Neural network analysis of sleep stages enables efficient diagnosis of narcolepsy

The National Sleep Research Resource: making data findable, accessible, interoperable, reusable and promoting sleep science

This paper presents a comprehensive overview of the National Sleep Research Resource (NSRR), a National Heart Lung and Blood Institute-supported repository developed to share data from clinical studies focused on the evaluation of sleep disorders. The NSRR addresses challenges presented by the heterogeneity of sleep-related data, leveraging innovative strategies to optimize the quality and accessibility of available datasets. It provides authorized users with secure centralized access to a large quantity of sleep-related data including polysomnography, actigraphy, demographics, patient-reported outcomes, and other data. In developing the NSRR, we have implemented data processing protocols that ensure de-identification and compliance with FAIR (Findable, Accessible, Interoperable, Reusable) principles. Heterogeneity stemming from intrinsic variation in the collection, annotation, definition, and interpretation of data has proven to be one of the primary obstacles to efficient sharing of datasets. Approaches employed by the NSRR to address this heterogeneity include (1) development of standardized sleep terminologies utilizing a compositional coding scheme, (2) specification of comprehensive metadata, (3) harmonization of commonly used variables, and (3) computational tools developed to standardize signal processing. We have also leveraged external resources to engineer a domain-specific approach to data harmonization. We describe the scope of data within the NSRR, its role in promoting sleep and circadian research through data sharing, and harmonization of large datasets and analytical tools. Finally, we identify opportunities for approaches for the field of sleep medicine to further support data standardization and sharing.

Narcolepsy and rapid eye movement sleep

Since the first description of narcolepsy at the end of the 19th Century, great progress has been made. The disease is nowadays distinguished as narcolepsy type 1 and type 2. In the 1960s, the discovery of rapid eye movement sleep at sleep onset led to improved understanding of core sleep-related disease symptoms of the disease (excessive daytime sleepiness with early occurrence of rapid eye movement sleep, sleep-related hallucinations, sleep paralysis, rapid eye movement parasomnia), as possible dysregulation of rapid eye movement sleep, and cataplexy resembling an intrusion of rapid eye movement atonia during wake. The relevance of non-sleep-related symptoms, such as obesity, precocious puberty, psychiatric and cardiovascular morbidities, has subsequently been recognized. The diagnostic tools have been improved, but sleep-onset rapid eye movement periods on polysomnography and Multiple Sleep Latency Test remain key criteria. The pathogenic mechanisms of narcolepsy type 1 have been partly elucidated after the discovery of strong HLA class II association and orexin/hypocretin deficiency, a neurotransmitter that is involved in altered rapid eye movement sleep regulation. Conversely, the causes of narcolepsy type 2, where cataplexy and orexin deficiency are absent, remain unknown. Symptomatic medications to treat patients with narcolepsy have been developed, and management has been codified with guidelines, until the recent promising orexin-receptor agonists. The present review retraces the steps of the research on narcolepsy that linked the features of the disease with rapid eye movement sleep abnormality, and those that do not appear associated with rapid eye movement sleep.

Brain Age Estimation from Overnight Sleep Electroencephalography with Multi-Flow Sequence Learning

Purpose

This study aims to improve brain age estimation by developing a novel deep learning model utilizing overnight electroencephalography (EEG) data.

Methods

We address limitations in current brain age prediction methods by proposing a model trained and evaluated on multiple cohort data, covering a broad age range. The model employs a one-dimensional Swin Transformer to efficiently extract complex patterns from sleep EEG signals and a convolutional neural network with attentional mechanisms to summarize sleep structural features. A multi-flow learning-based framework attentively merges these two features, employing sleep structural information to direct and augment the EEG features. A post-prediction model is designed to integrate the age-related features throughout the night. Furthermore, we propose a DecadeCE loss function to address the problem of an uneven age distribution.

Results

We utilized 18,767 polysomnograms (PSGs) from 13,616 subjects to develop and evaluate the proposed model. The model achieves a mean absolute error (MAE) of 4.19 and a correlation of 0.97 on the mixed-cohort test set, and an MAE of 6.18 years and a correlation of 0.78 on an independent test set. Our brain age estimation work reduced the error by more than 1 year compared to other studies that also used EEG, achieving the level of neuroimaging. The estimated brain age index demonstrated longitudinal sensitivity and exhibited a significant increase of 1.27 years in individuals with psychiatric or neurological disorders relative to healthy individuals.

Conclusion

The multi-flow deep learning model proposed in this study, based on overnight EEG, represents a more accurate approach for estimating brain age. The utilization of overnight sleep EEG for the prediction of brain age is both cost-effective and adept at capturing dynamic changes. These findings demonstrate the potential of EEG in predicting brain age, presenting a noninvasive and accessible method for assessing brain aging.

Strengths, weaknesses, opportunities, and threats of using AI-enabled technology in sleep medicine: a commentary

Over the past few years, artificial intelligence (AI) has emerged as a powerful tool used to efficiently automate several tasks across multiple domains. Sleep medicine is perfectly positioned to leverage this tool due to the wealth of physiological signals obtained through sleep studies or sleep tracking devices and abundance of accessible clinical data through electronic medical records. However, caution must be applied when utilizing AI, due to intrinsic challenges associated with novel technology. The Artificial Intelligence in Sleep Medicine Committee of the American Academy of Sleep Medicine reviews advancements in AI within the sleep medicine field. In this article, the Artificial Intelligence in Sleep Medicine committee members provide a commentary on the scope of AI technology in sleep medicine. The commentary identifies 3 pivotal areas in sleep medicine that can benefit from AI technologies: clinical care, lifestyle management, and population health management. This article provides a detailed analysis of the strengths, weaknesses, opportunities, and threats associated with using AI-enabled technologies in each pivotal area. Finally, the article broadly reviews barriers and challenges associated with using AI-enabled technologies and offers possible solutions.

CITATION

Bandyopadhyay A, Oks M, Sun H, et al. Strengths, weaknesses, opportunities, and threats of using AI-enabled technology in sleep medicine: a commentary. J Clin Sleep Med. 2024;20(7):1183-1191.

"Counting sheep PSG": EEGLAB-compatible open-source matlab software for signal processing, visualization, event marking and staging of polysomnographic data

BACKGROUND

Progress in advancing sleep research employing polysomnography (PSG) has been negatively impacted by the limited availability of widely available, open-source sleep-specific analysis tools.

NEW METHOD

Here, we introduce Counting Sheep PSG, an EEGLAB-compatible software for signal processing, visualization, event marking and manual sleep stage scoring of PSG data for MATLAB.

RESULTS

Key features include: (1) signal processing tools including bad channel interpolation, down-sampling, re-referencing, filtering, independent component analysis, artifact subspace reconstruction, and power spectral analysis, (2) customizable display of polysomnographic data and hypnogram, (3) event marking mode including manual sleep stage scoring, (4) automatic event detections including movement artifact, sleep spindles, slow waves and eye movements, and (5) export of main descriptive sleep architecture statistics, event statistics and publication-ready hypnogram.

COMPARISON WITH EXISTING METHODS

Counting Sheep PSG was built on the foundation created by sleepSMG (https://sleepsmg.sourceforge.net/). The scope and functionalities of the current software have made significant advancements in terms of EEGLAB integration/compatibility, preprocessing, artifact correction, event detection, functionality and ease of use. By comparison, commercial software can be costly and utilize proprietary data formats and algorithms, thereby restricting the ability to distribute and share data and analysis results.

CONCLUSIONS

The field of sleep research remains shackled by an industry that resists standardization, prevents interoperability, builds-in planned obsolescence, maintains proprietary black-box data formats and analysis approaches. This presents a major challenge for the field of sleep research. The need for free, open-source software that can read open-format data is essential for scientific advancement to be made in the field.

Sleep disorders as both risk factors for, and a consequence of, stroke: A narrative review

BACKGROUND AND PURPOSE

Sleep disorders are increasingly implicated as risk factors for stroke, as well as a determinant of stroke outcome. They can also occur secondary to the stroke itself. In this review, we describe the variety of different sleep disorders associated with stroke and analyze their effect on stroke risk and outcome.

METHODS

A search term-based literature review ("sleep," "insomnia," "narcolepsy," "restless legs syndrome," "periodic limb movements during sleep," "excessive daytime sleepiness" AND "stroke" OR "cerebrovascular" in PubMed; "stroke" and "sleep" in ClinicalTrials.gov) was performed. English articles from 1990 to March 2023 were considered.

RESULTS

Increasing evidence suggests that sleep disorders are risk factors for stroke. In addition, sleep disturbance has been reported in half of all stroke sufferers; specifically, an increase is not only sleep-related breathing disorders but also periodic limb movements during sleep, narcolepsy, rapid eye movement (REM) sleep behavior disorder, insomnia, sleep duration, and circadian rhythm sleep-wake disorders. Poststroke sleep disturbance has been associated with worse outcome.

CONCLUSION

Sleep disorders are risk factors for stroke and associated with worse stroke outcome. They are also a common consequence of stroke. Recent guidelines suggest screening for sleep disorders after stroke. It is possible that treatment of sleep disorders could both reduce stroke risk and improve stroke outcome, although further data from clinical trials are required.

Bridging AI and Clinical Practice: Integrating Automated Sleep Scoring Algorithm with Uncertainty-Guided Physician Review

Purpose

This study aims to enhance the clinical use of automated sleep-scoring algorithms by incorporating an uncertainty estimation approach to efficiently assist clinicians in the manual review of predicted hypnograms, a necessity due to the notable inter-scorer variability inherent in polysomnography (PSG) databases. Our efforts target the extent of review required to achieve predefined agreement levels, examining both in-domain (ID) and out-of-domain (OOD) data, and considering subjects' diagnoses.

Patients and Methods

A total of 19,578 PSGs from 13 open-access databases were used to train U-Sleep, a state-of-the-art sleep-scoring algorithm. We leveraged a comprehensive clinical database of an additional 8832 PSGs, covering a full spectrum of ages (0-91 years) and sleep-disorders, to refine the U-Sleep, and to evaluate different uncertainty-quantification approaches, including our novel confidence network. The ID data consisted of PSGs scored by over 50 physicians, and the two OOD sets comprised recordings each scored by a unique senior physician.

Results

U-Sleep demonstrated robust performance, with Cohen's kappa (K) at 76.2% on ID and 73.8-78.8% on OOD data. The confidence network excelled at identifying uncertain predictions, achieving AUROC scores of 85.7% on ID and 82.5-85.6% on OOD data. Independently of sleep-disorder status, statistical evaluations revealed significant differences in confidence scores between aligning vs discording predictions, and significant correlations of confidence scores with classification performance metrics. To achieve κ ≥ 90% with physician intervention, examining less than 29.0% of uncertain epochs was required, substantially reducing physicians' workload, and facilitating near-perfect agreement.

Conclusion

Inter-scorer variability limits the accuracy of the scoring algorithms to ~80%. By integrating an uncertainty estimation with U-Sleep, we enhance the review of predicted hypnograms, to align with the scoring taste of a responsible physician. Validated across ID and OOD data and various sleep-disorders, our approach offers a strategy to boost automated scoring tools' usability in clinical settings.

Single-channel EOG sleep staging on a heterogeneous cohort of subjects with sleep disorders

Objective.Sleep staging based on full polysomnography is the gold standard in the diagnosis of many sleep disorders. It is however costly, complex, and obtrusive due to the use of multiple electrodes. Automatic sleep staging based on single-channel electro-oculography (EOG) is a promising alternative, requiring fewer electrodes which could be self-applied below the hairline. EOG sleep staging algorithms are however yet to be validated in clinical populations with sleep disorders.Approach.We utilized the SOMNIA dataset, comprising 774 recordings from subjects with various sleep disorders, including insomnia, sleep-disordered breathing, hypersomnolence, circadian rhythm disorders, parasomnias, and movement disorders. The recordings were divided into train (574), validation (100), and test (100) groups. We trained a neural network that integrated transformers within a U-Net backbone. This design facilitated learning of arbitrary-distance temporal relationships within and between the EOG and hypnogram.Main results.For 5-class sleep staging, we achieved median accuracies of 85.0% and 85.2% and Cohen's kappas of 0.781 and 0.796 for left and right EOG, respectively. The performance using the right EOG was significantly better than using the left EOG, possibly because in the recommended AASM setup, this electrode is located closer to the scalp. The proposed model is robust to the presence of a variety of sleep disorders, displaying no significant difference in performance for subjects with a certain sleep disorder compared to those without.Significance.The results show that accurate sleep staging using single-channel EOG can be done reliably for subjects with a variety of sleep disorders.

SleepBoost: a multi-level tree-based ensemble model for automatic sleep stage classification

Neurodegenerative diseases often exhibit a strong link with sleep disruption, highlighting the importance of effective sleep stage monitoring. In this light, automatic sleep stage classification (ASSC) plays a pivotal role, now more streamlined than ever due to the advancements in deep learning (DL). However, the opaque nature of DL models can be a barrier in their clinical adoption, due to trust concerns among medical practitioners. To bridge this gap, we introduce SleepBoost, a transparent multi-level tree-based ensemble model specifically designed for ASSC. Our approach includes a crafted feature engineering block (FEB) that extracts 41 time and frequency domain features, out of which 23 are selected based on their high mutual information score (> 0.23). Uniquely, SleepBoost integrates three fundamental linear models into a cohesive multi-level tree structure, further enhanced by a novel reward-based adaptive weight allocation mechanism. Tested on the Sleep-EDF-20 dataset, SleepBoost demonstrates superior performance with an accuracy of 86.3%, F1-score of 80.9%, and Cohen kappa score of 0.807, outperforming leading DL models in ASSC. An ablation study underscores the critical role of our selective feature extraction in enhancing model accuracy and interpretability, crucial for clinical settings. This innovative approach not only offers a more transparent alternative to traditional DL models but also extends potential implications for monitoring and understanding sleep patterns in the context of neurodegenerative disorders. The open-source availability of SleepBoost's implementation at https://github.com/akibzaman/SleepBoost can further facilitate its accessibility and potential for widespread clinical adoption.

Reliable automatic sleep stage classification based on hybrid intelligence

Sleep staging is a vital aspect of sleep assessment, serving as a critical tool for evaluating the quality of sleep and identifying sleep disorders. Manual sleep staging is a laborious process, while automatic sleep staging is seldom utilized in clinical practice due to issues related to the inadequate accuracy and interpretability of classification results in automatic sleep staging models. In this work, a hybrid intelligent model is presented for automatic sleep staging, which integrates data intelligence and knowledge intelligence, to attain a balance between accuracy, interpretability, and generalizability in the sleep stage classification. Specifically, it is built on any combination of typical electroencephalography (EEG) and electrooculography (EOG) channels, including a temporal fully convolutional network based on the U-Net architecture and a multi-task feature mapping structure. The experimental results show that, compared to current interpretable automatic sleep staging models, our model achieves a Macro-F1 score of 0.804 on the ISRUC dataset and 0.780 on the Sleep-EDFx dataset. Moreover, we use knowledge intelligence to address issues of excessive jumps and unreasonable sleep stage transitions in the coarse sleep graphs obtained by the model. We also explore the different ways knowledge intelligence affects coarse sleep graphs by combining different sleep graph correction methods. Our research can offer convenient support for sleep physicians, indicating its significant potential in improving the efficiency of clinical sleep staging.

A sleep staging model on wavelet-based adaptive spectrogram reconstruction and light weight CNN

Effective methods for automatic sleep staging are important for diagnosis and treatment of sleep disorders. EEG has weak signal properties and complex frequency components during the transition of sleep stages. Wavelet-based adaptive spectrogram reconstruction (WASR) by seed growth is utilized to capture dominant time-frequency patterns of sleep EEG. We introduced variant energy from Teager operator in WASR to capture hidden dynamic patterns of EEG, which produced additional spectrograms. These spectrograms enabled a light weight CNN to detect and extract finer details of different sleep stages, which improved the feature representation of EEG. With specially designed depthwise separable convolution, the light weight CNN achieved more robust sleep stage classification. Experimental results on Sleep-EDF 20 dataset showed that our proposed model yielded overall accuracy of 87.6%, F1-score of 82.1%, and Cohen kappa of 0.83, which is competitive compared with baselines with reduced computation cost.

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 pretrained model is flexible and can be fine-tuned to perform well on new tasks including distinguishing individuals and 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 schemas and further data-driven exploration of sleep.

ZleepAnlystNet: a novel deep learning model for automatic sleep stage scoring based on single-channel raw EEG data using separating training

Numerous models for sleep stage scoring utilizing single-channel raw EEG signal have typically employed CNN and BiLSTM architectures. While these models, incorporating temporal information for sequence classification, demonstrate superior overall performance, they often exhibit low per-class performance for N1-stage, necessitating an adjustment of loss function. However, the efficacy of such adjustment is constrained by the training process. In this study, a pioneering training approach called separating training is introduced, alongside a novel model, to enhance performance. The developed model comprises 15 CNN models with varying loss function weights for feature extraction and 1 BiLSTM for sequence classification. Due to its architecture, this model cannot be trained using an end-to-end approach, necessitating separate training for each component using the Sleep-EDF dataset. Achieving an overall accuracy of 87.02%, MF1 of 82.09%, Kappa of 0.8221, and per-class F1-socres (W 90.34%, N1 54.23%, N2 89.53%, N3 88.96%, and REM 87.40%), our model demonstrates promising performance. Comparison with sleep technicians reveals a Kappa of 0.7015, indicating alignment with reference sleep stags. Additionally, cross-dataset validation and adaptation through training with the SHHS dataset yield an overall accuracy of 84.40%, MF1 of 74.96% and Kappa of 0.7785 when tested with the Sleep-EDF-13 dataset. These findings underscore the generalization potential in model architecture design facilitated by our novel training approach.

A perspective on automated rapid eye movement sleep assessment

Rapid eye movement sleep is associated with distinct changes in various biomedical signals that can be easily captured during sleep, lending themselves to automated sleep staging using machine learning systems. Here, we provide a perspective on the critical characteristics of biomedical signals associated with rapid eye movement sleep and how they can be exploited for automated sleep assessment. We summarise key historical developments in automated sleep staging systems, having now achieved classification accuracy on par with human expert scorers and their role in the clinical setting. We also discuss rapid eye movement sleep assessment with consumer sleep trackers and its potential for unprecedented sleep assessment on a global scale. We conclude by providing a future outlook of computerised rapid eye movement sleep assessment and the role AI systems may play.

Long sleep time and excessive need for sleep: State of the art and perspectives

The mechanisms underlying the individual need for sleep are unclear. Sleep duration is indeed influenced by multiple factors, such as genetic background, circadian and homeostatic processes, environmental factors, and sometimes transient disturbances such as infections. In some cases, the need for sleep dramatically and chronically increases, inducing a daily-life disability. This "excessive need for sleep" (ENS) was recently proposed and defined in a European Position Paper as a dimension of the hypersomnolence spectrum, "hypersomnia" being the objectified complaint of ENS. The most severe form of ENS has been described in Idiopathic Hypersomnia, a rare neurological disorder, but this disabling symptom can be also found in other hypersomnolence conditions. Because ENS has been defined recently, it remains a symptom poorly investigated and understood. However, protocols of long-term polysomnography recordings have been reported by expert centers in the last decades and open the way to a better understanding of ENS through a neurophysiological approach. In this narrative review, we will 1) present data related to the physiological and pathological variability of sleep duration and their mechanisms, 2) describe the published long-term polysomnography recording protocols, and 3) describe current neurophysiological tools to study sleep microstructure and discuss perspectives for a better understanding of ENS.

Research and application of deep learning-based sleep staging: Data, modeling, validation, and clinical practice

Over the past few decades, researchers have attempted to simplify and accelerate the process of sleep stage classification through various approaches; however, only a few such approaches have gained widespread acceptance. Artificial intelligence technology, particularly deep learning, is promising for earning the trust of the sleep medicine community in automated sleep-staging systems, thus facilitating its application in clinical practice and integration into daily life. We aimed to comprehensively review the latest methods that are applying deep learning for enhancing sleep staging efficiency and accuracy. Starting from the requisite "data" for constructing deep learning algorithms, we elucidated the current landscape of this domain and summarized the fundamental modeling process, encompassing signal selection, data pre-processing, model architecture, classification tasks, and performance metrics. Furthermore, we reviewed the applications of automated sleep staging in scenarios such as sleep-disorder screening, diagnostic procedures, and health monitoring and management. Finally, we conducted an in-depth analysis and discussion of the challenges and future in intelligent sleep staging, particularly focusing on large-scale sleep datasets, interdisciplinary collaborations, and human-computer interactions.

U-PASS: An uncertainty-guided deep learning pipeline for automated sleep staging

With the increasing prevalence of machine learning in critical fields like healthcare, ensuring the safety and reliability of these systems is crucial. Estimating uncertainty plays a vital role in enhancing reliability by identifying areas of high and low confidence and reducing the risk of errors. This study introduces U-PASS, a specialized human-centered machine learning pipeline tailored for clinical applications, which effectively communicates uncertainty to clinical experts and collaborates with them to improve predictions. U-PASS incorporates uncertainty estimation at every stage of the process, including data acquisition, training, and model deployment. Training is divided into a supervised pre-training step and a semi-supervised recording-wise finetuning step. We apply U-PASS to the challenging task of sleep staging and demonstrate that it systematically improves performance at every stage. By optimizing the training dataset, actively seeking feedback from domain experts for informative samples, and deferring the most uncertain samples to experts, U-PASS achieves an impressive expert-level accuracy of 85% on a challenging clinical dataset of elderly sleep apnea patients. This represents a significant improvement over the starting point at 75% accuracy. The largest improvement gain is due to the deferral of uncertain epochs to a sleep expert. U-PASS presents a promising AI approach to incorporating uncertainty estimation in machine learning pipelines, improving their reliability and unlocking their potential in clinical settings.

Artificial Intelligence Models for the Automation of Standard Diagnostics in Sleep Medicine-A Systematic Review

Sleep disorders, prevalent in the general population, present significant health challenges. The current diagnostic approach, based on a manual analysis of overnight polysomnograms (PSGs), is costly and time-consuming. Artificial intelligence has emerged as a promising tool in this context, offering a more accessible and personalized approach to diagnosis, particularly beneficial for under-served populations. This is a systematic review of AI-based models for sleep disorder diagnostics that were trained, validated, and tested on diverse clinical datasets. An extensive search of PubMed and IEEE databases yielded 2114 articles, but only 18 met our stringent selection criteria, underscoring the scarcity of thoroughly validated AI models in sleep medicine. The findings emphasize the necessity of a rigorous validation of AI models on multimodal clinical data, a step crucial for their integration into clinical practice. This would be in line with the American Academy of Sleep Medicine's support of AI research.

An automatic method using MFCC features for sleep stage classification

Sleep stage classification is a necessary step for diagnosing sleep disorders. Generally, experts use traditional methods based on every 30 seconds (s) of the biological signals, such as electrooculograms (EOGs), electrocardiograms (ECGs), electromyograms (EMGs), and electroencephalograms (EEGs), to classify sleep stages. Recently, various state-of-the-art approaches based on a deep learning model have been demonstrated to have efficient and accurate outcomes in sleep stage classification. In this paper, a novel deep convolutional neural network (CNN) combined with a long short-time memory (LSTM) model is proposed for sleep scoring tasks. A key frequency domain feature named Mel-frequency Cepstral Coefficient (MFCC) is extracted from EEG and EMG signals. The proposed method can learn features from frequency domains on different bio-signal channels. It firstly extracts the MFCC features from multi-channel signals, and then inputs them to several convolutional layers and an LSTM layer. Secondly, the learned representations are fed to a fully connected layer and a softmax classifier for sleep stage classification. The experiments are conducted on two widely used sleep datasets, Sleep Heart Health Study (SHHS) and Vincent's University Hospital/University College Dublin Sleep Apnoea (UCDDB) to test the effectiveness of the method. The results of this study indicate that the model can perform well in the classification of sleep stages using the features of the 2-dimensional (2D) MFCC feature. The advantage of using the feature is that it can be used to input a two-dimensional data stream, which can be used to retain information about each sleep stage. Using 2D data streams can reduce the time it takes to retrieve the data from the one-dimensional stream. Another advantage of this method is that it eliminates the need for deep layers, which can help improve the performance of the model. For instance, by reducing the number of layers, our seven layers of the model structure takes around 400 s to train and test 100 subjects in the SHHS1 dataset. Its best accuracy and Cohen's kappa are 82.35% and 0.75 for the SHHS dataset, and 73.07% and 0.63 for the UCDDB dataset, respectively.

The application of machine learning on brain imaging features of different narcolepsy subtypes

STUDY OBJECTIVES

Narcolepsy is a central hypersomnia disorder, and differential diagnoses between its subtypes can be difficult. Hence, we applied machine learning to analyze the positron emission tomography (PET) data of patients with type 1 or type 2 narcolepsy, and patients with type 1 narcolepsy and comorbid schizophrenia, to construct predictive models to facilitate the diagnosis.

METHODS

This is a retrospective and prospective case-control study of adolescent and young adult patients with type 1 or type 2 narcolepsy, and type 1 narcolepsy and comorbid schizophrenia. All participants received 18-F-fluorodeoxy glucose PET, sleep studies, neurocognitive tests, sleep questionnaires, and human leukocyte antigen typing. The collected PET data were analyzed by feature selections and classification methods in machine learning to construct predictive models.

RESULTS

A total of 314 participants with narcolepsy were enrolled; 204 had type 1 narcolepsy, 90 had type 2 narcolepsy, and 20 had type 1 narcolepsy and comorbid schizophrenia. We used three filter methods for feature selection followed by a comparative analysis of classification methods. To apply a small number of regions of interest (ROI) and high classification accuracy, the Naïve Bayes classifier with the Term Variance as feature selection achieved the goal with only three ROIs (left basal ganglia, left Heschl, and left striatum) and produced an accuracy of higher than 99%.

CONCLUSIONS

The accuracy of our predictive model of PET data are promising and can aid clinicians in the diagnosis of narcolepsy subtypes. Future research with a larger sample size could further refine the predictive model of narcolepsy.

Review and perspective on sleep-disordered breathing research and translation to clinics

Sleep-disordered breathing, ranging from habitual snoring to severe obstructive sleep apnea, is a prevalent public health issue. Despite rising interest in sleep and awareness of sleep disorders, sleep research and diagnostic practices still rely on outdated metrics and laborious methods reducing the diagnostic capacity and preventing timely diagnosis and treatment. Consequently, a significant portion of individuals affected by sleep-disordered breathing remain undiagnosed or are misdiagnosed. Taking advantage of state-of-the-art scientific, technological, and computational advances could be an effective way to optimize the diagnostic and treatment pathways. We discuss state-of-the-art multidisciplinary research, review the shortcomings in the current practices of SDB diagnosis and management in adult populations, and provide possible future directions. We critically review the opportunities for modern data analysis methods and machine learning to combine multimodal information, provide a perspective on the pitfalls of big data analysis, and discuss approaches for developing analysis strategies that overcome current limitations. We argue that large-scale and multidisciplinary collaborative efforts based on clinical, scientific, and technical knowledge and rigorous clinical validation and implementation of the outcomes in practice are needed to move the research of sleep-disordered breathing forward, thus increasing the quality of diagnostics and treatment.

MixSleepNet: A Multi-Type Convolution Combined Sleep Stage Classification Model

BACKGROUND AND OBJECTIVE

Sleep staging is an essential step for sleep disorder diagnosis, which is time-intensive and laborious for experts to perform this work manually. Automatic sleep stage classification methods not only alleviate experts from these demanding tasks but also enhance the accuracy and efficiency of the classification process.

METHODS

A novel multi-channel biosignal-based model constructed by the combination of a 3D convolutional operation and a graph convolutional operation is proposed for the automated sleep stages using various physiological signals. Both the 3D convolution and graph convolution can aggregate information from neighboring brain areas, which helps to learn intrinsic connections from the biosignals. Electroencephalogram (EEG), electromyogram (EMG), electrooculogram (EOG) and electrocardiogram (ECG) signals are employed to extract time domain and frequency domain features. Subsequently, these signals are input to the 3D convolutional and graph convolutional branches, respectively. The 3D convolution branch can explore the correlations between multi-channel signals and multi-band waves in each channel in the time series, while the graph convolution branch can explore the connections between each channel and each frequency band. In this work, we have developed the proposed multi-channel convolution combined sleep stage classification model (MixSleepNet) using ISRUC datasets (Subgroup 3 and 50 random samples from Subgroup 1).

RESULTS

Based on the first expert's label, our generated MixSleepNet yielded an accuracy, F1-score and Cohen kappa scores of 0.830, 0.821 and 0.782, respectively for ISRUC-S3. It obtained accuracy, F1-score and Cohen kappa scores of 0.812, 0.786, and 0.756, respectively for the ISRUC-S1 dataset. In accordance with the evaluations conducted by the second expert, the comprehensive accuracies, F1-scores, and Cohen kappa coefficients for the ISRUC-S3 and ISRUC-S1 datasets are determined to be 0.837, 0.820, 0.789, and 0.829, 0.791, 0.775, respectively.

CONCLUSION

The results of the performance metrics by the proposed method are much better than those from all the compared models. Additional experiments were carried out on the ISRUC-S3 sub-dataset to evaluate the contributions of each module towards the classification performance.

Role of Daytime Continuous Polysomnography in the Diagnosis of Pediatric Narcolepsy Type 1

BACKGROUND AND OBJECTIVES

Narcolepsy type 1 (NT1) is still largely underdiagnosed or diagnosed too late in children. Difficulties in obtaining rapid and reliable diagnostic evaluations of the condition in clinical practice partially explain this problem. Predictors of NT1 include cataplexy and sleep-onset REM periods (SOREMPs), documented during nocturnal polysomnography (N-PSG) or through the multiple sleep latency test (MSLT), although low CSF hypocretin-1 (CSF hcrt-1) is the definitive biological disease marker. Obtaining reliable MSLT results is not always feasible in children; therefore, this study aimed to validate daytime continuous polysomnography (D-PSG) as an alternative diagnostic tool.

METHODS

Two hundred consecutive patients aged younger than 18 years (112 with NT1; 25 with other hypersomnias, including narcolepsy type 2 and idiopathic hypersomnia; and 63 with subjective excessive daytime sleepiness) were randomly split into 2 groups: group 1 (n = 133) for the identification of diagnostic markers and group 2 (n = 67) for the validation of the detected markers. The D-PSG data collected included the number of spontaneous naps, total sleep time, and the number of daytime SOREMPs (d-SOREMP). D-PSG data were tested against CSF hcrt-1 deficiency (NT1 diagnosis) as the gold standard using receiver operating characteristic (ROC) curve analysis in group 1. ROC diagnostic performances of single and combined D-PSG parameters were tested in group 1 and validated in group 2.

RESULTS

In group 1, the areas under the ROC curve (AUCs) were 0.91 (95% CI 0.86-0.96) for d-SOREMPs, 0.81 (95% CI 0.74-0.89) for the number of spontaneous naps, and 0.70 (95% CI 0.60-0.79) for total sleep time. A d-SOREMP count ≥1 (sensitivity of 95% and specificity of 72%), coupled with a diurnal total sleep time above 60 minutes (sensitivity of 89% and specificity of 91%), identified NT1 in group 1 with high reliability (area under the ROC curve of 0.93, 95% CI 0.88-0.97). These results were confirmed in the validation group with an AUC of 0.88 (95% CI 0.79-0.97).

DISCUSSION

D-PSG recording is an easily performed, cost-effective, and reliable tool for identifying NT1 in children. Further studies should confirm its validity with home D-PSG monitoring. These alternative procedures could be used to confirm NT1 diagnosis and curtail diagnostic delay.

Standardized image-based polysomnography database and deep learning algorithm for sleep-stage classification

STUDY OBJECTIVES

Polysomnography (PSG) scoring is labor-intensive, subjective, and often ambiguous. Recently several deep learning (DL) models for automated sleep scoring have been developed, they are tied to a fixed amount of input channels and resolution. In this study, we constructed a standardized image-based PSG dataset in order to overcome the heterogeneity of raw signal data obtained from various PSG devices and various sleep laboratory environments.

METHODS

All individually exported European data format files containing raw signals were converted into images with an annotation file, which contained the demographics, diagnoses, and sleep statistics. An image-based DL model for automatic sleep staging was developed, compared with a signal-based model, and validated in an external dataset.

RESULTS

We constructed 10253 image-based PSG datasets using a standardized format. Among these, 7745 diagnostic PSG data were used to develop our DL model. The DL model using the image dataset showed similar performance to the signal-based dataset for the same subject. The overall DL accuracy was greater than 80%, even with severe obstructive sleep apnea. Moreover, for the first time, we showed explainable DL in the field of sleep medicine as visualized key inference regions using Eigen-class activation maps. Furthermore, when a DL model for sleep scoring performs external validation, we achieved a relatively good performance.

CONCLUSIONS

Our main contribution demonstrates the availability of a standardized image-based dataset, and highlights that changing the data sampling rate or number of sensors may not require retraining, although performance decreases slightly as the number of sensors decreases.

Dusk2Dawn: an EEGLAB plugin for automatic cleaning of whole-night sleep electroencephalogram using Artifact Subspace Reconstruction

Whole-night sleep electroencephalogram (EEG) is plagued by several types of large-amplitude artifacts. Common approaches to remove them are fraught with issues: channel interpolation, rejection of noisy intervals, and independent component analysis are time-consuming, rely on subjective user decisions, and result in signal loss. Artifact Subspace Reconstruction (ASR) is an increasingly popular approach to rapidly and automatically clean wake EEG data. Indeed, ASR adaptively removes large-amplitude artifacts regardless of their scalp topography or consistency throughout the recording. This makes ASR, at least in theory, a highly-promising tool to clean whole-night EEG. However, ASR crucially relies on calibration against a subset of relatively clean "baseline" data. This is problematic when the baseline changes substantially over time, as in whole-night EEG data. Here we tackled this issue and, for the first time, validated ASR for cleaning sleep EEG. We demonstrate that ASR applied out-of-the-box, with the parameters recommended for wake EEG, results in the dramatic removal of slow waves. We also provide an appropriate procedure to use ASR for automatic and rapid cleaning of whole-night sleep EEG data or any long EEG recording. Our procedure is freely available in Dusk2Dawn, an open-source plugin for EEGLAB.

Enhanced sleep staging with artificial intelligence: a validation study of new software for sleep scoring

Manual sleep staging (MSS) using polysomnography is a time-consuming task, requires significant training, and can lead to significant variability among scorers. STAGER is a software program based on machine learning algorithms that has been developed by Medibio Limited (Savage, MN, USA) to perform automatic sleep staging using only EEG signals from polysomnography. This study aimed to extensively investigate its agreement with MSS performed during clinical practice and by three additional expert sleep technicians. Forty consecutive polysomnographic recordings of patients referred to three US sleep clinics for sleep evaluation were retrospectively collected and analyzed. Three experienced technicians independently staged the recording using the electroencephalography, electromyography, and electrooculography signals according to the American Academy of Sleep Medicine guidelines. The staging initially performed during clinical practice was also considered. Several agreement statistics between the automatic sleep staging (ASS) and MSS, among the different MSSs, and their differences were calculated. Bootstrap resampling was used to calculate 95% confidence intervals and the statistical significance of the differences. STAGER's ASS was most comparable with, or statistically significantly better than the MSS, except for a partial reduction in the positive percent agreement in the wake stage. These promising results indicate that STAGER software can perform ASS of inpatient polysomnographic recordings accurately in comparison with MSS.

Development of generalizable automatic sleep staging using heart rate and movement based on large databases

Purpose

With the advancement of deep neural networks in biosignals processing, the performance of automatic sleep staging algorithms has improved significantly. However, sleep staging using only non-electroencephalogram features has not been as successful, especially following the current American Association of Sleep Medicine (AASM) standards. This study presents a fine-tuning based approach to widely generalizable automatic sleep staging using heart rate and movement features trained and validated on large databases of polysomnography.

Methods

A deep neural network is used to predict sleep stages using heart rate and movement features. The model is optimized on a dataset of 8731 nights of polysomnography recordings labeled using the Rechtschaffen & Kales scoring system, and fine-tuned to a smaller dataset of 1641 AASM-labeled recordings. The model prior to and after fine-tuning is validated on two AASM-labeled external datasets totaling 1183 recordings. In order to measure the performance of the model, the output of the optimized model is compared to reference expert-labeled sleep stages using accuracy and Cohen's κ as key metrics.

Results

The fine-tuned model showed accuracy of 76.6% with Cohen's κ of 0.606 in one of the external validation datasets, outperforming a previously reported result, and showed accuracy of 81.0% with Cohen's κ of 0.673 in another external validation dataset.

Conclusion

These results indicate that the proposed model is generalizable and effective in predicting sleep stages using features which can be extracted from non-contact sleep monitors. This holds valuable implications for future development of home sleep evaluation systems.

Decentralized Data-Privacy Preserving Deep-Learning Approaches for Enhancing Inter-Database Generalization in Automatic Sleep Staging

Automatic sleep staging has been an active field of development. Despite multiple efforts, the area remains a focus of research interest. Indeed, while promising results have reported in past literature, uptake of automatic sleep scoring in the clinical setting remains low. One of the current issues regards the difficulty to generalization performance results beyond the local testing scenario, i.e. across data from different clinics. Issues derived from data-privacy restrictions, that generally apply in the medical domain, pose additional difficulties in the successful development of these methods. We propose the use of several decentralized deep-learning approaches, namely ensemble models and federated learning, for robust inter-database performance generalization and data-privacy preservation in automatic sleep staging scenario. Specifically, we explore four ensemble combination strategies (max-voting, output averaging, size-proportional weighting, and Nelder-Mead) and present a new federated learning algorithm, so-called sub-sampled federated stochastic gradient descent (ssFedSGD). To evaluate generalization capabilities of such approaches, experimental procedures are carried out using a leaving-one-database-out direct-transfer scenario on six independent and heterogeneous public sleep staging databases. The resulting performance is compared with respect to two baseline approaches involving single-database and centralized multiple-database derived models. Our results show that proposed decentralized learning methods outperform baseline local approaches, and provide similar generalization results to centralized database-combined approaches. We conclude that these methods are more preferable choices, as they come with additional advantages concerning improved scalability, flexible design, and data-privacy preservation.

Modeling the Impact of Inter-Rater Disagreement on Sleep Statistics Using Deep Generative Learning

Sleep staging is the process by which an overnight polysomnographic measurement is segmented into epochs of 30 seconds, each of which is annotated as belonging to one of five discrete sleep stages. The resulting scoring is graphically depicted as a hypnogram, and several overnight sleep statistics are derived, such as total sleep time and sleep onset latency. Gold standard sleep staging as performed by human technicians is time-consuming, costly, and comes with imperfect inter-scorer agreement, which also results in inter-scorer disagreement about the overnight statistics. Deep learning algorithms have shown promise in automating sleep scoring, but struggle to model inter-scorer disagreement in sleep statistics. To that end, we introduce a novel technique using conditional generative models based on Normalizing Flows that permits the modeling of the inter-rater disagreement of overnight sleep statistics, termed U-Flow. We compare U-Flow to other automatic scoring methods on a hold-out test set of 70 subjects, each scored by six independent scorers. The proposed method achieves similar sleep staging performance in terms of accuracy and Cohen's kappa on the majority-voted hypnograms. At the same time, U-Flow outperforms the other methods in terms of modeling the inter-rater disagreement of overnight sleep statistics. The consequences of inter-rater disagreement about overnight sleep statistics may be great, and the disagreement potentially carries diagnostic and scientifically relevant information about sleep structure. U-Flow is able to model this disagreement efficiently and can support further investigations into the impact inter-rater disagreement has on sleep medicine and basic sleep research.

Dietary Supplementation with Lauric Acid Improves Aerobic Endurance in Sedentary Mice via Enhancing Fat Mobilization and Glyconeogenesis

BACKGROUND

Lauric acid (LA), a major, natural, medium-chain fatty acid, is considered an efficient energy substrate for intense exercise and in patients with long-chain fatty acid β-oxidation disorders. However, few studies have focused on the role of LA in exercise performance and related glucolipid metabolism in vivo.

OBJECTIVES

We aimed to investigate the effect of dietary supplementation with LA on exercise performance and related metabolic mechanisms.

METHODS

Male C57BL/6N mice (14 wk old) were fed a basal diet or a diet containing 1% LA, and a series of exercise tests, including a high-speed treadmill test, aerobic endurance exercises, a 4-limb hanging test, and acute aerobic exercises, were performed.

RESULTS

Dietary supplementation with 1.0% LA accelerated the recovery from fatigue after explosive exercise (P < 0.05) and improved aerobic endurance and muscle strength in sedentary mice (P = 0.039). Lauric acid intake not only changed muscle fatty acid profiles, including increases in C12:0 and n-6/n-3 PUFAs (P < 0.001) and reductions in C18:0, C20:4n-6, C22:6n-3, and n-3 PUFAs (P < 0.05) but also enhanced fat mobilization from adipose tissue and fatty acid oxidation in the liver, at least partly via the AMP-activated protein kinase-acetyl CoA carboxylase pathway (P < 0.05). Likewise, LA supplementation promoted liver glyconeogenesis and conserved muscular glycogen during acute aerobic exercise (P < 0.05), which was accompanied by an increase in the mitochondrial DNA copy number and Krebs cycle activity in skeletal muscle (P < 0.05).

CONCLUSIONS

Dietary supplemental LA serves as an efficient energy substrate for sedentary mice to improve aerobic exercise endurance and muscle strength through regulation of glucolipid metabolism. These findings imply that LA supplementation might be a promising nutritional strategy to improve aerobic exercise performance in sedentary people.

An explainable deep-learning model to stage sleep states in children and propose novel EEG-related patterns in sleep apnea

Automatic deep-learning models used for sleep scoring in children with obstructive sleep apnea (OSA) are perceived as black boxes, limiting their implementation in clinical settings. Accordingly, we aimed to develop an accurate and interpretable deep-learning model for sleep staging in children using single-channel electroencephalogram (EEG) recordings. We used EEG signals from the Childhood Adenotonsillectomy Trial (CHAT) dataset (n = 1637) and a clinical sleep database (n = 980). Three distinct deep-learning architectures were explored to automatically classify sleep stages from a single-channel EEG data. Gradient-weighted Class Activation Mapping (Grad-CAM), an explainable artificial intelligence (XAI) algorithm, was then applied to provide an interpretation of the singular EEG patterns contributing to each predicted sleep stage. Among the tested architectures, a standard convolutional neural network (CNN) demonstrated the highest performance for automated sleep stage detection in the CHAT test set (accuracy = 86.9% and five-class kappa = 0.827). Furthermore, the CNN-based estimation of total sleep time exhibited strong agreement in the clinical dataset (intra-class correlation coefficient = 0.772). Our XAI approach using Grad-CAM effectively highlighted the EEG features associated with each sleep stage, emphasizing their influence on the CNN's decision-making process in both datasets. Grad-CAM heatmaps also allowed to identify and analyze epochs within a recording with a highly likelihood to be misclassified, revealing mixed features from different sleep stages within these epochs. Finally, Grad-CAM heatmaps unveiled novel features contributing to sleep scoring using a single EEG channel. Consequently, integrating an explainable CNN-based deep-learning model in the clinical environment could enable automatic sleep staging in pediatric sleep apnea tests.

Narcolepsies, update in 2023

Narcolepsy type 1 (NT1) and type 2 (NT2), also known as narcolepsy with and without cataplexy, are sleep disorders that benefited from major scientific advances over the last two decades. NT1 is caused by the loss of hypothalamic neurons producing orexin/hypocretin, a neurotransmitter regulating sleep and wake, which can be measured in the cerebrospinal fluid (CSF). A low CSF level of hypocretin-1/orexin-A is a highly specific and sensitive biomarker, sufficient to diagnose NT1. Orexin-deficiency is responsible for the main NT1 symptoms: sleepiness, cataplexy, disrupted nocturnal sleep, sleep-related hallucinations, and sleep paralysis. In the absence of a lumbar puncture, the diagnosis is based on neurophysiological tests (nocturnal and diurnal) and the presence of the pathognomonic symptom cataplexy. In the revised version of the International Classification of sleep Disorders, 3rd edition (ICSD-3-TR), a sleep onset rapid eye movement sleep (REM) period (SOREMP) (i.e. rapid occurrence of REM sleep) during the previous polysomnography may replace the diurnal multiple sleep latency test, when clear-cut cataplexy is present. A nocturnal SOREMP is very specific but not sensitive enough, and the diagnosis of cataplexy is usually based on clinical interview. It is thus of crucial importance to define typical versus atypical cataplectic attacks, and a list of clinical features and related degrees of certainty is proposed in this paper (expert opinion). The time frame of at least three months of evolution of sleepiness to diagnose NT1 was removed in the ICSD-3-TR, when clear-cut cataplexy or orexin-deficiency are established. However, it was kept for NT2 diagnosis, a less well-characterized disorder with unknown clinical course and absence of biolo biomarkers; sleep deprivation, shift working and substances intake being major differential diagnoses. Treatment of narcolepsy is nowadays only symptomatic, but the upcoming arrival of non-peptide orexin receptor-2 agonists should be a revolution in the management of these rare sleep diseases.

Software defined radio frequency sensing framework for intelligent monitoring of sleep apnea syndrome

Healthy sleep is vital to all functions in the body. It improves physical and mental health, strengthens resistance against diseases, and develops strong immunity against metabolism and chronic diseases. However, a sleep disorder can cause the inability to sleep well. Sleep apnea syndrome is a critical breathing disorder that occurs during sleeping when breathing stops suddenly and starts when awake, causing sleep disturbance. If it is not treated timely, it can produce loud snoring and drowsiness or causes more acute health problems such as high blood pressure or heart attack. The accepted standard for diagnosing sleep apnea syndrome is full-night polysomnography. However, its limitations include a high cost and inconvenience. This article aims to develop an intelligent monitoring framework for detecting breathing events based on Software Defined Radio Frequency (SDRF) sensing and verify its feasibility for diagnosing sleep apnea syndrome. We extract the wireless channel state information (WCSI) for breathing motion using channel frequency response (CFR) recorded in time at every instant at the receiver. The proposed approach simplifies the receiver structure with the added functionality of communication and sensing together. Initially, simulations are conducted to test the feasibility of the SDRF sensing design for the simulated wireless channel. Then, a real-time experimental setup is developed in a lab environment to address the challenges of the wireless channel. We conducted 100 experiments to collect the dataset of 25 subjects for four breathing patterns. SDRF sensing system accurately detected breathing events during sleep without subject contact. The developed intelligent framework uses machine learning classifiers to classify sleep apnea syndrome and other breathing patterns with an acceptable accuracy of 95.9%. The developed framework aims to build a non-invasive sensing system to diagnose patients conveniently suffering from sleep apnea syndrome. Furthermore, this framework can easily be further extended for E-health applications.

Repeated polysomnography and multiple sleep latency test in narcolepsy type 1 and other hypersomnolence disorders

BACKGROUND

The diagnosis of narcolepsy is based on clinical information, combined with polysomnography (PSG) and the Multiple Sleep Latency Test (MSLT). PSG and the MSLT are moderately reliable at diagnosing narcolepsy type 1 (NT1) but unreliable for diagnosing narcolepsy type 2 (NT2). This is a problem, especially given the increased risk of a false-positive MSLT in the context of circadian misalignment or sleep deprivation, both of which commonly occur in the general population.

AIM

We aimed to clarify the accuracy of PSG/MSLT testing in diagnosing NT1 versus controls without sleep disorders. Repeatability and reliability of PSG/MSLT testing and temporal changes in clinical findings of patients with NT1 versus patients with hypersomnolence with normal hypocretin-1 were compared.

METHOD

84 patients with NT1 and 100 patients with non-NT1-hypersomnolence disorders, all with congruent cerebrospinal fluid hypocretin-1 (CSF-hcrt-1) levels, were included. Twenty-five of the 84 NT1 patients and all the hypersomnolence disorder patients underwent a follow-up evaluation consisting of clinical assessment, PSG, and a modified MSLT. An additional 68 controls with no sleep disorders were assessed at baseline.

CONCLUSION

Confirming results from previous studies, we found that PSG and our modified MSLT accurately and reliably diagnosed hypocretin-deficient NT1 (accuracy = 0.88, reliability = 0.80). Patients with NT1 had stable clinical and electrophysiological presentations over time that suggested a stable phenotype. In contrast, the PSG/MSLT results of patients with hypersomnolence, and normal CSF-hcrt-1 had poor reliability (0.32) and low repeatability.

Narcolepsy Diagnosis With Sleep Stage Features Using PSG Recordings

Narcolepsy is a sleep disorder affecting millions of people worldwide and causes serious public health problems. It is hard for doctors to correctly and objectively diagnose narcolepsy. Polysomnography (PSG) recordings, a gold standard for sleep monitoring and quality measurement, can provide abundant and objective cues for the narcolepsy diagnosis. There have been some studies on automatic narcolepsy diagnosis using PSG recordings. However, the sleep stage information, an important cue for narcolepsy diagnosis, has not been fully utilized. For example, some studies have not considered the sleep stage information to diagnose narcolepsy. Although some studies consider the sleep stage information, the stages are manually scored by experts, which is time-consuming and subjective. And the framework using sleep stages scored automatically for narcolepsy diagnosis is designed in a two-phase learning manner, where sleep staging in the first phase and diagnosis in the second phase, causing cumulative error and degrading the performance. To address these challenges, we propose a novel end-to-end framework for automatic narcolepsy diagnosis using PSG recordings. In particular, adopting the idea of multi-task learning, we take the sleep staging as our auxiliary task, and then combine the sleep stage related features with narcolepsy related features for our primary task of narcolepsy diagnosis. We collected a dataset of PSG recordings from 77 participants and evaluated our framework on it. Both of the sleep stage features and the end-to-end fashion contribute to diagnosis performance. Moreover, we do a comprehensive analysis on the relationship between sleep stages and narcolepsy, correlation of different channels, predictive ability of different sensing data, and diagnosis results in subject level.

Moving time zones in a flash with light therapy during sleep

In humans, exposure to continuous light is typically used to change the timing of the circadian clock. This study examines the efficiency of a sequence of light flashes ("flash therapy") applied during sleep to shift the clock. Healthy participants (n = 10) took part in two 36-h laboratory stays, receiving a placebo (goggles, no light) during one visit and the intervention (goggles, 2-ms flashes broad-spectrum light for 60 min, delivered every 15 s, starting 30 min after habitual sleep onset) during the other. Circadian phase shift was assessed with changes in salivary dim light melatonin onset (DLMO). Sleep, measured with polysomnography, was analyzed to assess changes in sleep architecture and spectral power. After 1 h of flashes, DLMO showed a substantial delay (1.13 ± 1.27 h) compared to placebo (12 ± 20 min). Two individuals exhibited very large shifts of 6.4 and 3.1 h. There were no substantive differences in sleep architecture, but some evidence for greater instability in sleep. 1 h of flash therapy during sleep evokes large changes in circadian timing, up to 6 h, and does so with only minimal, if any, impact on sleep. Flash therapy may offer a practical option to delay the circadian clock in shift workers and jet travelers.

Challenges of Applying Automated Polysomnography Scoring at Scale

Automatic polysomnography analysis can be leveraged to shorten scoring times, reduce associated costs, and ultimately improve the overall diagnosis of sleep disorders. Multiple and diverse strategies have been attempted for implementation of this technology at scale in the routine workflow of sleep centers. The field, however, is complex and presents unsolved challenges in a number of areas. Recent developments in computer science and artificial intelligence are nevertheless closing the gap. Technological advances are also opening new pathways for expanding our current understanding of the domain and its analysis.

MSED: A Multi-Modal Sleep Event Detection Model for Clinical Sleep Analysis

Clinical sleep analysis require manual analysis of sleep patterns for correct diagnosis of sleep disorders. However, several studies have shown significant variability in manual scoring of clinically relevant discrete sleep events, such as arousals, leg movements, and sleep disordered breathing (apneas and hypopneas). We investigated whether an automatic method could be used for event detection and if a model trained on all events (joint model) performed better than corresponding event-specific models (single-event models). We trained a deep neural network event detection model on 1653 individual recordings and tested the optimized model on 1000 separate hold-out recordings. F1 scores for the optimized joint detection model were 0.70, 0.63, and 0.62 for arousals, leg movements, and sleep disordered breathing, respectively, compared to 0.65, 0.61, and 0.60 for the optimized single-event models. Index values computed from detected events correlated positively with manual annotations (r2 = 0.73, r2 = 0.77, r2 = 0.78, respectively). We furthermore quantified model accuracy based on temporal difference metrics, which improved overall by using the joint model compared to single-event models. Our automatic model jointly detects arousals, leg movements and sleep disordered breathing events with high correlation with human annotations. Finally, we benchmark against previous state-of-the-art multi-event detection models and found an overall increase in F1 score with our proposed model despite a 97.5% reduction in model size.

Automated analysis of a large-scale paediatric dataset illustrates the interdependent relationship between epilepsy and sleep

Slow waves are an electrophysiological characteristic of non-rapid eye movement sleep and a marker of the restorative function of sleep. In certain pathological conditions, such as different types of epilepsy, slow-wave sleep is affected by epileptiform discharges forming so-called "spike-waves". Previous evidence shows that the overnight change in slope of slow waves during sleep is impaired under these conditions. However, these past studies were performed in a small number of patients, considering only short segments of the recording night. Here, we screened a clinical data set of 39'179 pediatric EEG recordings acquired in the past 25 years (1994-2019) at the University Children's Hospital Zurich and identified 413 recordings of interest. We applied an automated approach based on machine learning to investigate the relationship between sleep and epileptic spikes in this large-scale data set. Our findings show that the overnight change in the slope of slow waves was correlated with the spike-wave index, indicating that the impairment of the net reduction in synaptic strength during sleep is spike dependent.

Central Disorders of Hypersomnolence

OBJECTIVE

The goals of this article are to describe the clinical approach to and management of patients with central disorders of hypersomnolence, and to understand and differentiate available diagnostic tools.

LATEST DEVELOPMENTS

Updated clinical practice guidelines for the treatment of central disorders of hypersomnolence and narcolepsy specifically highlight new treatment options. Approval for a lower-sodium oxybate formulation that contains 92% less sodium than the standard sodium oxybate for the treatment of narcolepsy and idiopathic hypersomnia adds to the number of medications available for these disorders, allowing for a more tailored management of symptoms.

ESSENTIAL POINTS

Central disorders of hypersomnolence are characterized by excessive daytime sleepiness that impacts daily functions. These disorders can be differentiated by obtaining a detailed clinical sleep history and by a thoughtful interpretation of sleep diagnostic testing. Tailoring treatment approaches to meet the needs of individuals and accounting for medical and psychiatric comorbidities may improve quality of life.

Identification of Sleep Patterns via Clustering of Hypnodensities

Sleep patterns vary widely between individuals. We explore methods for identifying populations exhibiting similar sleep patterns in an automated fashion using polysomnography data. Our novel approach applies unsupervised machine learning algorithms to hypnodensities graphs generated by a pre-trained neural network. In a population of 100 subjects we identify two stable clusters whose characteristics we visualize graphically and through estimates of total sleep time. We also find that the hypnodensity representation of the sleep stages produces more robust clustering results than the same methods applied to traditional hypnograms.

A two-branch trade-off neural network for balanced scoring sleep stages on multiple cohorts

Introduction

Automatic sleep staging is a classification process with severe class imbalance and suffers from instability of scoring stage N1. Decreased accuracy in classifying stage N1 significantly impacts the staging of individuals with sleep disorders. We aim to achieve automatic sleep staging with expert-level performance in both N1 stage and overall scoring.

Methods

A neural network model combines an attention-based convolutional neural network and a classifier with two branches is developed. A transitive training strategy is employed to balance universal feature learning and contextual referencing. Parameter optimization and benchmark comparisons are conducted using a large-scale dataset, followed by evaluation on seven datasets in five cohorts.

Results

The proposed model achieves an accuracy of 88.16%, Cohen's kappa of 0.836, and MF1 score of 0.818 on the SHHS1 test set, also with comparable performance to human scorers in scoring stage N1. Incorporating multiple cohort data improves its performance. Notably, the model maintains high performance when applied to unseen datasets and patients with neurological or psychiatric disorders.

Discussion

The proposed algorithm demonstrates strong performance and generalizablility, and its direct transferability is noteworthy among similar studies on automated sleep staging. It is publicly available, which is conducive to expanding access to sleep-related analysis, especially those associated with neurological or psychiatric disorders.

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.

U-Sleep's resilience to AASM guidelines

AASM guidelines are the result of decades of efforts aiming at standardizing sleep scoring procedure, with the final goal of sharing a worldwide common methodology. The guidelines cover several aspects from the technical/digital specifications, e.g., recommended EEG derivations, to detailed sleep scoring rules accordingly to age. Automated sleep scoring systems have always largely exploited the standards as fundamental guidelines. In this context, deep learning has demonstrated better performance compared to classical machine learning. Our present work shows that a deep learning-based sleep scoring algorithm may not need to fully exploit the clinical knowledge or to strictly adhere to the AASM guidelines. Specifically, we demonstrate that U-Sleep, a state-of-the-art sleep scoring algorithm, can be strong enough to solve the scoring task even using clinically non-recommended or non-conventional derivations, and with no need to exploit information about the chronological age of the subjects. We finally strengthen a well-known finding that using data from multiple data centers always results in a better performing model compared with training on a single cohort. Indeed, we show that this latter statement is still valid even by increasing the size and the heterogeneity of the single data cohort. In all our experiments we used 28528 polysomnography studies from 13 different clinical studies.

Clinical applications of artificial intelligence in sleep medicine: a sleep clinician's perspective

BACKGROUND

The past few years have seen a rapid emergence of artificial intelligence (AI)-enabled technology in the field of sleep medicine. AI refers to the capability of computer systems to perform tasks conventionally considered to require human intelligence, such as speech recognition, decision-making, and visual recognition of patterns and objects. The practice of sleep tracking and measuring physiological signals in sleep is widely practiced. Therefore, sleep monitoring in both the laboratory and ambulatory environments results in the accrual of massive amounts of data that uniquely positions the field of sleep medicine to gain from AI.

METHOD

The purpose of this article is to provide a concise overview of relevant terminology, definitions, and use cases of AI in sleep medicine. This was supplemented by a thorough review of relevant published literature.

RESULTS

Artificial intelligence has several applications in sleep medicine including sleep and respiratory event scoring in the sleep laboratory, diagnosing and managing sleep disorders, and population health. While still in its nascent stage, there are several challenges which preclude AI's generalizability and wide-reaching clinical applications. Overcoming these challenges will help integrate AI seamlessly within sleep medicine and augment clinical practice.

CONCLUSION

Artificial intelligence is a powerful tool in healthcare that may improve patient care, enhance diagnostic abilities, and augment the management of sleep disorders. However, there is a need to regulate and standardize existing machine learning algorithms prior to its inclusion in the sleep clinic.