The data acquisition device addresses the difficulty of accurate and consistent data collection to get to better sleep.
According to the National Academies and the National Institutes of Health, about 70 million people in the US suffer from chronic sleep loss or sleep disorders. In February 2016, results of a study released by the US Centers for Disease Control and Prevention (CDC) indicated more than a third of American adults are not getting enough sleep on a regular basis. Lack of adequate sleep (quantity and/or quality) impacts more than just next day performance and mood; the persistent lack of adequate sleep has been shown to be a risk factor for new onset and recurrent major depression and confers increased risk for suicidal ideation and behaviour. Further, the persistent lack of adequate sleep has been shown to be a risk factor for obesity, hypertension, diabetes, and cardiovascular disease.
Given the prevalence of insufficient sleep and sleep disturbances, many devices – wearable and standalone – have been brought to the market that purport to track sleep metrics and advise users on sleep improvement. Each provide components necessary to the goal but none provide a complete offering and each misses the fundamental step towards better sleep – while they may characterize sleep and provide broad recommendations, none can deliver effective, individualized, self-correcting recommendations for optimizing sleep time. In addition, available products suffer from a lack of quality baseline data which results in flawed recommendations on improving sleep.
Approach, Advantages, and Future Directions
To address these gaps in current offerings, researchers at the U of A and Penn are developing a novel sleep optimization system including a data acquisition device, methods to gradually increase sleep time based on a person’s own sleep patterns and optimize sleep efficiency, and sophisticated calibration algorithms to optimize sleep against external benchmarks (like health and daily functioning).
Primarily this system is meant to track the sleeping patterns of an individual through passive and active input of metrics and deliver useful and actionable recommendations for achieving optimal sleep (i.e., the identification of the sleep durations and phases that may be achievable for the individual and best suited to their target daytime health and functioning). The system is meant to be highly flexible in that the recommendations will change over time (e.g., with season and over successive months and years). Ultimately, the method may serve as a systematic means towards the identification of new onset disease where early detection of significant sleep changes may serve to allow for early interventions.
Applications and Advantages
This invention solves several key problems. First, the data acquisition device addresses the difficulty of accurate and consistent data collection to get to better sleep. It improves the ability of sleep trackers to gather the best information about sleep. Second, the technology platform solves the problem of sleep tracking without tailored recommendations since it provides an algorithm to tell people what to do next to get more and better sleep. It works with a person’s natural ebbs and flows to maximize their sleep ability. Third, the calibration algorithms solve the problem of not knowing how much sleep is right for a person to achieve their health and functioning goals. It tells a person how much sleep they need and when they should be sleeping, based on outcomes that are important to them.