Neural network analysis of sleep stages enables efficient diagnosis of narcolepsy.
Ontology highlight
ABSTRACT:
SUBMITTER: Stephansen JB
PROVIDER: S-EPMC6283836 | biostudies-literature | 2018 Dec
REPOSITORIES: biostudies-literature
Publications
Neural network analysis of sleep stages enables efficient diagnosis of narcolepsy.
Stephansen Jens B JB Olesen Alexander N AN Olsen Mads M Ambati Aditya A Leary Eileen B EB Moore Hyatt E HE Carrillo Oscar O Lin Ling L Han Fang F Yan Han H Sun Yun L YL Dauvilliers Yves Y Scholz Sabine S Barateau Lucie L Hogl Birgit B Stefani Ambra A Hong Seung Chul SC Kim Tae Won TW Pizza Fabio F Plazzi Giuseppe G Vandi Stefano S Antelmi Elena E Perrin Dimitri D Kuna Samuel T ST Schweitzer Paula K PK Kushida Clete C Peppard Paul E PE Sorensen Helge B D HBD Jennum Poul P Mignot Emmanuel E
Nature communications 20181206 1
Analysis of sleep for the diagnosis of sleep disorders such as Type-1 Narcolepsy (T1N) currently requires visual inspection of polysomnography records by trained scoring technicians. Here, we used neural networks in approximately 3,000 normal and abnormal sleep recordings to automate sleep stage scoring, producing a hypnodensity graph-a probability distribution conveying more information than classical hypnograms. Accuracy of sleep stage scoring was validated in 70 subjects assessed by six score ...[more]
Similar Datasets
Project description:Obstructive sleep apnea (OSA) is a prevalent respiratory condition in children and is characterized by partial or complete obstruction of the upper airway during sleep. The respiratory events in OSA induce transient alterations of the cardiovascular system that ultimately can lead to increased cardiovascular risk in affected children. Therefore, a timely and accurate diagnosis is of utmost importance. However, polysomnography (PSG), the standard diagnostic test for pediatric OSA, is complex, uncomfortable, costly, and relatively inaccessible, particularly in low-resource environments, thereby resulting in substantial underdiagnosis. Here, we propose a novel deep-learning approach to simplify the diagnosis of pediatric OSA using raw electrocardiogram tracing (ECG). Specifically, a new convolutional neural network (CNN)-based regression model was implemented to automatically predict pediatric OSA by estimating its severity based on the apnea-hypopnea index (AHI) and deriving 4 OSA severity categories. For this purpose, overnight ECGs from 1,610 PSG recordings obtained from the Childhood Adenotonsillectomy Trial (CHAT) database were used. The database was randomly divided into approximately 60%, 20%, and 20% for training, validation, and testing, respectively. The diagnostic performance of the proposed CNN model largely outperformed the most accurate previous algorithms that relied on ECG-derived features (4-class Cohen's kappa coefficient of 0.373 versus 0.166). Specifically, for AHI cutoff values of 1, 5, and 10 events/hour, the binary classification achieved sensitivities of 84.19%, 76.67%, and 53.66%; specificities of 46.15%, 91.39%, and 98.06%; and accuracies of 75.92%, 86.96%, and 91.97%, respectively. Therefore, pediatric OSA can be readily identified by our proposed CNN model, which provides a simpler, faster, and more accessible diagnostic test that can be implemented in clinical practice.
| S-EPMC11556022 | biostudies-literature
Project description:Automatic sleep stage scoring based on deep neural networks has come into focus of sleep researchers and physicians, as a reliable method able to objectively classify sleep stages would save human resources and simplify clinical routines. Due to novel open-source software libraries for machine learning, in combination with enormous recent progress in hardware development, a paradigm shift in the field of sleep research towards automatic diagnostics might be imminent. We argue that modern machine learning techniques are not just a tool to perform automatic sleep stage classification, but are also a creative approach to find hidden properties of sleep physiology. We have already developed and established algorithms to visualize and cluster EEG data, facilitating first assessments on sleep health in terms of sleep-apnea and consequently reduced daytime vigilance. In the following study, we further analyze cortical activity during sleep by determining the probabilities of momentary sleep stages, represented as hypnodensity graphs and then computing vectorial cross-correlations of different EEG channels. We can show that this measure serves to estimate the period length of sleep cycles and thus can help to find disturbances due to pathological conditions.
| S-EPMC7973384 | biostudies-literature
Project description:IntroductionAutomatic 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.MethodsA 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.ResultsThe 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.DiscussionThe 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.
| S-EPMC10326279 | biostudies-literature
Project description:BackgroundMost existing automated sleep staging methods rely on multimodal data, and scoring a specific epoch requires not only the current epoch but also a sequence of consecutive epochs that precede and follow the epoch.ObjectiveWe proposed and tested a convolutional neural network called SleepInceptionNet, which allows sleep classification of a single epoch using a single-channel electroencephalogram (EEG).MethodsSleepInceptionNet is based on our systematic evaluation of the effects of different EEG preprocessing methods, EEG channels, and convolutional neural networks on automatic sleep staging performance. The evaluation was performed using polysomnography data of 883 participants (937,975 thirty-second epochs). Raw data of individual EEG channels (ie, frontal, central, and occipital) and 3 specific transformations of the data, including power spectral density, continuous wavelet transform, and short-time Fourier transform, were used separately as the inputs of the convolutional neural network models. To classify sleep stages, 7 sequential deep neural networks were tested for the 1D data (ie, raw EEG and power spectral density), and 16 image classifier convolutional neural networks were tested for the 2D data (ie, continuous wavelet transform and short-time Fourier transform time-frequency images).ResultsThe best model, SleepInceptionNet, which uses time-frequency images developed by the continuous wavelet transform method from central single-channel EEG data as input to the InceptionV3 image classifier algorithm, achieved a Cohen κ agreement of 0.705 (SD 0.077) in reference to the gold standard polysomnography.ConclusionsSleepInceptionNet may allow real-time automated sleep staging in free-living conditions using a single-channel EEG, which may be useful for on-demand intervention or treatment during specific sleep stages.
| S-EPMC9960035 | biostudies-literature
Project description:Fundamental principles underlying computation in multi-scale brain networks illustrate how multiple brain areas and their coordinated activity give rise to complex cognitive functions. Whereas brain activity has been studied at the micro- to meso-scale to reveal the connections between the dynamical patterns and the behaviors, investigations of neural population dynamics are mainly limited to single-scale analysis. Our goal is to develop a cross-scale dynamical model for the collective activity of neuronal populations. Here we introduce a bio-inspired deep learning approach, termed NeuroBondGraph Network (NBGNet), to capture cross-scale dynamics that can infer and map the neural data from multiple scales. Our model not only exhibits more than an 11-fold improvement in reconstruction accuracy, but also predicts synchronous neural activity and preserves correlated low-dimensional latent dynamics. We also show that the NBGNet robustly predicts held-out data across a long time scale (2 weeks) without retraining. We further validate the effective connectivity defined from our model by demonstrating that neural connectivity during motor behaviour agrees with the established neuroanatomical hierarchy of motor control in the literature. The NBGNet approach opens the door to revealing a comprehensive understanding of brain computation, where network mechanisms of multi-scale activity are critical.
| S-EPMC10907713 | biostudies-literature
Project description:Randomized controlled trials (RCTs) that compared the safety and efficacy of medical treatments for narcolepsy were analyzed using network meta-analysis. The RCTs in narcolepsy were searched. Network meta-analysis compared efficacy and safety of multiple treatments, multi-arm studies, and multi-criteria treatment decisions, based on a random model that assumed heterogeneity between studies, with corrections for multi-arm studies. Fourteen RCTs, three drug treatments, and six doses were identified: sodium oxybate (6 and 9 g/d), modafinil (between 200 and 400 mg/d), and pitolisant (up to 20 and up to 40 mg/d). Significant heterogeneity (>50%) between studies was found in 12/14 studies for almost all endpoints, but between-design consistency was present. For ESS and MWT, sodium oxybate 9 g/d, modafinil, and pitolisant up to 40 mg/d had similar efficacy. Pitolisant 40 mg/d and sodium oxybate 9 g/d in two nightly doses had similar efficacy in reducing cataplexy. A good safety profile characterized by a TEAE incidence risk ratio (IRR) <1.5 was found for all the compared treatments, except for sodium oxybate 9 g/d. Although no significant difference was found, Pitolisant 40 mg was shown with the best P scores for the benefit/risk (BR) ratio. Modafinil (200-400 mg/d), sodium oxybate 9 g/d, and pitolisant up to 40 mg/d had similar efficacy in reducing excessive day time sleepiness. Only sodium oxybate 9 g/d and pitolisant up to 40 mg/d were shown with a comparable beneficial effect on cataplexy. Overall, Pitolisant was found with the best P score on the BR ratio. PROSPERO 2017 CRD42017054686. Efficacy, safety, and benefit-risk comparison of alternative treatments in narcolepsy: a network multiple comparisons of treatment meta-analysis. http://www.crd.york.ac.uk/PROSPERO/display_record.php?ID=CRD42017054686.
| S-EPMC6289237 | biostudies-literature
Project description:STUDY OBJECTIVES:Portable devices for home sleep apnea testing are often limited by their inability to discriminate sleep/wake status, possibly resulting in underestimations. Tracheal sound (TS), which can be visualized as a spectrogram, carries information about apnea/hypopnea and sleep/wake status. We hypothesized that image analysis of all-night TS recordings by a deep neural network (DNN) would be capable of detecting breathing events and classifying sleep/wake status. The aim of this study is to develop a DNN-based system for sleep apnea testing and validate it using a large sampling of polysomnography (PSG) data. METHODS:PSG examinations for the evaluation of sleep-disordered breathing (SDB) were performed for 1,852 patients: 1,548 PSG records were used to develop the system, and the remaining 304 records were used for validation. TS spectrogram images were obtained every 60 seconds and labeled with the PSG scoring results (breathing event and sleep/wake status), then introduced to DNN learning. Two different DNNs were trained for breathing status and sleep/wake status, respectively. RESULTS:A DNN with convolutional layers showed the best performance for discriminating breathing status. The same DNN structure was trained for sleep/wake discrimination. In the validation study, the DNN analysis was capable of discriminating the sleep/wake status with reasonable accuracy. The diagnostic sensitivity, specificity, and area under the receiver operating characteristic curves for diagnosis of SDB with apnea-hypopnea index of > 5, 15, and 30 were 0.98, 0.76, and 0.99; 0.97, 0.90, and 0.99; and 0.92, 0.94, and 0.98, respectively. CONCLUSIONS:The developed system using the TS DNN analysis has a good performance for SDB testing. CITATION:Nakano H, Furukawa T, Tanigawa T. Tracheal sound analysis using a deep neural network to detect sleep apnea. J Clin Sleep Med. 2019;15(8): 1125-1133.
| S-EPMC6707047 | biostudies-literature
Project description:Study objectivesTo evaluate the reliability of nocturnal sleep dynamics in the differential diagnosis of central disorders of hypersomnolence.DesignCross-sectional.SettingSleep laboratory.PatientsOne hundred seventy-five patients with hypocretin-deficient narcolepsy type 1 (NT1, n = 79), narcolepsy type 2 (NT2, n = 22), idiopathic hypersomnia (IH, n = 22), and "subjective" hypersomnolence (sHS, n = 52).InterventionsNone.MethodsPolysomnographic (PSG) work-up included 48 h of continuous PSG recording. From nocturnal PSG conventional sleep macrostructure, occurrence of sleep onset rapid eye movement period (SOREMP), sleep stages distribution, and sleep stage transitions were calculated. Patient groups were compared, and receiver operating characteristic (ROC) curve analysis was used to test the diagnostic utility of nocturnal PSG data to identify NT1.ResultsSleep macrostructure was substantially stable in the 2 nights of each diagnostic group. NT1 and NT2 patients had lower latency to rapid eye movement (REM) sleep, and NT1 patients showed the highest number of awakenings, sleep stage transitions, and more time spent in N1 sleep, as well as most SOREMPs at daytime PSG and at multiple sleep latency test (MSLT) than all other groups. ROC curve analysis showed that nocturnal SOREMP (area under the curve of 0.724 ± 0.041, P < 0.0001), percent of total sleep time spent in N1 (0.896 ± 0.023, P < 0.0001), and the wakefulness-sleep transition index (0.796 ± 0.034, P < 0.0001) had a good sensitivity and specificity profile to identify NT1 sleep, especially when used in combination (0.903 ± 0.023, P < 0.0001), similarly to SOREMP number at continuous daytime PSG (0.899 ± 0.026, P < 0.0001) and at MSLT (0.956 ± 0.015, P < 0.0001).ConclusionsSleep macrostructure (i.e. SOREMP, N1 timing) including stage transitions reliably identifies hypocretin-deficient narcolepsy type 1 among central disorders of hypersomnolence.
| S-EPMC4507733 | biostudies-literature
Project description:A fundamental goal of motor learning is to establish the neural patterns that produce a desired behavioral outcome. It remains unclear how and when the nervous system solves this 'credit assignment' problem. Using neuroprosthetic learning, in which we could control the causal relationship between neurons and behavior, we found that sleep-dependent processing was required for credit assignment and the establishment of task-related functional connectivity reflecting the casual neuron-behavior relationship. Notably, we observed a strong link between the microstructure of sleep reactivations and credit assignment, with downscaling of non-causal activity. Decoupling of spiking to slow oscillations using optogenetic methods eliminated rescaling. Thus, our results suggest that coordinated firing during sleep is essential for establishing sparse activation patterns that reflect the causal neuron-behavior relationship.
| S-EPMC5808917 | biostudies-literature
Project description:Theories of efficient coding propose that the auditory system is optimized for the statistical structure of natural sounds, yet the transformations underlying optimal acoustic representations are not well understood. Using a database of natural sounds including human speech and a physiologically-inspired auditory model, we explore the consequences of peripheral (cochlear) and mid-level (auditory midbrain) filter tuning transformations on the representation of natural sound spectra and modulation statistics. Whereas Fourier-based sound decompositions have constant time-frequency resolution at all frequencies, cochlear and auditory midbrain filters bandwidths increase proportional to the filter center frequency. This form of bandwidth scaling produces a systematic decrease in spectral resolution and increase in temporal resolution with increasing frequency. Here we demonstrate that cochlear bandwidth scaling produces a frequency-dependent gain that counteracts the tendency of natural sound power to decrease with frequency, resulting in a whitened output representation. Similarly, bandwidth scaling in mid-level auditory filters further enhances the representation of natural sounds by producing a whitened modulation power spectrum (MPS) with higher modulation entropy than both the cochlear outputs and the conventional Fourier MPS. These findings suggest that the tuning characteristics of the peripheral and mid-level auditory system together produce a whitened output representation in three dimensions (frequency, temporal and spectral modulation) that reduces redundancies and allows for a more efficient use of neural resources. This hierarchical multi-stage tuning strategy is thus likely optimized to extract available information and may underlies perceptual sensitivity to natural sounds.
| S-EPMC9970106 | biostudies-literature