Longitudinal Cardiorespiratory Wearable Sleep Staging in the Home

There is a growing interest in performing automated, longitudinal tracking of sleep in the home environment using wearables and machine learning. Wearables such as smart watches or chest patches can be comfortably worn for long periods of time, and cardiorespiratory waveforms measured by these wearables combined with machine learning models to estimate sleep state. However, these machine learning models are typically trained and tested on retrospective data from sleep labs, where cardiorespiratory waveforms are monitored using bulky, specialised equipment rather than wearables. As such, these models have yet to be validated in their intended scenario of use: longitudinal, wearable sleep monitoring in the home.

This paper establishes and validates a pipeline for longitudinal cardiorespiratory sleep monitoring in the home using data from the RESTORE study. In RESTORE, 17 participants with a sleep-related condition (insomnia and depressive symptoms) underwent a sleep-related clinical intervention (sleep restriction therapy). Participants simultaneously wore a low-density home electroencephalogram device, allowing for expert, manual sleep staging using brain activity, as well as a wearable chest patch, allowing for wearable monitoring of cardiorespiratory waveforms. Both devices were worn by participants for 10 nights while undergoing treatment at home. A state-of-the-art cardiorespiratory sleep staging model, combining transformer and convolutional neural networks, was then tuned and tested on the wearable data using leave-one-subject-out-cross-validation.

After transfer learning, the cardiorespiratory sleep staging model had an accuracy of 77.1% and Cohen’s Kappa of 0.679 for four-class sleep staging using the wearable data from the RESTORE study. Further, the model was able to accurately track sleep and sleep-derived metrics longitudinally while participants underwent sleep restriction therapy. These results represent one of the first direct demonstrations of the potential for wearable, cardiorespiratory sleep staging to track longitudinal, clinically relevant changes in sleep in individuals undergoing a sleep-related intervention in the home.