Towards proactively improving sleep: machine learning and wearable device data forecast sleep efficiency 4-8 hours before sleep onset

Abstract

Wearable devices with sleep-tracking functionalities can prompt behavioral changes to promote sleep, but proactively preventing poor sleep when it is likely to occur remains a challenge due to a lack of prediction models that can forecast sleep parameters prior to sleep onset. We developed models that forecast low sleep efficiency 4 and 8 hours prior to sleep onset using gradient boosting (CatBoost) and deep learning (Convolutional Neural Network Long Short-Term Memory, CNN-LSTM) algorithms trained exclusively on accelerometer data from 80,811 adults in the UK Biobank. Associations of various sleep and activity parameters with sleep efficiency were further examined. During repeated cross-validation, both CatBoost and CNN-LSTM exhibited excellent predictive performance (median AUCs > 0.90, median AUPRCs > 0.79). U-shaped relationships were observed between total activity within 4 and 8 hours of sleep onset and low sleep efficiency. Functional data analyses revealed higher activity 6-8 hours prior to sleep onset had negligible associations with sleep efficiency. Higher activity 4-6 hours prior had moderate beneficial associations, while higher activity within 4 hours had detrimental associations. Additional analyses showed that increased variability in sleep duration, efficiency, onset timing, and offset timing over the preceding 4 days was associated with lower sleep efficiency. Our study represents a first step towards wearable-based machine learning systems that proactively prevent poor sleep by demonstrating that sleep efficiency can be accurately forecasted prior to bedtime and by identifying pre-bed activity targets for subsequent intervention.

Keywords: accelerometer; deep learning; forecasting; functional data analysis; machine learning; sleep efficiency; sleep interventions; sleep quality; wearables.