Video-Based Actigraphy for Monitoring Wake and Sleep in Healthy Infants: A Laboratory Study.

Xi Long,Jan Werth,Tao Tan,Eric Sanden,Renée Otte

doi:10.3390/s19051075

Xi Long, Jan Werth + Show 3 more

Open Access

https://doi.org/10.3390/s19051075

Copy DOI

Abstract

Prolonged monitoring of infant sleep is paramount for parents and healthcare professionals for interpreting and evaluating infants’ sleep quality. Wake-sleep patterns are often studied to assess this. Video cameras have received a lot of attention in infant sleep monitoring because they are unobtrusive and easy to use at home. In this paper, we propose a method using motion data detected from infrared video frames (video-based actigraphy) to identify wake and sleep states. The motion, mostly caused by infant body movement, is known to be substantially associated with infant wake and sleep states. Two features were calculated from the video-based actigraphy, and a Bayesian-based linear discriminant classification model was employed to classify the two states. Leave-one-subject-out cross validation was performed to validate our proposed wake and sleep classification model. From a total of 11.6 h of infrared video recordings of 10 healthy term infants in a laboratory pilot study, we achieved a reliable classification performance with a Cohen’s kappa coefficient of 0.733 ± 0.204 (mean ± standard deviation) and an overall accuracy of 92.0% ± 4.6%.

Highlights

During the first year of life, the average infant is asleep for a greater part of the day than they are awake [1], making sleep one of the most important activities for their brains [2].Essential developmental processes take place during sleep, and problems with sleeping, may inhibit optimal development [3]
The most common way to monitor infant sleep is by polysomnography (PSG) [8], including multiple sensor modalities, such as electroencephalography, electrooculography, electromyography, electrocardiography, respiration, and others
We describe a new method for reliably classifying infant wake and sleep states using motions derived from IR video frames

Summary

Introduction

During the first year of life, the average infant is asleep for a greater part of the day than they are awake [1], making sleep one of the most important activities for their brains [2].Essential developmental processes take place during sleep, and problems with sleeping, may inhibit optimal development [3]. Sleep tracking and assessment can offer valuable information on an infant’s mental and physical development, for healthcare professionals, and for parents [4,5]. This information, for instance, could enable tailored coaching for parents and help improve an infant’s sleep quality [6,7]. The most common way to monitor infant sleep is by polysomnography (PSG) [8], including multiple sensor modalities, such as electroencephalography, electrooculography, electromyography, electrocardiography, respiration, and others. For reliable measures of wake-sleep patterns, prolonged monitoring over multiple nights is recommended [9,10], increasing the need for unobtrusive monitoring

Methods

Results

Conclusion