Performance of an open machine learning model to classify sleep/wake from actigraphy across ∼24-hour intervals without knowledge of rest timing

Goal and aims: Commonly used actigraphy algorithms are designed to operate within a known in-bed interval. However, in free-living scenarios this interval is often unknown. We trained and evaluated a sleep/wake classifier that operates on actigraphy over ∼24-hour intervals, without knowledge of in-bed timing.

Focus technology: Actigraphy counts from ActiWatch Spectrum devices.

Reference technology: Sleep staging derived from polysomnography, supplemented by observation of wakefulness outside of the staged interval. Classifications from the Oakley actigraphy algorithm were additionally used as performance reference.

Sample: Adults, sleeping in either a home or laboratory environment.

Design: Machine learning was used to train and evaluate a sleep/wake classifier in a supervised learning paradigm. The classifier is a temporal convolutional network, a form of deep neural network.

Core analytics: Performance was evaluated across ∼24 hours, and additionally restricted to only in-bed intervals, both in terms of epoch-by-epoch performance, and the discrepancy of summary statistics within the intervals.

Additional analytics and exploratory analyses: Performance of the trained model applied to the Multi-Ethnic Study of Atherosclerosis dataset.

Core outcomes: Over ∼24 hours, the temporal convolutional network classifier produced the same or better performance as the Oakley classifier on all measures tested. When restricting analysis to the in-bed interval, the temporal convolutional network remained favorable on several metrics.

Important supplemental outcomes: Performance decreased on the Multi-Ethnic Study of Atherosclerosis dataset, especially when restricting analysis to the in-bed interval.

Core conclusion: A classifier using data labeled over ∼24-hour intervals allows for the continuous classification of sleep/wake without knowledge of in-bed intervals. Further development should focus on improving generalization performance.