Performance of an open machine learning model to classify sleep/wake from actigraphy across ∼24-hour intervals...

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.

Actigraphy counts from ActiWatch Spectrum devices.

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.

Adults, sleeping in either a home or laboratory environment.

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.

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.

Performance of the trained model applied to the Multi-Ethnic Study of Atherosclerosis dataset.

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.

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

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.