Kleine-Levin syndrome is associated with birth difficulties and genetic variants in the TRANK1 gene loci.

Kleine-Levin syndrome (KLS) is a rare disorder characterized by severe episodic hypersomnia, with cognitive impairment accompanied by apathy or disinhibition. Pathophysiology is unknown, although imaging studies indicate decreased activity in hypothalamic/thalamic areas during episodes. Familial occurrence is increased, and risk is associated with reports of a difficult birth. We conducted a worldwide case-control genome-wide association study in 673 KLS cases collected over 14 y, and ethnically matched 15,341 control individuals. We found a strong genome-wide significant association (rs71947865, Odds Ratio [OR] = 1.48, P = 8.6 × 10-9) within the 3'region of TRANK1 gene locus, previously associated with bipolar disorder and schizophrenia. Strikingly, KLS cases with rs71947865 variant had significantly increased reports of a difficult birth. As perinatal outcomes have dramatically improved over the last 40 y, we further stratified our sample by birth years and found that recent cases had a significantly reduced rs71947865 association. While the rs71947865 association did not replicate in the entire follow-up sample of 171 KLS cases, rs71947865 was significantly associated with KLS in the subset follow-up sample of 59 KLS cases who reported birth difficulties (OR = 1.54, P = 0.01). Genetic liability of KLS as explained by polygenic risk scores was increased (pseudo R2 = 0.15; P < 2.0 × 10-22 at P = 0.5 threshold) in the follow-up sample. Pathway analysis of genetic associations identified enrichment of circadian regulation pathway genes in KLS cases. Our results suggest links between KLS, circadian regulation, and bipolar disorder, and indicate that the TRANK1 polymorphisms in conjunction with reported birth difficulties may predispose to KLS.

Comorbid neurotrauma increases neurodegenerative-relevant cognitive, motor, and autonomic dysfunction in patients with rapid eye movement sleep behavior disorder: a substudy of the North American Prodromal Synucleinopathy Consortium.

STUDY OBJECTIVES: Rapid eye movement sleep behavior disorder (RBD) is strongly associated with phenoconversion to an overt synucleinopathy, e.g. Parkinson's disease (PD), Lewy body dementia, and related disorders. Comorbid traumatic brain injury (TBI) and posttraumatic stress disorder (PTSD)-henceforth "neurotrauma" (NT)-increase the odds of RBD by ~2.5-fold and are associated with an increased rate of service-connected PD in Veterans. Thus, RBD and NT are both independently associated with PD; however, it is unclear how NT influences neurological function in patients with RBD. METHODS: Participants ≥18 years with overnight polysomnogram-confirmed RBD were enrolled between 8/2018 to 4/2021 through the North American Prodromal Synucleinopathy Consortium. Standardized assessments for RBD, TBI, and PTSD history, as well as cognitive, motor, sensory, and autonomic function, were completed. This cross-sectional analysis compared cases (n = 24; RBD + NT) to controls (n = 96; RBD), matched for age (~60 years), sex (15% female), and years of education (~15 years). RESULTS: RBD + NT reported earlier RBD symptom onset (37.5 ±â€…11.9 vs. 52.2 ±â€…15.1 years of age) and a more severe RBD phenotype. Similarly, RBD + NT reported more severe anxiety and depression, greater frequency of hypertension, and significantly worse cognitive, motor, and autonomic function compared to RBD. No differences in olfaction or color vision were observed. CONCLUSIONS: This cross-sectional, matched case:control study shows individuals with RBD + NT have significantly worse neurological measures related to common features of an overt synucleinopathy. Confirmatory longitudinal studies are ongoing; however, these results suggest RBD + NT may be associated with more advanced neurological symptoms related to an evolving neurodegenerative process.

Validation of the RBD Symptom Severity Scale in the North American Prodromal Synucleinopathy Consortium.

BACKGROUND AND OBJECTIVES: REM sleep behavior disorder (RBD) is a parasomnia characterized by dream enactment. The International RBD Study Group developed the RBD Symptom Severity Scale (RBDSSS) to assess symptom severity for clinical or research use. We assessed the psychometric and clinimetric properties of the RBDSSS in participants enrolled in the North American Prodromal Synucleinopathy (NAPS) Consortium for RBD. METHODS: NAPS participants, who have polysomnogram-confirmed RBD, and their bedpartners completed the RBDSSS (participant and bedpartner versions). The RBDSSS contains 8 questions to assess the frequency and severity/impact of (1) dream content, (2) vocalizations, (3) movements, and (4) injuries associated with RBD. Total scores for participant (maximum score = 54) and bedpartner (maximum score = 38) questionnaires were derived by multiplying frequency and severity scores for each question. The Clinical Global Impression Scale of Severity (CGI-S) and RBD symptom frequency were assessed by a physician during a semistructured clinical interview with participants and, if available, bedpartners. Descriptive analyses, correlations between overall scores, and subitems were assessed, and item response analysis was performed to determine the scale's validity. RESULTS: Among 261 study participants, the median (interquartile range) score for the RBDSSS-PT (participant) was 10 (4-18) and that for the RBDSSS-BP (bedpartner) was 8 (4-15). The median CGI-S was 3 (3-4), indicating moderate severity. RBDSSS-BP scores were significantly lower in women with RBD (6 vs 9, p = 0.02), while there were no sex differences in RBDSSS-PT scores (8 vs 10.5, p = 0.615). Positive correlations were found between RBDSSS-PT vs RBDSSS-BP (Spearman rs = 0.561), RBDSSS-PT vs CGI-S (rs = 0.556), and RBDSSS-BP vs CGI-S (rs = 0.491, all p < 0.0001). Item response analysis showed a high discriminatory value (range 1.40-2.12) for the RBDSSS-PT and RBDSSS-BP (1.29-3.47). DISCUSSION: We describe the RBDSSS with adequate psychometric and clinimetric properties to quantify RBD symptom severity and good concordance between participant and bedpartner questionnaires and between RBDSSS scores and clinician-assessed global severity.

Detection and Characterization of Walking Bouts Using a Single Wrist-Worn Accelerometer in Free-living Conditions.

Detection and characterization of abnormalities of movement are important to develop a method for detecting early signs of Parkinson's disease (PD). Most of the current research in detection of characteristic reduction of movements due to PD, known as parkinsonism, requires using a set of invasive sensors in a clinical or controlled environment. Actigraphy has been widely used in medical research as a non-invasive data acquisition method in free-living conditions for long periods of time. The proposed algorithm uses triaxial accelerometer data obtained through actigraphy to detect walking bouts at least 10 seconds long and characterize them using cadence and arm swing. Accurate detection of walking periods is the first step toward the characterization of movement based on gait abnormalities. The algorithm was based on a Walking Score (WS) derived using the value of the auto-correlation function (ACF) for the Resultant acceleration vector. The algorithm achieved a precision of 0.90, recall of 0.77, and F1 score of 0.83 compared to the expert scoring for walking bout detection. We additionally described a method to measure arm swing amplitude.

Sodium oxybate in treatment-resistant rapid-eye-movement sleep behavior disorder.

STUDY OBJECTIVES: Symptomatic therapies for rapid-eye-movement (REM) sleep behavior disorder (RBD) are limited. Sodium oxybate (SXB), a gamma-aminobutyric acid (GABA)-B agonist, could be effective but has not been evaluated against placebo. METHODS: This double-blind, parallel-group, randomized, placebo-controlled trial in 24 participants was conducted at the Stanford Sleep Center. Patients were adults with definite iRBD or Parkinson's disease and probable RBD (PD-RBD), and persistence of ≥ 2 weekly episodes despite standard therapy. Patients were randomized 1:1 to receive SXB during a 4-week titration followed by a 4-week stable dosing period. Primary outcome was number of monthly RBD episodes according to a diary filled by patients and partners. Secondary outcomes were severity, number of severe RBD episodes, and objective RBD activity on video polysomnography. RESULTS: Twelve iRBD and 12 PD-RBD participated (mean 65.8 years), and 22 (n = 10 SXB, 12 placebo) completed the study. Although no significant between-group difference was found, SXB showed reduction of monthly RBD episodes by 23.1 (95% CI -36.0, -10.2; p = 0.001) versus 10.5 with placebo (95% CI, -22.6, 1.6; p = 0.087). Improvement from baseline was similarly observed for RBD overall severity burden (each episode weighted for severity), number of severe episodes, and objective RBD activity per video-polysomnography. Two participants receiving SXB withdrew due to anxiety and dizziness. The majority of adverse events are otherwise resolved with dose adjustment. CONCLUSION: SXB could reduce RBD symptoms; however, response was inconsistent and a large placebo effect was observed across patient-reported outcomes. Larger studies using objective endpoints are needed. CLINICAL TRIAL: Treatment of REM Sleep Behavior Disorder (RBD) With Sodium Oxybate https://clinicaltrials.gov/ct2/show/NCT04006925 ClinicalTrials.gov identifier: NCT04006925.

Management of REM sleep behavior disorder: an American Academy of Sleep Medicine systematic review, meta-analysis, and GRADE assessment.

This systematic review provides supporting evidence for a clinical practice guideline for the management of rapid eye movement (REM) sleep behavior disorder in adults and children. The American Academy of Sleep Medicine commissioned a task force of 7 experts in sleep medicine. A systematic review was conducted to identify randomized controlled trials and observational studies that addressed interventions for the management of REM sleep behavior disorder in adults and children. Statistical analyses were performed to determine the clinical significance of critical and important outcomes. Finally, the Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) process was used to assess the evidence for making recommendations. The literature search identified 4,690 studies; 148 studies provided data suitable for statistical analyses; evidence for 45 interventions is presented. The task force provided a detailed summary of the evidence assessing the certainty of evidence, the balance of benefits and harms, patient values and preferences, and resource use considerations. CITATION: Howell M, Avidan AY, Foldvary-Schaefer N, et al. Management of REM sleep behavior disorder: an American Academy of Sleep Medicine systematic review, meta-analysis, and GRADE assessment. J Clin Sleep Med. 2023;19(4):769-810.

Management of REM sleep behavior disorder: an American Academy of Sleep Medicine clinical practice guideline.

INTRODUCTION: This guideline establishes clinical practice recommendations for the management of rapid eye movement sleep behavior disorder (RBD) in adults. METHODS: The American Academy of Sleep Medicine (AASM) commissioned a task force of experts in sleep medicine to develop recommendations and assign strengths based on a systematic review of the literature and an assessment of the evidence using Grading of Recommendations, Assessment, Development and Evaluation methodology. The task force provided a summary of the relevant literature and the certainty of evidence, the balance of benefits and harms, patient values and preferences, and resource use considerations that support the recommendations. The AASM Board of Directors approved the final recommendations. GOOD PRACTICE STATEMENT: The following good practice statement is based on expert consensus, and its implementation is necessary for the appropriate and effective management of patients with RBD: It is critically important to help patients maintain a safe sleeping environment to prevent potentially injurious nocturnal behaviors. In particular, the removal of bedside weapons, or objects that could inflict injury if thrown or wielded against a bed partner, is of paramount importance. Sharp furniture like nightstands should be moved away or their edges and headboard should be padded. To reduce the risk of injurious falls, a soft carpet, rug, or mat should be placed next to the bed. Patients with severe, uncontrolled RBD should be recommended to sleep separately from their partners, or at the minimum, to place a pillow between themselves and their partners. RECOMMENDATIONS: The following recommendations, with medications listed in alphabetical order, are a guide for clinicians in choosing a specific treatment for RBD in adults. Each recommendation statement is assigned a strength ("strong" or "conditional"). A "strong" recommendation (ie, "We recommend…") is one that clinicians should follow under most circumstances. A "conditional" recommendation (ie, "We suggest…") is one that requires that the clinician use clinical knowledge and experience and strongly consider the patient's values and preferences to determine the best course of action.Adult patients with isolated RBD.1. The AASM suggests that clinicians use clonazepam (vs no treatment) for the treatment of isolated RBD in adults. (CONDITIONAL).2. * The AASM suggests that clinicians use immediate-release melatonin (vs no treatment) for the treatment of isolated RBD in adults. (CONDITIONAL).3. * The AASM suggests that clinicians use pramipexole (vs no treatment) for the treatment of isolated RBD in adults. (CONDITIONAL).4. The AASM suggests that clinicians use transdermal rivastigmine (vs no treatment) for the treatment of isolated RBD in adults with mild cognitive impairment. (CONDITIONAL).Adult patients with secondary RBD due to medical condition.5. * The AASM suggests that clinicians use clonazepam (vs no treatment) for the treatment of secondary RBD due to medical condition in adults. (CONDITIONAL).6. * The AASM suggests that clinicians use immediate-release melatonin (vs no treatment) for the treatment of secondary RBD due to medical condition in adults. (CONDITIONAL).7. The AASM suggests that clinicians use transdermal rivastigmine (vs no treatment) for the treatment of secondary RBD due to medical condition (Parkinson disease) in adults. (CONDITIONAL).8. * The AASM suggests that clinicians not use deep brain stimulation (DBS; vs no treatment) for the treatment of secondary RBD due to medical condition in adults. (CONDITIONAL).Adult patients with drug-induced RBD.9. * The AASM suggests that clinicians use drug discontinuation (vs drug continuation) for the treatment of drug-induced RBD in adults. (CONDITIONAL).* The Recommendations section of this paper includes remarks that provide additional context to guide clinicians with implementation of this recommendation. CITATION: Howell M, Avidan AY, Foldvary-Schaefer N, et al. Management of REM sleep behavior disorder: an American Academy of Sleep Medicine clinical practice guideline. J Clin Sleep Med. 2023;19(4):759-768.

Baseline characteristics of the North American prodromal Synucleinopathy cohort.

OBJECTIVE: Rapid eye movement (REM) sleep behavior disorder (RBD) is widely considered a prodromal synucleinopathy, as most with RBD develop overt synucleinopathy within ~10 years. Accordingly, RBD offers an opportunity to test potential treatments at the earliest stages of synucleinopathy. The North American Prodromal Synucleinopathy (NAPS) Consortium has created a multisite RBD participant, primarily clinic-based cohort to better understand characteristics at diagnosis, and in future work, identify predictors of phenoconversion, develop synucleinopathy biomarkers, and enable early stage clinical trial enrollment. METHODS: Participants ≥18 years of age with overnight polysomnogram-confirmed RBD without Parkinson's disease, dementia, multiple system atrophy, or narcolepsy were enrolled from nine sites across North America (8/2018 to 4/2021). Data collection included family/personal history of RBD and standardized assessments of cognitive, motor, sensory, and autonomic function. RESULTS: Outcomes are primarily reported based on sex (361 total: n = 295 male, n = 66 female), and secondarily based on history of antidepressant use (n = 200 with, n = 154 without; with correction for sex differences) and based on extent of synucleinopathy burden (n = 56 defined as isolated RBD, n = 305 defined as RBD+ [i.e., exhibiting ≥1 abnormality]). Overall, these participants commonly demonstrated abnormalities in global cognition (MoCA; 38%), motor function (alternate tap test; 48%), sensory (BSIT; 57%), autonomic function (orthostatic hypotension, 38.8%), and anxiety/depression (BAI and PHQ-9; 39.3% and 31%, respectively). INTERPRETATION: These RBD participants, assessed with extensive history, demographic, cognitive, motor, sensory, and autonomic function demonstrated a lack of sex differences and high frequency of concomitant neurological abnormalities. These participants will be valuable for future longitudinal study and neuroprotective clinical trials.

Frequency of Orthostatic Hypotension in Isolated REM Sleep Behavior Disorder.

BACKGROUND AND OBJECTIVES: Although orthostatic hypotension (OH) can be an early feature of autonomic dysfunction in isolated REM sleep behavior disorder (iRBD), no large-scale studies have examined the frequency of OH in iRBD. In this study, we prospectively evaluated the frequency of OH in a large multicenter iRBD cohort. METHODS: Participants 18 years or older with video polysomnogram-confirmed iRBD were enrolled through the North American Prodromal Synucleinopathy consortium. All participants underwent 3-minute orthostatic stand testing to assess the frequency of OH, and a Δ heart rate/Δ systolic blood pressure (ΔHR/ΔSBP) ratio <0.5 was used to define reduced HR augmentation, suggestive of neurogenic OH. All participants completed a battery of assessments, including the Scales for Outcomes in Parkinson Disease-Autonomic Dysfunction (SCOPA-AUT) and others assessing cognitive, motor, psychiatric, and sensory domains. RESULTS: Of 340 iRBD participants (65 ± 10 years, 82% male), 93 (27%) met criteria for OH (ΔHR/ΔSBP 0.37 ± 0.28; range 0.0-1.57), and of these, 72 (77%) met criteria for OH with reduced HR augmentation (ΔHR/ΔSBP 0.28 ± 0.21; range 0.0-0.5). Supine hypertension (sHTN) was present in 72% of those with OH. Compared with iRBD participants without OH, those with OH were older, reported older age of RBD symptom onset, and had worse olfaction. There was no difference in autonomic symptom scores as measured by SCOPA-AUT. DISCUSSION: OH and sHTN are common in iRBD. However, as patients may have reduced autonomic symptom awareness, orthostatic stand testing should be considered in clinical evaluations. Longitudinal studies are needed to clarify the relationship between OH and phenoconversion risk in iRBD. TRIAL REGISTRATION INFORMATION: ClinicalTrials.gov: NCT03623672; North American Prodromal Synucleinopathy Consortium.

The concept of FDG-PET endophenotype in Alzheimer's disease.

Often viewed as a potential tool for preclinical diagnosis in early asymptomatic stages of Alzheimer's disease (AD), the term "endophenotype" has acquired a recent popularity in the field. In this review, we analyze the construct of endophenotype-originally designed to discover genes, and examine the literature on potential endophenotypes for the late-onset form of AD (LOAD). We focus on the [18F]-fluoro-2-deoxyglucose (FDG) PET technique, which shows a characteristic pattern of hypometabolism in AD-related regions in asymptomatic carriers of the ApoE E4 allele and in children of AD mothers. We discuss the pathophysiological significance and the positive predictive accuracy of an FDG-endophenotype for LOAD in asymptomatic subjects, and discuss several applications of this endophenotype in the identification of both promoting and protective factors. Finally, we suggest that the term "endophenotype" should be reserved to the study of risk factors, and not to the preclinical diagnosis of LOAD.

A critical review of dissociative trance and possession disorders: etiological, diagnostic, therapeutic, and nosological issues.

OBJECTIVE: Although the Diagnostic and Statistical Manual of Mental Disorders (DSM), Fourth Edition, acknowledges the existence of dissociative trance and possession disorders, simply named dissociative trance disorder (DTD), it asks for further studies to assess its clinical utility in the DSM-5. To answer this question, we conducted the first review of the medical literature. METHOD: The MEDLINE, CINAHL, and PsycINFO databases were searched from 1988 to 2010, seeking case reports of DTD according to the DSM or the International Classification of Diseases definitions. For each article, we collected epidemiologic and clinical data, explanatory models used by authors, treatments, and information on the outcome. RESULTS: We found 28 articles reporting 402 cases of patients with DTD worldwide. The data show an equal proportion of female and male patients, and a predominance of possession (69%), compared with trance (31%). Amnesia is reported by 20% of patients. Conversely, hallucinatory symptoms during possession episodes were found in 56% of patients and thus should feature as an important criterion. Somatic complaints are found in 34% of patients. Multiple explanatory models are simultaneously held and appear to be complementary. CONCLUSION: Data strongly suggest the inclusion of DTD in the DSM-5, provided certain adjustments are implemented. DTD is a widespread disorder that can be understood as a global idiom of distress, probably underdiagnosed in Western countries owing to cultural biases, whose incidence could increase given the rising flow of migration. Accurate diagnosis and appropriate management should result from a comprehensive evaluation both of sociocultural and of idiosyncratic issues, among which acculturation difficulties should systematically be considered, especially in cross-cultural settings.

Sleep Issues in Parkinson's Disease and Their Management.

Parkinson's disease (PD) is an alpha-synucleinopathy that leads to prominent motor symptoms including tremor, bradykinesia, and postural instability. Nonmotor symptoms including autonomic, neurocognitive, psychiatric symptoms, and sleep disturbances are also seen frequently in PD. The impact of PD on sleep is related to motor and nonmotor symptoms, in addition to the disruption of the pathways regulating sleep by central nervous system pathology. Rapid eye movement sleep behavior disorder is a parasomnia that can lead to self-injury and/or injury to partners at night. Restless legs syndrome is a subjective sensation of discomfort and urge to move the legs prior to falling asleep and can lead to insomnia and reduced sleep quality. Excessive daytime sleepiness is common in PD and exerts a negative impact on quality of life in addition to increasing the risk of falls. Obstructive sleep apnea is a breathing disorder during sleep that can cause frequent awakenings and excessive daytime sleepiness. Circadian rhythm dysfunction can lead to an advanced or delayed onset of sleep in patients and create disruption of normal sleep and wake times. All of these disorders are common in PD and can significantly reduce sleep quantity, sleep quality, or quality of life for patients and caretakers. Treatment approaches for each of these disorders are distinct and should be individualized to the patient. We review the literature regarding these common sleep issues encountered in PD and their treatment options.

Dreem Open Datasets: Multi-Scored Sleep Datasets to Compare Human and Automated Sleep Staging.

Sleep stage classification constitutes an important element of sleep disorder diagnosis. It relies on the visual inspection of polysomnography records by trained sleep technologists. Automated approaches have been designed to alleviate this resource-intensive task. However, such approaches are usually compared to a single human scorer annotation despite an inter-rater agreement of about 85% only. The present study introduces two publicly-available datasets, DOD-H including 25 healthy volunteers and DOD-O including 55 patients suffering from obstructive sleep apnea (OSA). Both datasets have been scored by 5 sleep technologists from different sleep centers. We developed a framework to compare automated approaches to a consensus of multiple human scorers. Using this framework, we benchmarked and compared the main literature approaches to a new deep learning method, SimpleSleepNet, which reach state-of-the-art performances while being more lightweight. We demonstrated that many methods can reach human-level performance on both datasets. SimpleSleepNet achieved an F1 of 89.9% vs 86.8% on average for human scorers on DOD-H, and an F1 of 88.3% vs 84.8% on DOD-O. Our study highlights that state-of-the-art automated sleep staging outperforms human scorers performance for healthy volunteers and patients suffering from OSA. Considerations could be made to use automated approaches in the clinical setting.

Drug Treatment of Restless Legs Syndrome in Older Adults.

Restless legs syndrome (RLS) has a high prevalence in the elderly and can impact sleep quality and sleep quantity, reduce quality of life (QoL), and increase the risk of falls during episodes of night-time ambulation. In patients unable to verbalize their sensory symptoms, certain behavioral cues may help with the diagnosis. A state of brain iron deficiency could play a central role in the pathophysiology of RLS and be upstream to a series of dysfunctions that are not limited to the dopaminergic system. Management should initially emphasize lifestyle modifications and reduction of all possible iatrogenic contributors while maintaining a state of normal-high peripheral iron stores. Oral iron, in patients with ferritin levels < 75 µg/dL, appears to be effective, although iron infusions should be considered when more immediate benefit or oral iron have not been effective. When other attempts fail and patients continue to experience chronic RLS symptoms substantially interfering with QoL, pharmacological agents may present a favorable benefit versus risk profile. Such agents may include α-2-δ drugs or dopaminergic agents, after careful consideration of the risk of RLS augmentation with the latter class. In patients with established RLS augmentation from the use of dopaminergic drugs, the addition of α-2-δ agents or low-dose opioids, with subsequent slow tapering of dopaminergic agents, is recommended. With any of these agents, caution should be made with regard to the risk of drug-drug interactions and altered pharmacokinetics in this fragile population. Although showing excellent long-term safety data in non-elderly adults with RLS, studies are needed to ascertain that such treatments are effective and well tolerated in older adults.

Autonomic impairment as a potential biomarker in idiopathic REM-sleep-behavior disorder.

Autonomic dysfunction is common in REM-sleep behavior disorder (RBD). Several studies have demonstrated abnormalities in heart rate variability, cardiac scintigraphy, and cardiovascular autonomic reflex testing. In addition, the type and severity of these abnormalities may correlate with rate of phenoconversion from idiopathic RBD (iRBD) to manifest neurodegenerative disease. This article summarizes the current literature on autonomic impairment in iRBD, with specific focus on the role of autonomic impairment as a potential biomarker of disease progression. REM sleep physiology and relevant anatomy is also discussed in relation to the central autonomic network and autonomic neurodegeneration.

AI vs Humans for the diagnosis of sleep apnea.

Polysomnography (PSG) is the gold standard for diagnosing sleep obstructive apnea (OSA). It allows monitoring of breathing events throughout the night. The detection of these events is usually done by trained sleep experts. However, this task is tedious, highly time-consuming and subject to important inter-scorer variability. In this study, we adapted our state-of-the-art deep learning method for sleep event detection, DOSED, to the detection of sleep breathing events in PSG for the diagnosis of OSA. We used a dataset of 52 PSG recordings with apnea-hypopnea event scoring from 5 trained sleep experts. We assessed the performance of the automatic approach and compared it to the inter-scorer performance for both the diagnosis of OSA severity and, at the microscale, for the detection of single breathing events. We observed that human sleep experts reached an average accuracy of 75% while the automatic approach reached 81% for sleep apnea severity diagnosis. The F1 score for individual event detection was 0.55 for experts and 0.57 for the automatic approach, on average. These results demonstrate that the automatic approach can perform at a sleep expert level for the diagnosis of OSA.