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.

Inclusion Criteria:

• Capable of providing informed consent

Exclusion Criteria:

• Pregnant or nursing females
• History of any severe comorbidities such as cardiac, neurologic, or psychiatric diseases/disorders in the last 12 months
• Morbid obesity (BMI >= 40)
• Use of benzodiazepines, nonbenzodiazepine (Z-drugs), or Gammahydroxybutyrate (GHB) the day/night of the study

We plan to share de-identified physiological data in an open-source format to the public. However, this will only occur if the data files are of sufficient quality and likely to be of use to the scientific community. This decision may also depend on certain legal or business constraints.