Abstract
BackgroundWearable devices are now widely available to collect continuous objective behavioral data from individuals and to measure sleep.ObjectiveThis study aims to introduce a pipeline to infer sleep onset, duration, and quality from raw accelerometer data and then quantify the relationships between derived sleep metrics and other variables of interest.MethodsThe pipeline released here for the deep phenotyping of sleep, as the DPSleep software package, uses a stepwise algorithm to detect missing data; within-individual, minute-based, spectral power percentiles of activity; and iterative, forward-and-backward–sliding windows to estimate the major Sleep Episode onset and offset. Software modules allow for manual quality control adjustment of the derived sleep features and correction for time zone changes. In this paper, we have illustrated the pipeline with data from participants studied for more than 200 days each.ResultsActigraphy-based measures of sleep duration were associated with self-reported sleep quality ratings. Simultaneous measures of smartphone use and GPS location data support the validity of the sleep timing inferences and reveal how phone measures of sleep timing can differ from actigraphy data.ConclusionsWe discuss the use of DPSleep in relation to other available sleep estimation approaches and provide example use cases that include multi-dimensional, deep longitudinal phenotyping, extended measurement of dynamics associated with mental illness, and the possibility of combining wearable actigraphy and personal electronic device data (eg, smartphones and tablets) to measure individual differences across a wide range of behavioral variations in health and disease. A new open-source pipeline for deep phenotyping of sleep, DPSleep, analyzes raw accelerometer data from wearable devices and estimates sleep onset and offset while allowing for manual quality control adjustments.
Highlights
Background and ChallengeProlonged daily episodes of sleep behavior are expressed nearly ubiquitously in all members of our species, as they are innate and undergird both physical and mental health across the lifespan
This paper introduces an open-source sleep-analysis pipeline called DPSleep, referring to the deep phenotyping of sleep that we offer to the community as a platform to facilitate longitudinal studies of sleep using data from widely available wearable devices [11]
The platform was applied to two cohorts of participants that possessed extended data over months to years and included clinically healthy undergraduates and outpatients living with severe mental illness
Summary
Prolonged daily episodes of sleep behavior are expressed nearly ubiquitously in all members of our species, as they are innate and undergird both physical and mental health across the lifespan. Multiple studies have suggested that sleep loss or poor sleep quality are predictors (and potentially moderators and mediators) of mental illness symptoms and poor cognitive performance [1,2,3,4,5,6]. Actigraphy, defined as recording activity-related data, mainly acceleration, using wearable devices, has been suggested as an efficient and reliable alternative to measure certain features of sleep patterns in natural, at-home settings [18,19]. Openly available feature-extraction algorithms with the capability to retain and present the features from raw to derived measures are essential for a reproducible large-scale understanding of human sleep, even in the presence of proprietary algorithms associated with many of the devices
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
