Predicting Sleep and Sleep Stage in Children Using Actigraphy and Heartrate via a Long Short-Term Memory Deep Learning Algorithm: A Performance Evaluation

TL;DR

This study shows that LSTM deep learning can accurately predict sleep and wake states in children using actigraphy and heart rate data, outperforming traditional methods.

Contribution

The novel use of LSTM with actigraphy and heart rate data improves sleep stage prediction in children compared to conventional algorithms.

Findings

LSTM achieved 94.1–95.1% accuracy in sleep versus wake classification across devices.

Heart rate data improved sleep stage prediction but not binary sleep/wake classification.

LSTM outperformed logistic regression and random forest in sleep detection.

Abstract

Children's ambulatory sleep is commonly measured via actigraphy. However, traditional actigraphy measured sleep (e.g., Sadeh algorithm) struggles to predict wake (i.e., specificity, values typically < 70) and cannot predict sleep stages. Long short-term memory (LSTM) is a machine learning algorithm that may address these deficiencies. This study evaluated the agreement of LSTM sleep estimates from actigraphy and heartrate (HR) data with polysomnography (PSG). Children (N = 238, 5–12 years, 52.8% male, 50% Black 31.9% White) participated in an overnight laboratory polysomnography. Participants were referred because of suspected sleep disruptions. Children wore an ActiGraph GT9X accelerometer and two of three consumer wearables (i.e., Apple Watch Series 7, Fitbit Sense, Garmin Vivoactive 4) on their non-dominant wrist during the polysomnogram. LSTM estimated sleep versus wake and sleep stage (wake, not-REM, REM) using raw actigraphy and HR data for each 30-s epoch. Logistic regression and random forest were also estimated as a benchmark for performance with which to compare the LSTM results. A 10-fold cross-validation technique was employed, and confusion matrices were constructed. Sensitivity and specificity were calculated to assess the agreement between research-grade and consumer wearables with the criterion polysomnography. For sleep versus wake classification, LSTM outperformed logistic regression and random forest with accuracy ranging from 94.1 to 95.1, sensitivity ranging from 94.9 to 95.9 across different devices, and specificity ranging from 84.5 to 89.6. The addition of HR improved the prediction of sleep stages but not binary sleep versus wake. LSTM is promising for predicting sleep and sleep staging from actigraphy data, and HR may improve sleep stage prediction.

Figures