The Dreem Headband compared to polysomnography for electroencephalographic signal acquisition and sleep staging

Arnal, Pierrick J.; Thorey, Valentin; Debellemanière, Eden; Ballard, Michael E.; Hernández, Albert Bou; Guillot, Antoine; Jourde, Hugo R.; Harris, Mason; Guillard, Mathias; Beers, Pascal Van; Chennaoui, Mounir; Sauvet, Fabien

doi:10.1093/sleep/zsaa097

Cited by 237 publications

(197 citation statements)

References 31 publications

Supporting

Mentioning

188

Contrasting

Unclassified

Order By: Relevance

“…An analysis of nights scored by more than 2,500 scorers shows an average interrater agreement of 82.6% across sleep stages [4], the interrater agreement strongly depends on the dataset demographics and on the sleep center where the study is recorded. As a rule of thumb, a dataset with older subjects or subjects with sleep disorders presents lower inter-rater agreements [5] than a dataset composed of healthy subjects [6].…”

Section: Introductionmentioning

confidence: 99%

RobustSleepNet: Transfer Learning for Automated Sleep Staging at Scale

Guillot¹,

Thorey²

2021

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

View full text Add to dashboard Cite

Sleep disorder diagnosis relies on the analysis of polysomnography (PSG) records. As a preliminary step of this examination, sleep stages are systematically determined. In practice, sleep stage classification relies on the visual inspection of 30second epochs of polysomnography signals. Numerous automatic approaches have been developed to replace this tedious and expensive task. Although these methods demonstrated better performance than human sleep experts on specific datasets, they remain largely unused in sleep clinics. The main reason is that each sleep clinic uses a specific PSG montage that most automatic approaches cannot handle out-of-the-box. Moreover, even when the PSG montage is compatible, publications have shown that automatic approaches perform poorly on unseen data with different demographics. To address these issues, we introduce RobustSleepNet, a deep learning model for automatic sleep stage classification able to handle arbitrary PSG montages. We trained and evaluated this model in a leave-one-out-dataset fashion on a large corpus of 8 heterogeneous sleep staging datasets to make it robust to demographic changes. When evaluated on an unseen dataset, RobustSleepNet reaches 97% of the F1 of a model explicitly trained on this dataset. Hence, RobustSleepNet unlocks the possibility to perform high-quality out-of-the-box automatic sleep staging with any clinical setup. We further show that finetuning RobustSleepNet, using a part of the unseen dataset, increases the F1 by 2% when compared to a model trained specifically for this dataset. Therefore, finetuning might be used to reach a state-of-the-art level of performance on a specific population.

show abstract

Section: Introductionmentioning

confidence: 99%

RobustSleepNet: Transfer Learning for Automated Sleep Staging at Scale

Guillot¹,

Thorey²

2021

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

View full text Add to dashboard Cite

show abstract

“…This substudy will compare Dreem data and PSG in the geriatric population to complement early studies across a broad age. 148 …”

Section: Methodsmentioning

confidence: 99%

“…Device validation for elderly patients This substudy will compare Dreem data and PSG in the geriatric population to complement early studies across a broad age. 148 Postoperative cognitive trajectories This substudy uses a modified version of the Brief Test of Adult Cognition by Telephone to determine the rate of postoperative cognitive recovery and how delirium impacts cognitive recovery via interval assessments up to 6 months after surgery. 175 176 The battery will evaluate multiple cognitive domains including episodic memory, working memory, processing speed, attention and executive function.…”

Section: Open Accessmentioning

confidence: 99%

Protocol for the Prognosticating Delirium Recovery Outcomes Using Wakefulness and Sleep Electroencephalography (P-DROWS-E) study: a prospective observational study of delirium in elderly cardiac surgical patients

et al. 2020

View full text Add to dashboard Cite

IntroductionDelirium is a potentially preventable disorder characterised by acute disturbances in attention and cognition with fluctuating severity. Postoperative delirium is associated with prolonged intensive care unit and hospital stay, cognitive decline and mortality. The development of biomarkers for tracking delirium could potentially aid in the early detection, mitigation and assessment of response to interventions. Because sleep disruption has been posited as a contributor to the development of this syndrome, expression of abnormal electroencephalography (EEG) patterns during sleep and wakefulness may be informative. Here we hypothesise that abnormal EEG patterns of sleep and wakefulness may serve as predictive and diagnostic markers for postoperative delirium. Such abnormal EEG patterns would mechanistically link disrupted thalamocortical connectivity to this important clinical syndrome.Methods and analysisP-DROWS-E (Prognosticating Delirium Recovery Outcomes Using Wakefulness and Sleep Electroencephalography) is a 220-patient prospective observational study. Patient eligibility criteria include those who are English-speaking, age 60 years or older and undergoing elective cardiac surgery requiring cardiopulmonary bypass. EEG acquisition will occur 1–2 nights preoperatively, intraoperatively, and up to 7 days postoperatively. Concurrent with EEG recordings, two times per day postoperative Confusion Assessment Method (CAM) evaluations will quantify the presence and severity of delirium. EEG slow wave activity, sleep spindle density and peak frequency of the posterior dominant rhythm will be quantified. Linear mixed-effects models will be used to evaluate the relationships between delirium severity/duration and EEG measures as a function of time.Ethics and disseminationP-DROWS-E is approved by the ethics board at Washington University in St. Louis. Recruitment began in October 2018. Dissemination plans include presentations at scientific conferences, scientific publications and mass media.Trial registration numberNCT03291626.

show abstract

“…Secondly, only a single night of polysomnographic data was collected before treatment, which may have been impacted by “first night effects,” or night-to-night variability in objective sleep and respiratory parameters. Given the high costs associated with polysomnography, it may be possible for future studies to utilize novel and less expensive measures of objective sleep such as wearable wrist-worn or electroencephalography devices (e.g., actigraphy, portable EEG monitoring devices) capable of measuring sleep over several consecutive nights to produce more stable estimates of key sleep parameters ( Arnal et al, 2020 ).…”

Section: Limitationsmentioning

confidence: 99%

Polysomnographic Predictors of Treatment Response to Cognitive Behavioral Therapy for Insomnia in Participants With Co-morbid Insomnia and Sleep Apnea: Secondary Analysis of a Randomized Controlled Trial

et al. 2021

View full text Add to dashboard Cite

ObjectiveCo-morbid insomnia and sleep apnea (COMISA) is a common and debilitating condition that is more difficult to treat compared to insomnia or sleep apnea-alone. Emerging evidence suggests that cognitive behavioral therapy for insomnia (CBTi) is effective in patients with COMISA, however, those with more severe sleep apnea and evidence of greater objective sleep disturbance may be less responsive to CBTi. Polysomnographic sleep study data has been used to predict treatment response to CBTi in patients with insomnia-alone, but not in patients with COMISA. We used randomized controlled trial data to investigate polysomnographic predictors of insomnia improvement following CBTi, versus control in participants with COMISA.MethodsOne hundred and forty five participants with insomnia (ICSD-3) and sleep apnea [apnea-hypopnea index (AHI) ≥ 15] were randomized to CBTi (n = 72) or no-treatment control (n = 73). Mixed models were used to investigate the effect of pre-treatment AHI, sleep duration, and other traditional (AASM sleep macrostructure), and novel [quantitative electroencephalography (qEEG)] polysomnographic predictors of between-group changes in Insomnia Severity Index (ISI) scores from pre-treatment to post-treatment.ResultsCompared to control, CBTi was associated with greater ISI improvement among participants with; higher AHI (interaction p = 0.011), less wake after sleep onset (interaction p = 0.045), and less N3 sleep (interaction p = 0.005). No quantitative electroencephalographic, or other traditional polysomnographic variables predicted between-group ISI change (all p > 0.09).DiscussionAmong participants with COMISA, higher OSA severity predicted a greater treatment-response to CBTi, versus control. People with COMISA should be treated with CBTi, which is effective even in the presence of severe OSA and objective sleep disturbance.

show abstract

The Dreem Headband compared to polysomnography for electroencephalographic signal acquisition and sleep staging

Cited by 237 publications

References 31 publications

RobustSleepNet: Transfer Learning for Automated Sleep Staging at Scale

RobustSleepNet: Transfer Learning for Automated Sleep Staging at Scale

Protocol for the Prognosticating Delirium Recovery Outcomes Using Wakefulness and Sleep Electroencephalography (P-DROWS-E) study: a prospective observational study of delirium in elderly cardiac surgical patients

Polysomnographic Predictors of Treatment Response to Cognitive Behavioral Therapy for Insomnia in Participants With Co-morbid Insomnia and Sleep Apnea: Secondary Analysis of a Randomized Controlled Trial

Contact Info

Product

Resources

About