Peer-Reviewed Study Shows Dreem Headband Combined With AI Is as Accurate as Sleep Center Experts

By AIT News Desk On Jun 25, 2020

The device enables large scale longitudinal research studies and provides healthcare professionals with a tool for remote patient monitoring

A recently published, peer-reviewed study has shown that the Dreem headband, an ambulatory sleep measuring device, and built-in algorithms achieve of a level of analysis as accurate as the method traditionally used in sleep centers-polysomnography (PSG) for measurement, and experts for sleep staging (or sleep stage analysis). The results represent the start of a revolution in the world of sleep science.

The study, a joint clinical trial between researchers at IRBA (French Armed Forces Biomedical Research Institute) and Dreem’s scientific research team tested the Dreem headband’s signal acquisition and performance of its sleep staging algorithms against the PSG, scored manually by five experts.

25 subjects completed an overnight sleep study at a sleep center wearing a PSG and a Dreem headband simultaneously. The researchers then compared the measure of brain activity (EEG), heart rate, breathing frequency and respiration rate variability (RRV) as well as the sleep staging. The results showed that the Dreem headband acquires EEG measures that correlate with that of the PSG, measure biomarkers reliably throughout the night and the algorithm performs sleep-staging with similar accuracy to that of the five experts manually scoring the PSG readings.

Traditionally, the study of sleep has been confined to the lab slowed down by costly and cumbersome PSG technology, as well as a reliance on trained experts to manage it. This effectively limits the possibility to provide at-home care, or conduct large scale studies easily. Portable, lightweight and easy to use, the Dreem headband opens a world of possibilities not just for sleep research but for patient care as a whole. The recent pandemic shows the medical world that the need for effective, reliable remote patient monitoring solutions, like Dreem, is more pressing than ever before.

The impact of this study extends beyond the worlds of research and medicine. As Prof. Raphael Heinzer, Director of the Sleep Center at the University of Lausanne, Switzerland, notes, “This study paves the way for longitudinal sleep studies that directly monitor brain activity instead of relying merely on wrist motion.” The Dreem headband offers people the opportunity to monitor and understand their sleep and its evolution over time, from home, with a level of sophistication once limited to a clinical setting.

Emmanuel Mignot, member of the US National Academy of Sciences and Professor at Stanford University says of the study, “Dreem is at the forefront of a new revolution. This is the beginning of true, comfortable EEG sleep recordings at home.” He adds, “Soon, the transition to sleep recording at home and machine learning-based interpretation of sleep studies will be fulfilled. This will enhance doctors’ ability to diagnose and take care of patients remotely.“