Explore the vast range of titles available.

Sleep stage classification plays a pivotal role in effective diagnosis and treatment of sleep related disorders. Traditionally, sleep scoring is done manually by trained sleep scorers. The analysis of electroencephalogram (EEG) signals recorded during sleep by clinicians is tedious, time-consuming and prone to human errors. Therefore, it is clinically important to score sleep stages using machine learning techniques to get accurate diagnosis. Several studies have been proposed for automated detection of sleep stages. However, these studies have employed only healthy normal subjects (good sleepers). The proposed study focuses on the automated sleep-stage scoring of subjects suffering from seven different kind of sleep disorders such as insomnia, bruxism, narcolepsy, nocturnal frontal lobe epilepsy (NFLE), periodic leg movement (PLM), rapid eye movement (REM) behavioural disorder and sleep-disordered breathing as well as normal subjects. The open source physionet’s cyclic alternating pattern (CAP) sleep database is used for this study. The EEG epochs are decomposed into sub-bands using a new class of optimized wavelet filters. Two EEG channels, namely F4-C4 and C4-A1, combined are used for this work as they can provide more insights into the changes in EEG signals during sleep. The norm features are computed from six sub-bands coefficients of optimal wavelet filter bank and fed to various supervised machine learning classifiers. We have obtained the highest classification performance using an ensemble of bagged tree (EBT) classifier with 10-fold cross validation. The CAP database comprising of 80 subjects is divided into ten different subsets and then ten different sleep-stage scoring tasks are performed. Since, the CAP database is unbalanced with different duration of sleep stages, the balanced dataset also has been created using over-sampling and under-sampling techniques. The highest average accuracy of 85.3% and Cohen’s Kappa coefficient of 0.786 and accuracy of 92.8% and Cohen’s Kappa coefficient of 0.915 are obtained for unbalanced and balanced databases, respectively. The proposed method can reliably classify the sleep stages using single or dual channel EEG epochs of 30 s duration instead of using multimodal polysomnography (PSG) which are generally used for sleep-stage scoring. Our developed automated system is ready to be tested with more sleep EEG data and can be employed in various sleep laboratories to evaluate the quality of sleep in various sleep disorder patients and normal subjects.

Sleep is vital for one’s general well-being, but it is often neglected, which has led to an increase in sleep disorders worldwide. Indicators of sleep disorders, such as sleep interruptions, extreme daytime drowsiness, or snoring, can be detected with sleep analysis. However, sleep analysis relies on visuals conducted by experts, and is susceptible to inter- and intra-observer variabilities. One way to overcome these limitations is to support experts with a programmed diagnostic tool (PDT) based on artificial intelligence for timely detection of sleep disturbances. Artificial intelligence technology, such as deep learning (DL), ensures that data are fully utilized with low to no information loss during training. This paper provides a comprehensive review of 36 studies, published between March 2013 and August 2020, which employed DL models to analyze overnight polysomnogram (PSG) recordings for the classification of sleep stages. Our analysis shows that more than half of the studies employed convolutional neural networks (CNNs) on electroencephalography (EEG) recordings for sleep stage classification and achieved high performance. Our study also underscores that CNN models, particularly one-dimensional CNN models, are advantageous in yielding higher accuracies for classification. More importantly, we noticed that EEG alone is not sufficient to achieve robust classification results. Future automated detection systems should consider other PSG recordings, such as electroencephalogram (EEG), electrooculogram (EOG), and electromyogram (EMG) signals, along with input from human experts, to achieve the required sleep stage classification robustness. Hence, for DL methods to be fully realized as a practical PDT for sleep stage scoring in clinical applications, inclusion of other PSG recordings, besides EEG recordings, is necessary. In this respect, our report includes methods published in the last decade, underscoring the use of DL models with other PSG recordings, for scoring of sleep stages.

BackgroundThe 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.MethodThe 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.ResultsArtificial 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.ConclusionArtificial 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.

PurposeThe Epworth sleepiness scale (ESS) is a widely used tool which has been validated as a measure of sleepiness. However, the scores within individual patients referred for clinical sleep services vary considerably which may limit the clinical use of the ESS. We sought to determine the test-retest reliability of the ESS if scores were classified as either normal or sleepy.MethodsWe measured the ESS in patients presenting to our sleep center at a clinical visit and again when a sleep study was done. Demographic and clinical information was extracted from the electronic medical record.ResultsAverage ESS scores were similar on 2 administrations, mean (SD) of 9.8 (5.4) and 10.2 (6.2). Bland-Altman analysis showed upper and lower limits of agreement of 7.5 and − 6.7, respectively. No demographic or clinical variables were identified which contributed to the intra-individual variability. Of the patients who presented with an initial ESS < 11, 80% had a second ESS < 11. Of the patients who presented with an initial ESS ≥ 11, 89% had a second ESS ≥ 11. Cohen’s kappa for the two administrations of the ESS was 0.67 (95% CI of 0.51–0.83). Using previously published reports, we calculated Cohen’s kappa for polysomnographic determination of the apnea-hypopnea index (AHI) with values ranging from 0.26 to 0.69.ConclusionsIndividual ESS scores varied considerably within individual patients, but with classification into either normal or sleepy, the test-retest reliability was substantial and in line with other clinical measures including polysomnographic determination of the AHI.

Human life necessitates high-quality sleep. However, humans suffer from a lower quality of life because of sleep disorders. The identification of sleep stages is necessary to predict the quality of sleep. Manual sleep-stage scoring is frequently conducted through sleep experts’ visually evaluations of a patient’s neurophysiological data, gathered in sleep laboratories. Manually scoring sleep is a tough, time-intensive, tiresome, and highly subjective activity. Hence, the need of creating automatic sleep-stage classification has risen due to the limitations imposed by manual sleep-stage scoring methods. In this study, a novel machine learning model is developed using dual-channel unipolar electroencephalogram (EEG), chin electromyogram (EMG), and dual-channel electrooculgram (EOG) signals. Using an optimum orthogonal filter bank, sub-bands are obtained by decomposing 30 s epochs of signals. Tsallis entropies are then calculated from the coefficients of these sub-bands. Then, these features are fed an ensemble bagged tree (EBT) classifier for automated sleep classification. We developed our automated sleep classification model using the Sleep Heart Health Study (SHHS) database, which contains two parts, SHHS-1 and SHHS-2, containing more than 8455 subjects with more than 75,000 h of recordings. The proposed model separated three classes if sleep: rapid eye movement (REM), non-REM, and wake, with a classification accuracy of 90.70% and 91.80% using the SHHS-1 and SHHS-2 datasets, respectively. For the five-class problem, the model produces a classification accuracy of 84.3% and 86.3%, corresponding to the SHHS-1 and SHHS-2 databases, respectively, to classify wake, N1, N2, N3, and REM sleep stages. The model acquired Cohen’s kappa (κ) coefficients as 0.838 with SHHS-1 and 0.86 with SHHS-2 for the three-class classification problem. Similarly, the model achieved Cohen’s κ of 0.7746 for SHHS-1 and 0.8007 for SHHS-2 in five-class classification tasks. The model proposed in this study has achieved better performance than the best existing methods. Moreover, the model that has been proposed has been developed to classify sleep stages for both good sleepers as well as patients suffering from sleep disorders. Thus, the proposed wavelet Tsallis entropy-based model is robust and accurate and may help clinicians to comprehend and interpret sleep stages efficiently.

Values for normative REM sleep without atonia (RSWA) remain unclear. Older age and male sex are associated with greater RSWA, and isolated elevated RSWA has been reported. We aimed to describe normative RSWA and characterize isolated RSWA frequency in adults without REM sleep behavior disorder (RBD). We visually quantified phasic, \"any,\" and tonic RSWA in the submentalis (SM) and anterior tibialis (AT) muscles, and the automated Ferri REM Atonia Index during polysomnography in adults without RBD aged 21-88. We calculated RSWA percentiles across age and sex deciles and compared RSWA in older (≥ 65) versus younger (<65) men and women. Isolated RSWA (exceeding diagnostic RBD cutoffs, or >95th percentile) frequency was also determined. Overall, 95th percentile RSWA percentages were SM phasic, any, tonic = 8.6%, 9.1%, 0.99%; AT phasic and \"any\" = 17.0%; combined SM/AT phasic, \"any\" = 22.3%, 25.5%; and RAI = 0.85. Most phasic RSWA burst durations were ≤1.0 s (85th percentiles: SM = 1.07, AT = 0.86 seconds). Older men had significantly higher AT RSWA than older women and younger patients (all p < 0.04). Twenty-nine (25%, 18 men) had RSWA exceeding the cohort 95th percentile, while 17 (14%, 12 men) fulfilled diagnostic cutoffs for phasic or automated RBD RSWA thresholds. RSWA levels are highest in older men, mirroring the demographic characteristics of RBD, suggesting that older men frequently have altered REM sleep atonia control. These data establish normative adult RSWA values and thresholds for determination of isolated RSWA elevation, potentially aiding RBD diagnosis and discussions concerning incidental RSWA in clinical sleep medicine practice.

Home portable monitor testing is increasingly being used to diagnose patients with obstructive sleep apnea (OSA) and to initiate them on continuous positive airway pressure (CPAP) treatment. To compare functional outcome and treatment adherence in patients who receive ambulatory versus in-laboratory testing for OSA. Veterans with suspected OSA were randomized to either home testing or standard in-laboratory testing. Home testing consisted of a type 3 portable monitor recording followed by at least three nights using an automatically adjusting positive airway pressure apparatus. Participants diagnosed with OSA were treated with CPAP for 3 months. We measured the change in Functional Outcomes of Sleep Questionnaire score, with an a priori noninferiority delta of -1, and the mean daily hours of objectively measured CPAP adherence, with an a priori noninferiority delta of -0.75 hour/day. Of the 296 subjects enrolled, 260 (88%) were diagnosed with OSA, and 213 (75%) were initiated on CPAP. Mean ± SD functional outcome score improved 1.74 ± 2.81 in the home group (P < 0.001) and 1.85 ± 2.46 in the in-laboratory group (P < 0.0001). The lower bound of the one-sided 95% noninferiority confidence interval was -0.54. Mean ± SD hours of daily CPAP adherence were 3.5 ± 2.5 hours/day in the home group and 2.9 ± 2.3 hours/day in the in-laboratory group (P = 0.08). The lower bound of the one-sided 95% noninferiority confidence interval was 0.03. Functional outcome and treatment adherence in patients evaluated according to a home testing algorithm is not clinically inferior to that in patients receiving standard in-laboratory polysomnography.

Sleep is highly essential for maintaining metabolism of the body and mental balance for increased productivity and concentration. Often, sleep is analyzed using macrostructure sleep stages which alone cannot provide information about the functional structure and stability of sleep. The cyclic alternating pattern (CAP) is a physiological recurring electroencephalogram (EEG) activity occurring in the brain during sleep and captures microstructure of the sleep and can be used to identify sleep instability. The CAP can also be associated with various sleep-related pathologies, and can be useful in identifying various sleep disorders. Conventionally, sleep is analyzed using polysomnogram (PSG) in various sleep laboratories by trained physicians and medical practitioners. However, PSG-based manual sleep analysis by trained medical practitioners is onerous, tedious and unfavourable for patients. Hence, a computerized, simple and patient convenient system is highly desirable for monitoring and analysis of sleep. In this study, we have proposed a system for automated identification of CAP phase-A and phase-B. To accomplish the task, we have utilized the openly accessible CAP sleep database. The study is performed using two single-channel EEG modalities and their combination. The model is developed using EEG signals of healthy subjects as well as patients suffering from six different sleep disorders namely nocturnal frontal lobe epilepsy (NFLE), sleep-disordered breathing (SDB), narcolepsy, periodic leg movement disorder (PLM), insomnia and rapid eye movement behavior disorder (RBD) subjects. An optimal orthogonal wavelet filter bank is used to perform the wavelet decomposition and subsequently, entropy and Hjorth parameters are extracted from the decomposed coefficients. The extracted features have been applied to different machine learning algorithms. The best performance is obtained using ensemble of bagged tress (EBagT) classifier. The proposed method has obtained the average classification accuracy of 84%, 83%, 81%, 78%, 77%, 76% and 72% for NFLE, healthy, SDB, narcolepsy, PLM, insomnia and RBD subjects, respectively in discriminating phases A and B using a balanced database. Our developed model yielded an average accuracy of 78% when all 77 subjects including healthy and sleep disordered patients are considered. Our proposed system can assist the sleep specialists in an automated and efficient analysis of sleep using sleep microstructure.

Sleep is crucial for human health. Automatic sleep stage classification based on polysomnogram (PSG) is meaningful for the diagnosis of sleep disorders, which has attracted extensive attention in recent years. Most existing methods could not fully consider the different transitions of sleep stages and fit the visual inspection of sleep experts simultaneously. To this end, we propose a temporal multi-scale hybrid attention network, namely TMHAN, to automatically achieve sleep staging. The temporal multi-scale mechanism incorporates short-term abrupt and long-term periodic transitions of the successive PSG epochs. Furthermore, the hybrid attention mechanism includes 1-D local attention, 2-D global attention, and 2-D contextual sparse multi-head self-attention for three kinds of sequence-level representations. The concatenated representation is subsequently fed into a softmax layer to train an end-to-end model. Experimental results on two benchmark sleep datasets show that TMHAN obtains the best performance compared with several baselines, demonstrating the effectiveness of our model. In general, our work not only provides good classification performance, but also fits the actual sleep staging processes, which makes contribution for the combination of deep learning and sleep medicine.

PurposeMost continuous positive airway pressure (CPAP) machines have built-in manufacturer-specific proprietary algorithms for automatic respiratory event detection (AED) based on very specific respiratory events scoring criteria. With regards to the accuracy of these data from CPAP machines, evidence from the literature seems conflicting, which formed the basis for this meta-analysis.MethodsA meta-analysis was performed on studies that reported Bland-Altman analysis data on agreement (mean bias and limits of agreement [LoA]) of CPAP-determined apnea-hypopnea index (AHI) at therapeutic pressures (AHIFLOW) with that determined from simultaneously conducted polysomnograms (AHIPSG).ResultsIn six studies, ResMed CPAPs were used, and in another six studies, Respironics CPAPs were used, while only one study used Fisher & Paykel (F&P) CPAPs. The pooled mean AHI bias from ResMed CPAP studies was − 1.01 with pooled LoAs from − 3.55 to 1.54 (I2 = 17.5%), and from Respironics CPAP studies, pooled mean AHI bias was − 0.59 with pooled LoAs from − 3.22 to 2.05 (I2 = 0%). Pooled percentage errors (corresponding to LoAs) from four ResMed CPAP studies, four Respironics CPAP studies, and the F&P CPAP study were 73%, 59%, and 112%, respectively. A review of the literature for this meta-analysis also revealed lack of uniformity not only in the CPAP manufacturers’ respiratory events scoring criteria but also in that used for PSGs across the studies analyzed.ConclusionsEven though the pooled results of mean AHI bias suggest good clinical agreement between AHIPSG and AHIFLOW, percentage errors calculated in this meta-analysis indicate the possibility of a significant degree of imprecision in the estimation of AHIFLOW by CPAP machines.