By establishing correlations between sleep parameters and wellbeing indicators, our project hopes to further understanding of fluctuations in wellbeing and inform the development of wearables that monitor sleep patterns.
We begin by identifying the impact of different combinations and transformations of sleep regularity metrics (Sleep Regularity Index - SRI, Composite Phase Deviation - CPD, Interdaily Stability - IS) and duration across various time frames on wellbeing scores (alertness, happiness, energy, health, and calmness) in the SNAPSHOT study. We further evaluate their linear and non-linear associations by using personalized methods, such as Linear Mixed Effects models (LMM) and Mixed Effects Random Forest (MERF), that can recognize individual differences.
We found statistically significant LMM results for independent regularity (SRI, IS), combined regularity (SRI and IS), total sleep time as duration (TST), and combined regularity and total sleep time (SRI and TST, IS and TST) for alertness and energy over 2-4 nights. MERF outperformed other models in terms of Mean Absolute Error (MAE) for all time split scenarios.