% F1-score. Furthermore, the model obtains 88.58% accuracy, 88.78% sensitivity, 88.38% specificity, and 88.61% F1 score on the MIT BIH polysomnographic dataset, showing its robust performance and balanced precision-recall trade-off. Afterwards, LIME, an explainable AI method, has been implemented to illustrate the insights responsible for predicting apnea or non apnea.

SleepECG-Net: Explainable Deep Learning Approach With ECG for Pediatric Sleep Apnea Diagnosis

Obstructive sleep apnea (OSA) in children is a prevalent and serious respiratory condition linked to cardiovascular morbidity. Polysomnography, the standard diagnostic approach, faces challenges in accessibility and complexity, leading to underdiagnosis. To simplify OSA diagnosis, deep learning (DL) algorithms have been developed using cardiac signals, but they often lack interpretability. Our study introduces a novel interpretable DL approach (SleepECG-Net) for directly estimating OSA severity in at-risk children. A combination of convolutional and recurrent neural networks (CNN-RNN) was trained on overnight electrocardiogram (ECG) signals. Gradient-weighted Class Activation Mapping (Grad-CAM), an eXplainable Artificial Intelligence (XAI) algorithm, was applied to explain model decisions and extract ECG patterns relevant to pediatric OSA. Accordingly, ECG signals from the semi-public Childhood Adenotonsillectomy Trial (CHAT, n = 1610) and Cleveland Family Study (CFS,n = 64), and the private University of Chicago (UofC, n = 981) databases were used. OSA diagnostic performance reached 4-class Cohen's Kappa of 0.410, 0.335, and 0.249 in CHAT, UofC, and CFS, respectively. The proposal demonstrated improved performance with increased severity along with heightened cardiovascular risk. XAI findings highlighted the detection of established ECG features linked to OSA, such as bradycardia-tachycardia events and delayed ECG patterns during apnea/hypopnea occurrences, focusing on clusters of events. Furthermore, Grad-CAM heatmaps identified potential ECG patterns indicating cardiovascular risk, such as P, T, and U waves, QT intervals, and QRS complex variations. Hence, SleepECG-Net approach may improve pediatric OSA diagnosis by also offering cardiac risk factor information, thereby increasing clinician confidence in automated systems, and promoting their effective adoption in clinical practice.

WaveSleepNet: An Interpretable Network for Expert-Like Sleep Staging

Although deep learning algorithms have proven their efficiency in automatic sleep staging, their "black-box" nature has limited their clinical adoption. In this study, we propose WaveSleepNet, an interpretable neural network for sleep staging that reasons in a similar way to sleep clinical experts. In this network, we utilize the latent space representations generated during training to identify characteristic wave prototypes corresponding to different sleep stages. The feature representation of an input signal is segmented into patches within the latent space, each of which is compared against the learned wave prototypes. The proximity between these patches and the wave prototypes is quantified through scores, indicating the prototypes' presence and relative proportion within the signal. The scores serve as the decision-making criteria for final sleep staging. During training, an ensemble of loss functions is employed for the prototypes' diversity and robustness. Furthermore, the learned wave prototypes are visualized by analyzing occlusion sensitivity. The efficacy of WaveSleepNet is validated across three public datasets, achieving sleep staging performance that are on par with those of the state-of-the-art models. A detailed case study examining the decision-making process of WaveSleepNet demonstrates that it aligns closely with American Academy of Sleep Medicine (AASM) manual guidelines. Another case study systematically explained the misidentified reasons behind each sleep stage. WaveSleepNet's transparent process provides specialists with direct access to the physiological significance of the model's criteria, allowing for future validation, adoption and further enrichment by sleep clinical experts.

EEG-powered cerebral transformer for athletic performance

Introduction

In recent years, with advancements in wearable devices and biosignal analysis technologies, sports performance analysis has become an increasingly popular research field, particularly due to the growing demand for real-time monitoring of athletes' conditions in sports training and competitive events. Traditional methods of sports performance analysis typically rely on video data or sensor data for motion recognition. However, unimodal data often fails to fully capture the neural state of athletes, leading to limitations in accuracy and real-time performance when dealing with complex movement patterns. Moreover, these methods struggle with multimodal data fusion, making it difficult to fully leverage the deep information from electroencephalogram (EEG) signals.

Methods

To address these challenges, this paper proposes a "Cerebral Transformer" model based on EEG signals and video data. By employing an adaptive attention mechanism and cross-modal fusion, the model effectively combines EEG signals and video streams to achieve precise recognition and analysis of athletes' movements. The model's effectiveness was validated through experiments on four datasets: SEED, DEAP, eSports Sensors, and MODA. The results show that the proposed model outperforms existing mainstream methods in terms of accuracy, recall, and F1 score, while also demonstrating high computational efficiency.

Results and discussion

The significance of this study lies in providing a more comprehensive and efficient solution for sports performance analysis. Through cross-modal data fusion, it not only improves the accuracy of complex movement recognition but also provides technical support for monitoring athletes' neural states, offering important applications in sports training and medical rehabilitation.

FlexSleepTransformer: a transformer-based sleep staging model with flexible input channel configurations

Clinical sleep diagnosis traditionally relies on polysomnography (PSG) and expert manual classification of sleep stages. Recent advancements in deep learning have shown promise in automating sleep stage classification using a single PSG channel. However, variations in PSG acquisition devices and environments mean that the number of PSG channels can differ across sleep centers. To integrate a sleep staging method into clinical practice effectively, it must accommodate a flexible number of PSG channels. In this paper, we proposed FlexSleepTransformer, a transformer-based model designed to handle varying number of input channels, making it adaptable to diverse sleep staging datasets. We evaluated FlexSleepTransformer using two distinct datasets: the public SleepEDF-78 dataset and the local SleepUHS dataset. Notably, FlexSleepTransformer is the first model capable of simultaneously training on datasets with differing number of PSG channels. Our experiments showed that FlexSleepTransformer trained on both datasets together achieved 98% of the accuracy compared to models trained on each dataset individually. Furthermore, it outperformed models trained exclusively on one dataset when tested on the other dataset. Additionally, FlexSleepTransformer surpassed state-of-the-art CNN and RNN-based models on both datasets. Due to its adaptability with varying channels numbers, FlexSleepTransformer holds significant potential for clinical adoption, especially when trained with data from a wide range of sleep centers.

An ensemble method for improving robustness against the electrode contact problems in automated sleep stage scoring

In-home automated scoring systems are in high demand; however, the current systems are not widely adopted in clinical settings. Problems with electrode contact and restriction on measurable signals often result in unstable and inaccurate scoring for clinical use. To address these issues, we propose a method based on ensemble of small sleep stage scoring models with different input signal sets. By excluding models that employ problematic signals from the voting process, our method can mitigate the effects of electrode contact failure. Comparative experiments demonstrated that our method could reduce the impact of contact problems and improve scoring accuracy for epochs with problematic signals by 8.3 points, while also decreasing the deterioration in scoring accuracy from 7.9 to 0.3 points compared to typical methods. Additionally, we confirmed that assigning different input sets to small models did not diminish the advantages of the ensemble but instead increased its efficacy. The proposed model can improve overall scoring accuracy and minimize the effect of problematic signals simultaneously, making in-home sleep stage scoring systems more suitable for clinical practice.

Performance Investigation of Somfit Sleep Staging Algorithm

Purpose

To investigate accuracy of the sleep staging algorithm in a new miniaturized home sleep monitoring device - Compumedics® Somfit. Somfit is attached to patient's forehead and combines channels specified for a pulse arterial tonometry (PAT)-based home sleep apnea testing (HSAT) device with the neurological signals. Somfit sleep staging deep learning algorithm is based on convolutional neural network architecture.

Patients and Methods

One hundred and ten participants referred for sleep investigation with suspected or preexisting obstructive sleep apnea (OSA) in need of a review were enrolled into the study involving simultaneous recording of full overnight polysomnography (PSG) and Somfit data. The recordings were conducted at three centers in Australia. The reported statistics include standard measures of agreement between Somfit automatic hypnogram and consensus PSG hypnogram.

Results

Overall percent agreement across five sleep stages (N1, N2, N3, REM, and wake) between Somfit automatic and consensus PSG hypnograms was 76.14 (SE: 0.79). The percent agreements between different pairs of sleep technologists' PSG hypnograms varied from 74.36 (1.93) to 85.50 (0.64), with interscorer agreement being greater for scorers from the same sleep laboratory. The estimate of kappa between Somfit and consensus PSG was 0.672 (0.002). Percent agreement for sleep/wake discrimination was 89.30 (0.37). The accuracy of Somfit sleep staging algorithm varied with increasing OSA severity - percent agreement was 79.67 (1.87) for the normal subjects, 77.38 (1.06) for mild OSA, 74.83 (1.79) for moderate OSA and 72.93 (1.68) for severe OSA.

Conclusion

Agreement between Somfit and PSG hypnograms was non-inferior to PSG interscorer agreement for a number of scorers, thus confirming acceptability of electrode placement at the center of the forehead. The directions for algorithm improvement include additional arousal detection, integration of motion and oximetry signals and separate inference models for individual sleep stages.

Derivative Method to Detect Sleep and Awake States through Heart Rate Variability Analysis Using Machine Learning Algorithms

Sleep disorders can have harmful consequences in both the short and long term. They can lead to attention deficits, as well as cardiac, neurological and behavioral repercussions. One of the most widely used methods for assessing sleep disorders is polysomnography (PSG). A major challenge associated with this method is all the cables needed to connect the recording devices, making the examination more intrusive and usually requiring a clinical environment. This can have potential consequences on the test results and their accuracy. One simple way to assess the state of the central nervous system (CNS), a well-known indicator of sleep disorder, could be the use of a portable medical device. With this in mind, we implemented a simple model using both the RR interval (RRI) and its second derivative to accurately predict the awake and napping states of a subject using a feature classification model. For training and validation, we used a database providing measurements from nine healthy young adults (six men and three women), in which heart rate variability (HRV) associated with light-on, light-off, sleep onset and sleep offset events. Results show that using a 30 min RRI time series window suffices for this lightweight model to accurately predict whether the patient was awake or napping.

Laying the Foundation: Modern Transformers for Gold-Standard Sleep Analysis and Beyond

Accurate sleep assessment is critical to the practice of sleep medicine and sleep research. The recent availability of large quantities of publicly available sleep data, alongside recent breakthroughs in AI like transformer architectures, present novel opportunities for data-driven discovery efforts. Transformers are flexible neural networks that not only excel at classification tasks, but also can enable data-driven discovery through un- or self-supervised learning, which requires no human annotations to the input data. While transformers have been extensively used in supervised learning scenarios for sleep stage classification, they have not been fully explored or optimized in forms designed from the ground up for use in un- or self-supervised learning tasks in sleep. A necessary first step will be to study these models on a canonical benchmark supervised learning task (5-class sleep stage classification). Hence, to lay the groundwork for future data-driven discovery efforts, we evaluated optimizations of a transformer-based architecture that has already demonstrated substantial success in self-supervised learning in another domain (audio speech recognition), and trained it to perform the canonical 5-class sleep stage classification task, to establish foundational baselines in the sleep domain. We found that small transformer models designed from the start for (later) self-supervised learning can match other state-of-the-art automated sleep scoring techniques, while also providing the basis for future data-driven discovery efforts using large sleep data sets.

Self-Supervised Transformer Model Training for a Sleep-EEG Foundation Model

The American Academy of Sleep Medicine (AASM) recognizes five sleep/wake states (Wake, N1, N2, N3, REM), yet this classification schema provides only a high-level summary of sleep and likely overlooks important neurological or health information. New, data-driven approaches are needed to more deeply probe the information content of sleep signals. Here we present a self-supervised approach that learns the structure embedded in large quantities of neurophysiological sleep data. This masked transformer training procedure is inspired by high performing self-supervised methods developed for speech transcription. We show that self-supervised pre-training matches or outperforms supervised sleep stage classification, especially when labeled data or compute-power is limited. Perhaps more importantly, we also show that our pre-trained model is flexible and can be fine-tuned to perform well on new EEG recording montages not seen in training, and for new tasks including distinguishing individuals or quantifying "brain age" (a potential health biomarker). This suggests that modern methods can automatically learn information that is potentially overlooked by the 5-class sleep staging schema, laying the groundwork for new sleep scoring schemas and further data-driven exploration of sleep.

Manifold Learning-Based Common Spatial Pattern for EEG Signal Classification

EEG signal classification using Riemannian manifolds has shown great potential. However, the huge computational cost associated with Riemannian metrics poses challenges for applying Riemannian methods, particularly in high-dimensional feature data. To address these, we propose an efficient ensemble method called MLCSP-TSE-MLP, which aims to reduce the computational cost while achieving superior performance. MLCSP of the ensemble utilizes a Riemannian graph embedding strategy to learn intrinsic low-dimensional sub-manifolds, enhancing discrimination. TSE uses the Euclidean mean as the reference point for tangent space mapping and reducing computational cost. Finally, the ensemble incorporates the MLP classifier to offer improved classification performance. Classification results conducted on three datasets demonstrate that MLCSP-TSE-MLP achieves significant superior performance compared to various competing methods. Notably, the MLCSP-TSE module achieves a remarkable increase in training speed and exhibits much lower test time compared to traditional Riemannian methods. Based on these results, we believe that the proposed MLCSP-TSE-MLP is a powerful tool for handling high-dimensional data and holds great potential for practical applications.

Multicentre sleep-stage scoring agreement in the Sleep Revolution project

Determining sleep stages accurately is an important part of the diagnostic process for numerous sleep disorders. However, as the sleep stage scoring is done manually following visual scoring rules there can be considerable variation in the sleep staging between different scorers. Thus, this study aimed to comprehensively evaluate the inter-rater agreement in sleep staging. A total of 50 polysomnography recordings were manually scored by 10 independent scorers from seven different sleep centres. We used the 10 scorings to calculate a majority score by taking the sleep stage that was the most scored stage for each epoch. The overall agreement for sleep staging was κ = 0.71 and the mean agreement with the majority score was 0.86. The scorers were in perfect agreement in 48% of all scored epochs. The agreement was highest in rapid eye movement sleep (κ = 0.86) and lowest in N1 sleep (κ = 0.41). The agreement with the majority scoring varied between the scorers from 81% to 91%, with large variations between the scorers in sleep stage-specific agreements. Scorers from the same sleep centres had the highest pairwise agreements at κ = 0.79, κ = 0.85, and κ = 0.78, while the lowest pairwise agreement between the scorers was κ = 0.58. We also found a moderate negative correlation between sleep staging agreement and the apnea-hypopnea index, as well as the rate of sleep stage transitions. In conclusion, although the overall agreement was high, several areas of low agreement were also found, mainly between non-rapid eye movement stages.

Deep transfer learning for automated single-lead EEG sleep staging with channel and population mismatches

Introduction: Automated sleep staging using deep learning models typically requires training on hundreds of sleep recordings, and pre-training on public databases is therefore common practice. However, suboptimal sleep stage performance may occur from mismatches between source and target datasets, such as differences in population characteristics (e.g., an unrepresented sleep disorder) or sensors (e.g., alternative channel locations for wearable EEG). Methods: We investigated three strategies for training an automated single-channel EEG sleep stager: pre-training (i.e., training on the original source dataset), training-from-scratch (i.e., training on the new target dataset), and fine-tuning (i.e., training on the original source dataset, fine-tuning on the new target dataset). As source dataset, we used the F3-M2 channel of healthy subjects (N = 94). Performance of the different training strategies was evaluated using Cohen's Kappa (κ) in eight smaller target datasets consisting of healthy subjects (N = 60), patients with obstructive sleep apnea (OSA, N = 60), insomnia (N = 60), and REM sleep behavioral disorder (RBD, N = 22), combined with two EEG channels, F3-M2 and F3-F4. Results: No differences in performance between the training strategies was observed in the age-matched F3-M2 datasets, with an average performance across strategies of κ = .83 in healthy, κ = .77 in insomnia, and κ = .74 in OSA subjects. However, in the RBD set, where data availability was limited, fine-tuning was the preferred method (κ = .67), with an average increase in κ of .15 to pre-training and training-from-scratch. In the presence of channel mismatches, targeted training is required, either through training-from-scratch or fine-tuning, increasing performance with κ = .17 on average. Discussion: We found that, when channel and/or population mismatches cause suboptimal sleep staging performance, a fine-tuning approach can yield similar to superior performance compared to building a model from scratch, while requiring a smaller sample size. In contrast to insomnia and OSA, RBD data contains characteristics, either inherent to the pathology or age-related, which apparently demand targeted training.

Few-shot EEG sleep staging based on transductive prototype optimization network

Electroencephalography (EEG) is a commonly used technology for monitoring brain activities and diagnosing sleep disorders. Clinically, doctors need to manually stage sleep based on EEG signals, which is a time-consuming and laborious task. In this study, we propose a few-shot EEG sleep staging termed transductive prototype optimization network (TPON) method, which aims to improve the performance of EEG sleep staging. Compared with traditional deep learning methods, TPON uses a meta-learning algorithm, which generalizes the classifier to new classes that are not visible in the training set, and only have a few examples for each new class. We learn the prototypes of existing objects through meta-training, and capture the sleep features of new objects through the "learn to learn" method of meta-learning. The prototype distribution of the class is optimized and captured by using support set and unlabeled high confidence samples to increase the authenticity of the prototype. Compared with traditional prototype networks, TPON can effectively solve too few samples in few-shot learning and improve the matching degree of prototypes in prototype network. The experimental results on the public SleepEDF-2013 dataset show that the proposed algorithm outperform than most advanced algorithms in the overall performance. In addition, we experimentally demonstrate the feasibility of cross-channel recognition, which indicates that there are many similar sleep EEG features between different channels. In future research, we can further explore the common features among different channels and investigate the combination of universal features in sleep EEG. Overall, our method achieves high accuracy in sleep stage classification, demonstrating the effectiveness of this approach and its potential applications in other medical fields.

MultiChannelSleepNet: A Transformer-Based Model for Automatic Sleep Stage Classification With PSG

Automatic sleep stage classification plays an essential role in sleep quality measurement and sleep disorder diagnosis. Although many approaches have been developed, most use only single-channel electroencephalogram signals for classification. Polysomnography (PSG) provides multiple channels of signal recording, enabling the use of the appropriate method to extract and integrate the information from different channels to achieve higher sleep staging performance. We present a transformer encoder-based model, MultiChannelSleepNet, for automatic sleep stage classification with multichannel PSG data, whose architecture is implemented based on the transformer encoder for single-channel feature extraction and multichannel feature fusion. In a single-channel feature extraction block, transformer encoders extract features from time-frequency images of each channel independently. Based on our integration strategy, the feature maps extracted from each channel are fused in the multichannel feature fusion block. Another set of transformer encoders further capture joint features, and a residual connection preserves the original information from each channel in this block. Experimental results on three publicly available datasets demonstrate that our method achieves higher classification performance than state-of-the-art techniques. MultiChannelSleepNet is an efficient method to extract and integrate the information from multichannel PSG data, which facilitates precision sleep staging in clinical applications.

Current status and prospects of automatic sleep stages scoring: Review

The scoring of sleep stages is one of the essential tasks in sleep analysis. Since a manual procedure requires considerable human and financial resources, and incorporates some subjectivity, an automated approach could result in several advantages. There have been many developments in this area, and in order to provide a comprehensive overview, it is essential to review relevant recent works and summarise the characteristics of the approaches, which is the main aim of this article. To achieve it, we examined articles published between 2018 and 2022 that dealt with the automated scoring of sleep stages. In the final selection for in-depth analysis, 125 articles were included after reviewing a total of 515 publications. The results revealed that automatic scoring demonstrates good quality (with Cohen's kappa up to over 0.80 and accuracy up to over 90%) in analysing EEG/EEG + EOG + EMG signals. At the same time, it should be noted that there has been no breakthrough in the quality of results using these signals in recent years. Systems involving other signals that could potentially be acquired more conveniently for the user (e.g. respiratory, cardiac or movement signals) remain more challenging in the implementation with a high level of reliability but have considerable innovation capability. In general, automatic sleep stage scoring has excellent potential to assist medical professionals while providing an objective assessment.

Age-integrated artificial intelligence framework for sleep stage classification and obstructive sleep apnea screening

Introduction

Sleep is an essential function to sustain a healthy life, and sleep dysfunction can cause various physical and mental issues. In particular, obstructive sleep apnea (OSA) is one of the most common sleep disorders and, if not treated in a timely manner, OSA can lead to critical problems such as hypertension or heart disease.

Methods

The first crucial step in evaluating individuals' quality of sleep and diagnosing sleep disorders is to classify sleep stages using polysomnographic (PSG) data including electroencephalography (EEG). To date, such sleep stage scoring has been mainly performed manually via visual inspection by experts, which is not only a time-consuming and laborious process but also may yield subjective results. Therefore, we have developed a computational framework that enables automatic sleep stage classification utilizing the power spectral density (PSD) features of sleep EEG based on three different learning algorithms: support vector machine, k-nearest neighbors, and multilayer perceptron (MLP). In particular, we propose an integrated artificial intelligence (AI) framework to further inform the risk of OSA based on the characteristics in automatically scored sleep stages. Given the previous finding that the characteristics of sleep EEG differ by age group, we employed a strategy of training age-specific models (younger and older groups) and a general model and comparing their performance.

Results

The performance of the younger age-specific group model was similar to that of the general model (and even higher than the general model at certain stages), but the performance of the older age-specific group model was rather low, suggesting that bias in individual variables, such as age bias, should be considered during model training. Our integrated model yielded an accuracy of 73% in sleep stage classification and 73% in OSA screening when MLP algorithm was applied, which indicates that patients with OSA could be screened with the corresponding accuracy level only with sleep EEG without respiration-related measures.

Discussion

The current outcomes demonstrate the feasibility of AI-based computational studies that when combined with advances in wearable devices and relevant technologies could contribute to personalized medicine by not only assessing an individuals' sleep status conveniently at home but also by alerting them to the risk of sleep disorders and enabling early intervention.

A Novel Measure of Cardiopulmonary Coupling During Sleep Based on the Synchrosqueezing Transform Algorithm

OBJECTIVE

This paper presents a novel method to quantify cardiopulmonary dynamics for automatic sleep apnea detection by integrating the synchrosqueezing transform (SST) algorithm with the standard cardiopulmonary coupling (CPC) method.

METHODS

Simulated data were designed to validate the reliability of the proposed method, with varying levels of signal bandwidth and noise contamination. Real data were collected from the Physionet sleep apnea database, consisting of 70 single-lead ECGs with expert-labeled apnea annotations on a minute-by-minute basis. Three different signal processing techniques applied to sinus interbeat interval and respiratory time series include short-time Fourier transform, continuous Wavelet transform, and synchrosqueezing transform, respectively. Subsequently, the CPC index was computed to construct sleep spectrograms. Features derived from such spectrogram were used as input to five machine- learning-based classifiers including decision trees, support vector machines, k-nearest neighbors, etc. Results: The simulation results showed that the SST-CPC method is robust to both noise level and signal bandwidth, outperforming Fourier-based and Wavelet-based approaches. Meanwhile, the SST-CPC spectrogram exhibited relatively explicit temporal-frequency biomarkers compared with the rest. Furthermore, by integrating SST-CPC features with common-used heart rate and respiratory features, accuracies for per-minute apnea detection improved from 72% to 83%, validating the added value of CPC biomarkers in sleep apnea detection.

CONCLUSION

The SST-CPC method improves the accuracy of automatic sleep apnea detection and presents comparable performances with those automated algorithms reported in the literature.

SIGNIFICANCE

The proposed SST-CPC method enhances sleep diagnostic capabilities, and may serve as a complementary tool to the routine diagnosis of sleep respiratory events.

Generalizable Deep Learning-Based Sleep Staging Approach for Ambulatory Textile Electrode Headband Recordings

Reliable, automated, and user-friendly solutions for the identification of sleep stages in home environment are needed in various clinical and scientific research settings. Previously we have shown that signals recorded with an easily applicable textile electrode headband (FocusBand Technologies, T 2 Green Pty Ltd) contain characteristics similar to the standard electrooculography (EOG, E1-M2). We hypothesize that the electroencephalographic (EEG) signals recorded using the textile electrode headband are similar enough with standard EOG in order to develop an automatic neural network-based sleep staging method that generalizes from diagnostic polysomnographic (PSG) data to ambulatory sleep recordings of textile electrode-based forehead EEG. Standard EOG signals together with manually annotated sleep stages from clinical PSG dataset (n = 876) were used to train, validate, and test a fully convolutional neural network (CNN). Furthermore, ambulatory sleep recordings including a standard set of gel-based electrodes and the textile electrode headband were conducted for 10 healthy volunteers at their homes to test the generalizability of the model. In the test set (n = 88) of the clinical dataset, the model's accuracy for 5-stage sleep stage classification was 80% (κ = 0.73) using only the single-channel EOG. The model generalized well for the headband-data, reaching 82% (κ = 0.75) overall sleep staging accuracy. In comparison, accuracy of the model was 87% (κ = 0.82) in home recordings using the standard EOG. In conclusion, the CNN model shows potential on automatic sleep staging of healthy individuals using a reusable electrode headband in a home environment.

A New Post-Processing Method Using Latent Structure Influence Models for Channel Fusion in Automatic Sleep Staging

Sleep stage dynamics can be adequately represented using Markov chain models to improve classification accuracy. The present study proposes a new post-processing method based on channel fusion using Latent Structure Influence Models (LSIMs). The proposed method develops and examines two channel-fusion algorithms: the standard LSIM fusion and the integrated LSIM fusion, in which the latter is more efficient and performs better. The proposed LSIM-based method simultaneously incorporates the nonlinear interactions between channels and the sleep stage dynamics. In the first step, existing sleep staging systems process every data channel independently and produce stage score sequences for each channel. These single-channel scores are then projected into belief space using the marginal one-slice parameter of all channels by LSIM fusion algorithms. The logarithms of marginal one-slice parameters are concatenated to obtain log-scale belief state space (LBSS) features in the standard LSIM fusion. In the integrated LSIM fusion, integrated LBSS (ILBSS) features are formed by combining the LBSS features of several LSIMs. By utilizing four recently developed sleep staging systems, the proposed method is applied to the publicly available SleepEDF-20 database that contains five AASM sleep stages (N1, N2, N3, REM, and W). Compared to single-channel (Fpz-Cz, Pz-Oz, and EOG) results, integrated LSIM fusion results have a statistically significant improvement of 1.5% in 2-channel fusion (Fpz-Cz and Pz-Oz) and 2.5% in 3-channel fusion (Fpz-Cz, Pz-Oz, and EOG). With an overall accuracy of 87.3% for 3-channel post-processing, the integrated LSIM fusion system offers one of the highest overall accuracy rates among existing studies.

A novel deep domain adaptation method for automated detection of sleep apnea/hypopnea events

Objective.Sleep apnea-hypopnea syndrome (SAHS) is a common sleep-related respiratory disorder that is generally assessed for severity using polysomnography (PSG); however, the diversity of sampling devices and patients makes this not only costly but may also degrade the performance of the algorithms.Approach.This paper proposes a novel deep domain adaptation module which uses a long short-term memory-convolutional neural network embedded with the channel attention mechanism to achieve autonomous extraction of high-quality features. Meanwhile, a domain adaptation module was built to achieve domain-invariant feature extraction for reducing the differences in data distribution caused by different devices and other factors. In addition, during the training process, the algorithm used the last second label as the label of the PSG segment, so that second-by-second evaluation of respiratory events could be achieved.Main results.The algorithm applied the two datasets provided by PhysioNet as the source and target domains. The accuracy, sensitivity and specificity of the algorithm on the source domain were 86.46%, 86.11% and 93.17%, respectively, and on the target domain were 83.63%, 82.52%, 91.62%, respectively. The proposed algorithm showed strong generalization ability and the classification results were comparable to the current advanced methods. Besides, the apnea-hypopnea index values estimated by the proposed algorithm showed a high correlation with the manual scoring values on both domains.Significance.The proposed algorithm can effectively perform SAHS detection and evaluation with certain generalization.

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.

Multi-Level Classification of Driver Drowsiness by Simultaneous Analysis of ECG and Respiration Signals Using Deep Neural Networks

The high number of fatal crashes caused by driver drowsiness highlights the need for developing reliable drowsiness detection methods. An ideal driver drowsiness detection system should estimate multiple levels of drowsiness accurately without intervening in the driving task. This paper proposes a multi-level drowsiness detection system by a deep neural network-based classification system using a combination of electrocardiogram and respiration signals. The proposed method is based on a combination of convolutional neural networks (CNNs) and long short-term memory (LSTM) networks for classifying drowsiness by concurrently using heart rate variability (HRV), power spectral density of HRV, and respiration rate signal as inputs. Two models, a CNN-based model and a hybrid CNN-LSTM-based model were used for multi-level classifications. The performance of the proposed method was evaluated on experimental data collected from 30 subjects in a simulated driving environment. The performance and the results of both models are presented and compared. The best performance for both three-level and five-level drowsiness classifications was achieved by the CNN-LSTM model. The results indicate that the three-level and five-level classifications of drowsiness can be achieved with 91 and 67% accuracy, respectively.

The Sleep Revolution project: the concept and objectives

Obstructive sleep apnea is linked to severe health consequences such as hypertension, daytime sleepiness, and cardiovascular disease. Nearly a billion people are estimated to have obstructive sleep apnea with a substantial economic burden. However, the current diagnostic parameter of obstructive sleep apnea, the apnea-hypopnea index, correlates poorly with related comorbidities and symptoms. Obstructive sleep apnea severity is measured by counting respiratory events, while other physiologically relevant consequences are ignored. Furthermore, as the clinical methods for analysing polysomnographic signals are outdated, laborious, and expensive, most patients with obstructive sleep apnea remain undiagnosed. Therefore, more personalised diagnostic approaches are urgently needed. The Sleep Revolution, funded by the European Union's Horizon 2020 Research and Innovation Programme, aims to tackle these shortcomings by developing machine learning tools to better estimate obstructive sleep apnea severity and phenotypes. This allows for improved personalised treatment options, including increased patient participation. Also, implementing these tools will alleviate the costs and increase the availability of sleep studies by decreasing manual scoring labour. Finally, the project aims to design a digital platform that functions as a bridge between researchers, patients, and clinicians, with an electronic sleep diary, objective cognitive tests, and questionnaires in a mobile application. These ambitious goals will be achieved through extensive collaboration between 39 centres, including expertise from sleep medicine, computer science, and industry and by utilising tens of thousands of retrospectively and prospectively collected sleep recordings. With the commitment of the European Sleep Research Society and Assembly of National Sleep Societies, the Sleep Revolution has the unique possibility to create new standardised guidelines for sleep medicine.

Automatic sleep staging of EEG signals: recent development, challenges, and future directions

Modern deep learning holds a great potential to transform clinical practice on human sleep. Teaching a machine to carry out routine tasks would be a tremendous reduction in workload for clinicians. Sleep staging, a fundamental step in sleep practice, is a suitable task for this and will be the focus in this article. Recently, automatic sleep staging systems have been trained to mimic manual scoring, leading to similar performance to human sleep experts, at least on scoring of healthy subjects. Despite tremendous progress, we have not seen automatic sleep scoring adopted widely in clinical environments. This review aims to give a shared view of the authors on the most recent state-of-the-art development in automatic sleep staging, the challenges that still need to be addressed, and the future directions for automatic sleep scoring to achieve clinical value.

CMS2-net: Semi-supervised Sleep Staging for Diverse Obstructive Sleep Apnea Severity

Although the development of computer-aided algorithms for sleep staging is integrated into automatic detection of sleep disorders, most supervised deep learning based models might suffer from insufficient labeled data. While the adoption of semi-supervised learning (SSL) can mitigate the issue, the SSL models are still limited to the lack of discriminative feature extraction for diverse obstructive sleep apnea (OSA) severity. This model deterioration might be exacerbated during the domain adaptation. Such exploration on the alleviation of domain-shift of SSL model between different OSA conditions has attracted more and more attentions from the clinic. In this work, a co-attention meta sleep staging network (CMS2-net) is proposed to simultaneously deal with two issues: the inter-class disparity problem and the intra-class selection problem. Within CMS2-net, a co-attention module and a triple-classifier are designed to explicitly refine the coarse feature representations by identifying the class boundary inconsistency. Moreover, the mutual information with meta contrastive variance is introduced to supervise the gradient stream from a multiscale view. The performance of the proposed framework is demonstrated on both public and local datasets. Furthermore, our approach achieves the state-of-the-art SSL results on both datasets.

Apnea Detection in Polysomnographic Recordings Using Machine Learning Techniques

Sleep disorders are diagnosed in sleep laboratories by polysomnography, a multi-parameter examination that monitors biological signals during sleep. The subsequent evaluation of the obtained records is very time-consuming. The goal of this study was to create an automatic system for evaluation of the airflow and SpO2 channels of polysomnography records, through the use of machine learning techniques and a large database, for apnea and desaturation detection (which is unusual in other studies). To that end, a convolutional neural network (CNN) was designed using hyperparameter optimization. It was then trained and tested for apnea and desaturation. The proposed CNN was compared with the commonly used k-nearest neighbors (k-NN) method. The classifiers were designed based on nasal airflow and blood oxygen saturation signals. The final neural network accuracy for apnea detection reached 84%, and that for desaturation detection was 74%, while the k-NN classifier reached accuracies of 83% and 64% for apnea detection and desaturation detection, respectively.

Self-Applied Home Sleep Recordings: The Future of Sleep Medicine

Sleep disorders form a massive global health burden and there is an increasing need for simple and cost-efficient sleep recording devices. Recent machine learning-based approaches have already achieved scoring accuracy of sleep recordings on par with manual scoring, even with reduced recording montages. Simple and inexpensive monitoring over multiple consecutive nights with automatic analysis could be the answer to overcome the substantial economic burden caused by poor sleep and enable more efficient initial diagnosis, treatment planning, and follow-up monitoring for individuals suffering from sleep disorders.

Detection of spontaneous seizures in EEGs in multiple experimental mouse models of epilepsy

Objective.Electroencephalography (EEG) is a key tool for non-invasive recording of brain activity and the diagnosis of epilepsy. EEG monitoring is also widely employed in rodent models to track epilepsy development and evaluate experimental therapies and interventions. Whereas automated seizure detection algorithms have been developed for clinical EEG, preclinical versions face challenges of inter-model differences and lack of EEG standardization, leaving researchers relying on time-consuming visual annotation of signals.Approach.In this study, a machine learning-based seizure detection approach, 'Epi-AI', which can semi-automate EEG analysis in multiple mouse models of epilepsy was developed. Twenty-six mice with a total EEG recording duration of 6451 h were used to develop and test the Epi-AI approach. EEG recordings were obtained from two mouse models of kainic acid-induced epilepsy (Models I and III), a genetic model of Dravet syndrome (Model II) and a pilocarpine mouse model of epilepsy (Model IV). The Epi-AI algorithm was compared against two threshold-based approaches for seizure detection, a local Teager-Kaiser energy operator (TKEO) approach and a global Teager-Kaiser energy operator-discrete wavelet transform (TKEO-DWT) combination approach.Main results.Epi-AI demonstrated a superior sensitivity, 91.4%-98.8%, and specificity, 93.1%-98.8%, in Models I-III, to both of the threshold-based approaches which performed well on individual mouse models but did not generalise well across models. The performance of the TKEO approach in Models I-III ranged from 66.9%-91.3% sensitivity and 60.8%-97.5% specificity to detect spontaneous seizures when compared with expert annotations. The sensitivity and specificity of the TKEO-DWT approach were marginally better than the TKEO approach in Models I-III at 73.2%-80.1% and 75.8%-98.1%, respectively. When tested on EEG from Model IV which was not used in developing the Epi-AI approach, Epi-AI was able to identify seizures with 76.3% sensitivity and 98.1% specificity.Significance.Epi-AI has the potential to provide fast, objective and reproducible semi-automated analysis of multiple types of seizure in long-duration EEG recordings in rodents.

A Combinatorial Deep Learning Structure for Precise Depth of Anesthesia Estimation From EEG Signals

Electroencephalography (EEG) is commonly used to measure the depth of anesthesia (DOA) because EEG reflects surgical pain and state of the brain. However, precise and real-time estimation of DOA index for painful surgical operations is challenging due to problems such as postoperative complications and accidental awareness. To tackle these problems, we propose a new combinatorial deep learning structure involving convolutional neural networks (inspired by the inception module), bidirectional long short-term memory, and an attention layer. The proposed model uses the EEG signal to continuously predicts the bispectral index (BIS). It is trained over a large dataset, mostly from those under general anesthesia with few cases receiving sedation/analgesia and spinal anesthesia. Despite the imbalance distribution of BIS values in different levels of anesthesia, our proposed structure achieves convincing root mean square error of 5.59 ± 1.04 and mean absolute error of 4.3 ± 0.87, as well as improvement in area under the curve of 15% on average, which surpasses state-of-the-art DOA estimation methods. The DOA values are also discretized into four levels of anesthesia and the results demonstrate strong inter-subject classification accuracy of 88.7% that outperforms the conventional methods.

Transferring Structured Knowledge in Unsupervised Domain Adaptation of a Sleep Staging Network

Automatic sleep staging based on deep learning (DL) has been attracting attention for analyzing sleep quality and determining treatment effects. It is challenging to acquire long-term sleep data from numerous subjects and manually labeling them even though most DL-based models are trained using large-scale sleep data to provide state-of-the-art performance. One way to overcome this data shortage is to create a pre-trained network with an existing large-scale dataset (source domain) that is applicable to small cohorts of datasets (target domain); however, discrepancies in data distribution between the domains prevent successful refinement of this approach. In this paper, we propose an unsupervised domain adaptation method for sleep staging networks to reduce discrepancies by realigning the domains in the same space and producing domain-invariant features. Specifically, in addition to a classical domain discriminator, we introduce local dis-criminators-subject and stage-to maintain the intrinsic structure of sleep data to decrease local misalignments while using adversarial learning to play a minimax game between the feature extractor and discriminators. Moreover, we present several optimization schemes during training because the conventional adversarial learning is not effective to our training scheme. We evaluate the performance of the proposed method by examining the staging performances of a baseline network compared with direct transfer (DT) learning in various conditions. The experimental results demonstrate that the proposed domain adaptation significantly improves the performance though it needs no labeled sleep data in target domain.

Automatic Respiratory Event Scoring in Obstructive Sleep Apnea Using a Long Short-Term Memory Neural Network

The diagnosis of obstructive sleep apnea is based on daytime symptoms and the frequency of respiratory events during the night. The respiratory events are scored manually from polysomnographic recordings, which is time-consuming and expensive. Therefore, automatic scoring methods could considerably improve the efficiency of sleep apnea diagnostics and release the resources currently needed for manual scoring to other areas of sleep medicine. In this study, we trained a long short-term memory neural network for automatic scoring of respiratory events using input signals from peripheral blood oxygen saturation, thermistor-airflow, nasal pressure -airflow, and thorax respiratory effort. The signals were extracted from 887 in-lab polysomnography recordings. 787 patients with suspected sleep apnea were used to train the neural network and 100 patients were used as an independent test set. The epoch-wise agreement between manual and automatic neural network scoring was high (88.9%, κ = 0.728). In addition, the apnea-hypopnea index (AHI) calculated from the automated scoring was close to the manually determined AHI with a mean absolute error of 3.0 events/hour and an intraclass correlation coefficient of 0.985. The neural network approach for automatic scoring of respiratory events achieved high accuracy and good agreement with manual scoring. The presented neural network could be used for analysis of large research datasets that are unfeasible to score manually, and has potential for clinical use in the future In addition, since the neural network scores individual respiratory events, the automatic scoring can be easily reviewed manually if desired.

Detailed Assessment of Sleep Architecture With Deep Learning and Shorter Epoch-to-Epoch Duration Reveals Sleep Fragmentation of Patients With Obstructive Sleep Apnea

Traditional sleep staging with non-overlapping 30-second epochs overlooks multiple sleep-wake transitions. We aimed to overcome this by analyzing the sleep architecture in more detail with deep learning methods and hypothesized that the traditional sleep staging underestimates the sleep fragmentation of obstructive sleep apnea (OSA) patients. To test this hypothesis, we applied deep learning-based sleep staging to identify sleep stages with the traditional approach and by using overlapping 30-second epochs with 15-, 5-, 1-, or 0.5-second epoch-to-epoch duration. A dataset of 446 patients referred for polysomnography due to OSA suspicion was used to assess differences in the sleep architecture between OSA severity groups. The amount of wakefulness increased while REM and N3 decreased in severe OSA with shorter epoch-to-epoch duration. In other OSA severity groups, the amount of wake and N1 decreased while N3 increased. With the traditional 30-second epoch-to-epoch duration, only small differences in sleep continuity were observed between the OSA severity groups. With 1-second epoch-to-epoch duration, the hazard ratio illustrating the risk of fragmented sleep was 1.14 (p = 0.39) for mild OSA, 1.59 (p < 0.01) for moderate OSA, and 4.13 (p < 0.01) for severe OSA. With shorter epoch-to-epoch durations, total sleep time and sleep efficiency increased in the non-OSA group and decreased in severe OSA. In conclusion, more detailed sleep analysis emphasizes the highly fragmented sleep architecture in severe OSA patients which can be underestimated with traditional sleep staging. The results highlight the need for a more detailed analysis of sleep architecture when assessing sleep disorders.

Automatic Sleep Stage Classification Using Temporal Convolutional Neural Network and New Data Augmentation Technique from Raw Single-Channel EEG

BACKGROUND AND OBJECTIVE

This paper presents a new framework for automatic classification of sleep stages using a deep learning algorithm from single-channel EEG signals. Each segmented EEG signal appended with its label of stages is fed into a deep learning model to create an automatic sleep stage classification. This is one of the most important problems that is critical to the realization of monitoring patients with sleep disorder.

METHODS

In the present study, a neural network architecture is introduced utilizing Convolutional Neural Networks (CNNs) to extract features, followed by Temporal Convolutional Neural Network to extract the temporal features from the extracted features vector of CNN. Finally, the performance of our model is improved by a Conditional Random Field layer. We also employed a new data augmentation technique to enhance the CNNs training which has auxiliary effects.

RESULTS

We evaluated our model by two different single-channel EEG signals (i.e., Fpz-Cz and Pz-Oz EEG channels) from two public sleep datasets, named Sleep-EDF-2013 and Sleep-EDF-2018. The evaluation results on both datasets showed that our model obtains the best total accuracy and kappa score (EDF-2013: 85.39%- 0.80, EDF-2018: 82.46%- 0.76) compared to the state-of-the-art methods.

CONCLUSIONS

This study will possibly allow us to have a wearable sleep monitoring system with a single-channel EEG. Also, unlike hand-crafted features methods, our model finds its own patterns through training epochs, and therefore, it may minimize engineering bias.

Deep learning enables sleep staging from photoplethysmogram for patients with suspected sleep apnea

Study Objectives

Accurate identification of sleep stages is essential in the diagnosis of sleep disorders (e.g. obstructive sleep apnea [OSA]) but relies on labor-intensive electroencephalogram (EEG)-based manual scoring. Furthermore, long-term assessment of sleep relies on actigraphy differentiating only between wake and sleep periods without identifying specific sleep stages and having low reliability in identifying wake periods after sleep onset. To address these issues, we aimed to develop an automatic method for identifying the sleep stages from the photoplethysmogram (PPG) signal obtained with a simple finger pulse oximeter.

Methods

PPG signals from the diagnostic polysomnographies of susptected OSA patients (n = 894) were utilized to develop a combined convolutional and recurrent neural network. The deep learning model was trained individually for three-stage (wake/NREM/REM), four-stage (wake/N1+N2/N3/REM), and five-stage (wake/N1/N2/N3/REM) classification of sleep.

Results

The three-stage model achieved an epoch-by-epoch accuracy of 80.1% with Cohen’s κ of 0.65. The four- and five-stage models achieved 68.5% (κ = 0.54), and 64.1% (κ = 0.51) accuracies, respectively. With the five-stage model, the total sleep time was underestimated with a mean bias error (SD) of of 7.5 (55.2) minutes.

Conclusion

The PPG-based deep learning model enabled accurate estimation of sleep time and differentiation between sleep stages with a moderate agreement to manual EEG-based scoring. As PPG is already included in ambulatory polygraphic recordings, applying the PPG-based sleep staging could improve their diagnostic value by enabling simple, low-cost, and reliable monitoring of sleep and help assess otherwise overlooked conditions such as REM-related OSA.

Automatic Sleep Stage Classification of Children with Sleep-Disordered Breathing Using the Modularized Network

PURPOSE

To develop an automatic sleep stage analysis model for children and evaluate the effect of the model on the diagnosis of sleep-disordered breathing (SDB).

PATIENTS AND METHODS

Three hundred and forty-four SDB patients aged between 2 to 18 years who completed polysomnography (PSG) to assess the severity of the disease were enrolled in this study. We developed deep neural networks to stage sleep from electroencephalography (EEG), electrooculography (EOG) and electromyogram (EMG). The model performance was estimated by accuracy, precision, recall, F1-score, and Cohen's Kappa coefficient (ĸ). And we compared the difference in calculation of sleep parameters among the technicians, the model ensemble, and the single-channel EEG model.

RESULTS

The numbers of raw data divided into training, validation, and testing were 240, 36, and 68, respectively. The best performance appeared in the model ensemble of which the accuracy was 83.36% (ĸ=0.7817) in 5-stages, and the accuracy was 96.76% (ĸ=0.8236) in 2-stages. The single-channel EEG model showed the classification satisfyingly as well. There was no significant difference in TST, SE, SOL, time in W, time in N1+N2, time in N3, and OAHI between technician and the model (P>0.05). On the datasets from sleep-EDF-13 and sleep-EDF-18, the average classification accuracies achieved were 92.76% and 91.94% in 5-stages by using the proposed method, respectively.

CONCLUSION

This research established the model for pediatric automatic sleep stage classification with satisfying reliability and generalizability. In addition, it could be applied for calculating quantitative sleep parameters and evaluating the severity of SDB.

Confidence-Based Framework Using Deep Learning for Automated Sleep Stage Scoring

STUDY OBJECTIVES

Automated sleep stage scoring is not yet vigorously used in practice because of the black-box nature and the risk of wrong predictions. The objective of this study was to introduce a confidence-based framework to detect the possibly wrong predictions that would inform clinicians about which epochs would require a manual review and investigate the potential to improve accuracy for automated sleep stage scoring.

METHODS

We used 702 polysomnography studies from a local clinical dataset (SNUBH dataset) and 2804 from an open dataset (SHHS dataset) for experiments. We adapted the state-of-the-art TinySleepNet architecture to train the classifier and modified the ConfidNet architecture to train an auxiliary confidence model. For the confidence model, we developed a novel method, Dropout Correct Rate (DCR), and the performance of it was compared with other existing methods.

RESULTS

Confidence estimates (0.754) reflected accuracy (0.758) well in general. The best performance for differentiating correct and wrong predictions was shown when using the DCR method (AUROC: 0.812) compared to the existing approaches which largely failed to detect wrong predictions. By reviewing only 20% of epochs that received the lowest confidence values, the overall accuracy of sleep stage scoring was improved from 76% to 87%. For patients with reduced accuracy (ie, individuals with obesity or severe sleep apnea), the possible improvement range after applying confidence estimation was even greater.

CONCLUSION

To the best of our knowledge, this is the first study applying confidence estimation on automated sleep stage scoring. Reliable confidence estimates by the DCR method help screen out most of the wrong predictions, which would increase the reliability and interpretability of automated sleep stage scoring.

Electro-Encephalography and Electro-Oculography in Aeronautics: A Review Over the Last Decade (2010-2020)

Electro-encephalography (EEG) and electro-oculography (EOG) are methods of electrophysiological monitoring that have potentially fruitful applications in neuroscience, clinical exploration, the aeronautical industry, and other sectors. These methods are often the most straightforward way of evaluating brain oscillations and eye movements, as they use standard laboratory or mobile techniques. This review describes the potential of EEG and EOG systems and the application of these methods in aeronautics. For example, EEG and EOG signals can be used to design brain-computer interfaces (BCI) and to interpret brain activity, such as monitoring the mental state of a pilot in determining their workload. The main objectives of this review are to, (i) offer an in-depth review of literature on the basics of EEG and EOG and their application in aeronautics; (ii) to explore the methodology and trends of research in combined EEG-EOG studies over the last decade; and (iii) to provide methodological guidelines for beginners and experts when applying these methods in environments outside the laboratory, with a particular focus on human factors and aeronautics. The study used databases from scientific, clinical, and neural engineering fields. The review first introduces the characteristics and the application of both EEG and EOG in aeronautics, undertaking a large review of relevant literature, from early to more recent studies. We then built a novel taxonomy model that includes 150 combined EEG-EOG papers published in peer-reviewed scientific journals and conferences from January 2010 to March 2020. Several data elements were reviewed for each study (e.g., pre-processing, extracted features and performance metrics), which were then examined to uncover trends in aeronautics and summarize interesting methods from this important body of literature. Finally, the review considers the advantages and limitations of these methods as well as future challenges.

An Automatic Sleep Stage Classification Algorithm Using Improved Model Based Essence Features

The automatic sleep stage classification technique can facilitate the diagnosis of sleep disorders and release the medical expert from labor-consumption work. In this paper, novel improved model based essence features (IMBEFs) were proposed combining locality energy (LE) and dual state space models (DSSMs) for automatic sleep stage detection on single-channel electroencephalograph (EEG) signals. Firstly, each EEG epoch is decomposed into low-level sub-bands (LSBs) and high-level sub-bands (HSBs) by wavelet packet decomposition (WPD), separately. Then, the DSSMs are estimated by the LSBs and the LE calculation is carried out on HSBs. Thirdly, the IMBEFs extracted from the DSSM and LE are fed into the appropriate classifier for sleep stage classification. The performance of the proposed method was evaluated on three public sleep databases. The experimental results show that under the Rechtschaffen's and Kale's (R&K) standard, the sleep stage classification accuracies of six classes on the Sleep EDF database and the Dreams Subjects database are 92.04% and 78.92%, respectively. Under the American Academy of Sleep Medicine (AASM) standard, the classification accuracies of five classes in the Dreams Subjects database and the ISRUC database reached 79.90% and 81.65%. The proposed method can be used for reliable sleep stage classification with high accuracy compared with state-of-the-art methods.