Search for: All records

Sleep behavior significantly impacts health and acts as an indicator of physical and mental well-being. Monitoring and predicting sleep behavior with ubiquitous sensors may therefore assist in both sleep management and tracking of related health conditions. While sleep behavior depends on, and is reflected in the physiology of a person, it is also impacted by external factors such as digital media usage, social network contagion, and the surrounding weather. In this work, we propose SleepNet, a system that exploits social contagion in sleep behavior through graph networks and integrates it with physiological and phone data extracted from ubiquitous mobile and wearable devices for predicting next-day sleep labels about sleep duration. Our architecture overcomes the limitations of large-scale graphs containing connections irrelevant to sleep behavior by devising an attention mechanism. The extensive experimental evaluation highlights the improvement provided by incorporating social networks in the model. Additionally, we conduct robustness analysis to demonstrate the system's performance in real-life conditions. The outcomes affirm the stability of SleepNet against perturbations in input data. Further analyses emphasize the significance of network topology in prediction performance revealing that users with higher eigenvalue centrality are more vulnerable to data perturbations. 

Abstract Context In children, growth hormone (GH) pulses occur after sleep onset in association with slow-wave sleep (SWS). There have been no studies in children to quantify the effect of disrupted sleep on GH secretion. Objective This study aimed to investigate the effect of acute sleep disruption on GH secretion in pubertal children. Methods Fourteen healthy individuals (aged 11.3-14.1 years) were randomly assigned to 2 overnight polysomnographic studies, 1 with and 1 without SWS disruption via auditory stimuli, with frequent blood sampling to measure GH. Results Auditory stimuli delivered during the disrupted sleep night caused a 40.0 ± 7.8% decrease in SWS. On SWS-disrupted sleep nights, the rate of GH pulses during N2 sleep was significantly lower than during SWS (IRR = 0.56; 95% CI, 0.32-0.97). There were no differences in GH pulse rates during the various sleep stages or wakefulness in disrupted compared with undisrupted sleep nights. SWS disruption had no effect on GH pulse amplitude and frequency or basal GH secretion. Conclusion In pubertal children, GH pulses were temporally associated with episodes of SWS. Acute disruption of sleep via auditory tones during SWS did not alter GH secretion. These results indicate that SWS may not be a direct stimulus of GH secretion. 

Circadian rhythms influence multiple essential biological activities, including sleep, performance, and mood. The dim light melatonin onset (DLMO) is the gold standard for measuring human circadian phase (i.e., timing). The collection of DLMO is expensive and time consuming since multiple saliva or blood samples are required overnight in special conditions, and the samples must then be assayed for melatonin. Recently, several computational approaches have been designed for estimating DLMO. These methods collect daily sampled data (e.g., sleep onset/offset times) or frequently sampled data (e.g., light exposure/skin temperature/physical activity collected every minute) to train learning models for estimating DLMO. One limitation of these studies is that they only leverage one time-scale data. We propose a two-step framework for estimating DLMO using data from both time scales. The first step summarizes data from before the current day, whereas the second step combines this summary with frequently sampled data of the current day. We evaluate three moving average models that input sleep timing data as the first step and use recurrent neural network models as the second step. The results using data from 207 undergraduates show that our two-step model with two time-scale features has statistically significantly lower root-mean-square errors than models that use either daily sampled data or frequently sampled data.