Abstract
Study Objectives
Sleep stage scoring is performed manually by sleep experts and is prone to subjective interpretation of scoring rules with low intra- and interscorer reliability. Many ...automatic systems rely on few small-scale databases for developing models, and generalizability to new datasets is thus unknown. We investigated a novel deep neural network to assess the generalizability of several large-scale cohorts.
Methods
A deep neural network model was developed using 15,684 polysomnography studies from five different cohorts. We applied four different scenarios: (1) impact of varying timescales in the model; (2) performance of a single cohort on other cohorts of smaller, greater, or equal size relative to the performance of other cohorts on a single cohort; (3) varying the fraction of mixed-cohort training data compared with using single-origin data; and (4) comparing models trained on combinations of data from 2, 3, and 4 cohorts.
Results
Overall classification accuracy improved with increasing fractions of training data (0.25%: 0.782 ± 0.097, 95% CI 0.777–0.787; 100%: 0.869 ± 0.064, 95% CI 0.864–0.872), and with increasing number of data sources (2: 0.788 ± 0.102, 95% CI 0.787–0.790; 3: 0.808 ± 0.092, 95% CI 0.807–0.810; 4: 0.821 ± 0.085, 95% CI 0.819–0.823). Different cohorts show varying levels of generalization to other cohorts.
Conclusions
Automatic sleep stage scoring systems based on deep learning algorithms should consider as much data as possible from as many sources available to ensure proper generalization. Public datasets for benchmarking should be made available for future research.
The aim of this European initiative is to facilitate a structured discussion to improve the next edition of the International Classification of Sleep Disorders (ICSD), particularly the chapter on ...central disorders of hypersomnolence.
The ultimate goal for a sleep disorders classification is to be based on the underlying neurobiological causes of the disorders with clear implication for treatment or, ideally, prevention and or healing. The current ICSD classification, published in 2014, inevitably has important shortcomings, largely reflecting the lack of knowledge about the precise neurobiological mechanisms underlying the majority of sleep disorders we currently delineate. Despite a clear rationale for the present structure, there remain important limitations that make it difficult to apply in routine clinical practice. Moreover, there are indications that the current structure may even prevent us from gaining relevant new knowledge to better understand certain sleep disorders and their neurobiological causes.
We suggest the creation of a new consistent, complaint driven, hierarchical classification for central disorders of hypersomnolence; containing levels of certainty, and giving diagnostic tests, particularly the MSLT, a weighting based on its specificity and sensitivity in the diagnostic context.
We propose and define three diagnostic categories (with levels of certainty):
1/“Narcolepsy” 2/“Idiopathic hypersomnia”, 3/“Idiopathic excessive sleepiness” (with subtypes).
Summary
This European guideline for the diagnosis and treatment of insomnia was developed by a task force of the European Sleep Research Society, with the aim of providing clinical recommendations ...for the management of adult patients with insomnia. The guideline is based on a systematic review of relevant meta‐analyses published till June 2016. The target audience for this guideline includes all clinicians involved in the management of insomnia, and the target patient population includes adults with chronic insomnia disorder. The GRADE (Grading of Recommendations Assessment, Development and Evaluation) system was used to grade the evidence and guide recommendations. The diagnostic procedure for insomnia, and its co‐morbidities, should include a clinical interview consisting of a sleep history (sleep habits, sleep environment, work schedules, circadian factors), the use of sleep questionnaires and sleep diaries, questions about somatic and mental health, a physical examination and additional measures if indicated (i.e. blood tests, electrocardiogram, electroencephalogram; strong recommendation, moderate‐ to high‐quality evidence). Polysomnography can be used to evaluate other sleep disorders if suspected (i.e. periodic limb movement disorder, sleep‐related breathing disorders), in treatment‐resistant insomnia, for professional at‐risk populations and when substantial sleep state misperception is suspected (strong recommendation, high‐quality evidence). Cognitive behavioural therapy for insomnia is recommended as the first‐line treatment for chronic insomnia in adults of any age (strong recommendation, high‐quality evidence). A pharmacological intervention can be offered if cognitive behavioural therapy for insomnia is not sufficiently effective or not available. Benzodiazepines, benzodiazepine receptor agonists and some antidepressants are effective in the short‐term treatment of insomnia (≤4 weeks; weak recommendation, moderate‐quality evidence). Antihistamines, antipsychotics, melatonin and phytotherapeutics are not recommended for insomnia treatment (strong to weak recommendations, low‐ to very‐low‐quality evidence). Light therapy and exercise need to be further evaluated to judge their usefulness in the treatment of insomnia (weak recommendation, low‐quality evidence). Complementary and alternative treatments (e.g. homeopathy, acupuncture) are not recommended for insomnia treatment (weak recommendation, very‐low‐quality evidence).
Sleep disorders affect a large portion of the global population and are strong predictors of morbidity and all-cause mortality. Sleep staging segments a period of sleep into a sequence of phases ...providing the basis for most clinical decisions in sleep medicine. Manual sleep staging is difficult and time-consuming as experts must evaluate hours of polysomnography (PSG) recordings with electroencephalography (EEG) and electrooculography (EOG) data for each patient. Here, we present U-Sleep, a publicly available, ready-to-use deep-learning-based system for automated sleep staging ( sleep.ai.ku.dk ). U-Sleep is a fully convolutional neural network, which was trained and evaluated on PSG recordings from 15,660 participants of 16 clinical studies. It provides accurate segmentations across a wide range of patient cohorts and PSG protocols not considered when building the system. U-Sleep works for arbitrary combinations of typical EEG and EOG channels, and its special deep learning architecture can label sleep stages at shorter intervals than the typical 30 s periods used during training. We show that these labels can provide additional diagnostic information and lead to new ways of analyzing sleep. U-Sleep performs on par with state-of-the-art automatic sleep staging systems on multiple clinical datasets, even if the other systems were built specifically for the particular data. A comparison with consensus-scores from a previously unseen clinic shows that U-Sleep performs as accurately as the best of the human experts. U-Sleep can support the sleep staging workflow of medical experts, which decreases healthcare costs, and can provide highly accurate segmentations when human expertize is lacking.
Narcolepsy type 1 (NT1) is a lifelong disorder of sleep-wake dysregulation defined by clinical symptoms, neurophysiological findings, and low hypocretin levels. Besides a role in sleep, hypocretins ...are also involved in regulation of heart rate and blood pressure. This literature review examines data on the autonomic effects of hypocretin deficiency and evidence about how narcolepsy is associated with multiple cardiovascular risk factors and comorbidities, including cardiovascular disease. An important impact in NT1 is lack of nocturnal blood pressure dipping, which has been associated with mortality in the general population. Hypertension is also prevalent in NT1. Furthermore, disrupted nighttime sleep and excessive daytime sleepiness, which are characteristic of narcolepsy, may increase cardiovascular risk. Patients with narcolepsy also often present with other comorbidities (eg, obesity, diabetes, depression, other sleep disorders) that may contribute to increased cardiovascular risk. Management of multimorbidity in patients with narcolepsy should include regular assessment of cardiovascular health (including ambulatory blood pressure monitoring), mitigation of cardiovascular risk factors (eg, cessation of smoking and other lifestyle changes, sleep hygiene, and pharmacotherapy), and prescription of a regimen of narcolepsy medications that balances symptomatic benefits with cardiovascular safety.
Nocturnal enuresis (NE) is a common condition affecting 5–10% of all 7-year-old children. NE pathophysiology relies on three main factors, abnormal bladder function, excess urine production during ...sleep and the inability to awaken to the signals of a full bladder. The aim of this review is to evaluate the connection between sleep and its structure and the pathophysiology of NE.
NE often occurs early at night and primarily in sleep stage 2 and “deep sleep”. Although sleep stage distribution seems similar between NE and healthy children recent studies indicate differences in sleep microstructure. Several lines of research support the common notion among parents that children with NE are difficult to awaken. Moreover, children with NE and nocturnal polyuria differ in terms of hemodynamics and possibly autonomic activation at night compared to healthy controls and the hypothesis has formed that these changes are attributable to different sleep characteristics. In support of this hypothesis, children with NE often suffer sleep disordered breathing, as well as disturbed sleep due to awakenings and arousals. Periodic limb movements (PLM) have been seen in children with refractory enuresis but the clinical significance remains unclear.
Abstract Benzodiazepines are frequently long-term prescribed for the treatment of patients with severe mental illness. This prescribing practice is problematic because of well-described side effects ...including risk of dependence. We examined the efficacy of prolonged-release melatonin on objective and subjective sleep quality during benzodiazepine discontinuation and whether sleep variables were associated with benzodiazepine withdrawal. Eligible patients included adults with a diagnosis of schizophrenia, schizoaffective disorder, or bipolar disorder and long-term use of benzodiazepines in combination with antipsychotics. All participants gradually tapered the use of benzodiazepines after randomization to add-on treatment with melatonin versus placebo. Here we report a subsample of 23 patients undergoing sleep recordings (one-night polysomnography) and 55 patients participating in subjective sleep quality ratings. Melatonin had no effect on objective sleep efficiency, but significantly improved self-reported sleep quality. Reduced benzodiazepine dosage at the 24-week follow-up was associated with a significantly decreased proportion of stage 2 sleep. These results indicate that prolonged-release melatonin has some efficacy for self-reported sleep quality after gradual benzodiazepine dose reduction, and that benzodiazepine discontinuation is not associated with rebound insomnia in medicated patients with severe mental illness. However, these findings were limited by a small sample size and a low retention rate.
To identify the factual morbidity and mortality of narcolepsy in a controlled design.
National Patient Registry.
All national diagnosed patients (757) with health information at least 3 years prior ...to and after diagnose of narcolepsy.
Randomly selected four citizens (3,013) matched for age, sex, and socioeconomic status from the Danish Civil Registration System Statistics.
Increased morbidity prior to narcolepsy diagnosis included (odds ratio, 95% confidence interval):- diseases of the endocrine, nutritional, and metabolic systems (2.10, 1.32-3.33); nervous system (5.27, 3.65-7.60); musculoskeletal system (1.59, 1.23-2.05); and other abnormal symptoms and laboratory findings (1.66, 1.25-2.22). After the diagnosis, narcolepsy patients experienced diseases of the endocrine, nutritional, and metabolic (2.31, 1.51-3.54), nervous (9.19, 6.80-12.41), musculoskeletal (1.70, 1.28-2.26), eye (1.67, 1.03-2.71), and respiratory systems (1.84, 1.21-2.81). Specific diagnoses were diabetes (2.4, 1,2-4.7, P < 0.01), obesity (13.4, 3.1-57.6, P < 0.001), sleep apnea (19.2, 7.7-48.3, P < 0.001), other sleep disorders (78.5, 11.8-523.3, P < 0.001), chronic obstructive pulmonary disease (2.8, 1.4-5.8, P < 0.01), lower back pain (2.5, 1.4-4.2, P < 0.001), arthrosis/arthritis (2.5, 1.3-4.8, P < 0.01), observation of neurological diseases (3.5, 1.9-6.5, P < 0.001), observation of other diseases (1.7, 1.2-2.5, P < 0.01), and rehabilitation (5.0, 1.5-16.5, P < 0.005). There was a trend towards greater mortality in narcolepsy (P = 0.07).
Patients with narcolepsy present higher morbidity several years prior to diagnose and even higher thereafter. The mortality rate due to narcolepsy was slightly but not significantly higher.
Narcolepsy Type 1 (NT1) is a neurological sleep disorder, characterized by the loss of hypocretin/orexin signaling in the brain. Genetic, epidemiological and experimental data support the hypothesis ...that NT1 is a T-cell-mediated autoimmune disease targeting the hypocretin producing neurons. While autoreactive CD4
T cells have been detected in patients, CD8
T cells have only been examined to a minor extent. Here we detect CD8
T cells specific toward narcolepsy-relevant peptides presented primarily by NT1-associated HLA types in the blood of 20 patients with NT1 as well as in 52 healthy controls, using peptide-MHC-I multimers labeled with DNA barcodes. In healthy controls carrying the disease-predisposing HLA-DQB1*06:02 allele, the frequency of autoreactive CD8
T cells was lower as compared with both NT1 patients and HLA-DQB1*06:02-negative healthy individuals. These findings suggest that a certain level of CD8
T-cell reactivity combined with HLA-DQB1*06:02 expression is important for NT1 development.
Summary Narcolepsy is a sleep disorder characterised by loss of hypothalamic hypocretin (orexin) neurons. The prevalence of narcolepsy is about 30 per 100 000 people, and typical age at onset is ...12–16 years. Narcolepsy is strongly associated with the HLA-DQB1*06:02 genotype, and has been thought of as an immune-mediated disease. Other risk genes, such as T-cell-receptor α chain and purinergic receptor subtype 2Y11, are also implicated. Interest in narcolepsy has increased since the epidemiological observations that H1N1 infection and vaccination are potential triggering factors, and an increase in the incidence of narcolepsy after the pandemic AS03 adjuvanted H1N1 vaccination in 2010 from Sweden and Finland supports the immune-mediated pathogenesis. Epidemiological observations from studies in China also suggest a role for H1N1 virus infections as a trigger for narcolepsy. Although the pathological mechanisms are unknown, an H1N1 virus-derived antigen might be the trigger.