This study aims to evaluate the accuracy of automated sleep analysis by the Dreem dry-EEG headband and deep learning algorithm in comparison to the consensus of 5 sleep technologists' manual scoring of a gold-standard clinical polysomnogram (PSG) record in healthy adult volunteers during an overnight clinic-based sleep study.
The study will enroll 25 adult volunteers who will undergo a one-night in-lab sleep study. All volunteers are first prescreened over the phone. Upon arrival at the research center, volunteers provide informed consent, are interviewed to confirm eligibility, and complete a detailed demographic, medical, health, sleep, and lifestyle survey. After the survey, participants are fitted with the PSG and the Dreem headband by the sleep technologist. During the PSG sleep study, the Dreem headband records EEG, pulse, oxygen saturation (SO2), movement, and respiratory rate. Dreem's algorithms will be used to automatically stage the Dreem sleep data, and the results will then be compared to the consensus of 5 sleep technologists' manual scoring of the respective PSG records for the same individuals to determine the accuracy of Dreem's sleep staging algorithms.
Study Type
INTERVENTIONAL
Allocation
NA
Purpose
DIAGNOSTIC
Masking
NONE
Enrollment
31
Dreem Band to be worn by each participant while undergoing in-lab sleep study with PSG.
Institut de Recherche Biomédicale des Armées
Brétigny-sur-Orge, D19, France
Sleep stages accuracy (Dreem vs. PSG consensus)
Cohen's kappa comparing the classification of AASM sleep stages at each 30-sec epoch determined automatically by the Dreem headband compared those determined by the consensus of 5 sleep technologists' scoring of each subject's PSG record from the same night.
Time frame: Day 1
Total Sleep Time (TST) (accuracy between Dreem and PSG consensus)
Total time (in minutes) the subject spends asleep as automatically determined by the Dreem headband compared to the TST determined by the consensus of 5 sleep technologists' scoring of the subject's PSG record from the same night.
Time frame: Day 1
Wake After Sleep Onset (WASO) time (accuracy between Dreem and PSG consensus)
Total time (in minutes) the subject spends awake from sleep onset to sleep end as automatically determined by the Dreem headband compared to the WASO determined by the consensus of 5 sleep technologists' scoring of the subject's PSG record from the same night.
Time frame: Day 1
Time in N1 sleep stage (accuracy between Dreem and PSG consensus)
Total time (in minutes) the subject spends in AASM N1 sleep stage as automatically determined by the Dreem headband compared to the N1 time determined by the consensus of 5 sleep technologists' scoring of the subject's PSG record from the same night.
Time frame: Day 1
Time in N2 sleep stage (accuracy between Dreem and PSG consensus)
Total time (in minutes) the subject spends in AASM N2 sleep stage as automatically determined by the Dreem headband compared to the N2 time determined by the consensus of 5 sleep technologists' scoring of the subject's PSG record from the same night.
Time frame: Day 1
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.
Time in N3 sleep stage (accuracy between Dreem and PSG consensus)
Total time (in minutes) the subject spends in AASM N3 sleep stage as automatically determined by the Dreem headband compared to the N3 time determined by the consensus of 5 sleep technologists' scoring of the subject's PSG record from the same night.
Time frame: Day 1
Time in rapid eye movement (REM) sleep stage (accuracy between Dreem and PSG consensus)
Total time (in minutes) the subject spends in AASM REM sleep stage as automatically determined by the Dreem headband compared to the REM time determined by the consensus of 5 sleep technologists' scoring of the subject's PSG record from the same night.
Time frame: Day 1
Number of sleep slow oscillations (accuracy between Dreem and PSG consensus)
Number of sleep slow oscillations counted automatically by the Dreem headband compared to those determined by the consensus of 5 sleep technologists' scoring of the subject's PSG record from the same night.
Time frame: Day 1
Number of sleep spindles (accuracy between Dreem and PSG consensus)
Number of sleep spindles counted automatically by the Dreem headband compared to those determined by the consensus of 5 sleep technologists' scoring of the subject's PSG record from the same night.
Time frame: Day 1
Number of sleep eye movements (accuracy between Dreem and PSG consensus)
Number of eye movements during sleep counted automatically by the Dreem headband compared to those determined by the consensus of 5 sleep technologists' scoring of the subject's PSG record from the same night.
Time frame: Day 1
Breathing frequency measurement (accuracy between Dreem and PSG consensus)
Breathing frequency measured automatically by the Dreem headband's accelerometer compared to those determined by the nasal cannula on the subject's PSG from the same night.
Time frame: Day 1