Jukka Ranta1,2, Manu Airaksinen1,2, Turkka Kirjavainen3, Sampsa Vanhatalo1,4, Nathan J Stevenson5. 1. Department of Clinical Neurophysiology, BABA Center, Children's Hospital, Helsinki University Hospital and University of Helsinki, Helsinki, Finland. 2. Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland. 3. Department of Paediatrics, Children's Hospital Helsinki University Hospital, Helsinki, Finland. 4. Neuroscience Center, Helsinki Institute of Life Science, University of Helsinki, Helsinki, Finland. 5. Brain Modeling Group, QIMR Berghofer Medical Research Institute, Brisbane, QLD, Australia.
Abstract
OBJECTIVE: To develop a non-invasive and clinically practical method for a long-term monitoring of infant sleep cycling in the intensive care unit. METHODS: Forty three infant polysomnography recordings were performed at 1-18 weeks of age, including a piezo element bed mattress sensor to record respiratory and gross-body movements. The hypnogram scored from polysomnography signals was used as the ground truth in training sleep classifiers based on 20,022 epochs of movement and/or electrocardiography signals. Three classifier designs were evaluated in the detection of deep sleep (N3 state): support vector machine (SVM), Long Short-Term Memory neural network, and convolutional neural network (CNN). RESULTS: Deep sleep was accurately identified from other states with all classifier variants. The SVM classifier based on a combination of movement and electrocardiography features had the highest performance (AUC 97.6%). A SVM classifier based on only movement features had comparable accuracy (AUC 95.0%). The feature-independent CNN resulted in roughly comparable accuracy (AUC 93.3%). CONCLUSION: Automated non-invasive tracking of sleep state cycling is technically feasible using measurements from a piezo element situated under a bed mattress. SIGNIFICANCE: An open source infant deep sleep detector of this kind allows quantitative, continuous bedside assessment of infant's sleep cycling.
OBJECTIVE: To develop a non-invasive and clinically practical method for a long-term monitoring of infant sleep cycling in the intensive care unit. METHODS: Forty three infant polysomnography recordings were performed at 1-18 weeks of age, including a piezo element bed mattress sensor to record respiratory and gross-body movements. The hypnogram scored from polysomnography signals was used as the ground truth in training sleep classifiers based on 20,022 epochs of movement and/or electrocardiography signals. Three classifier designs were evaluated in the detection of deep sleep (N3 state): support vector machine (SVM), Long Short-Term Memory neural network, and convolutional neural network (CNN). RESULTS: Deep sleep was accurately identified from other states with all classifier variants. The SVM classifier based on a combination of movement and electrocardiography features had the highest performance (AUC 97.6%). A SVM classifier based on only movement features had comparable accuracy (AUC 95.0%). The feature-independent CNN resulted in roughly comparable accuracy (AUC 93.3%). CONCLUSION: Automated non-invasive tracking of sleep state cycling is technically feasible using measurements from a piezo element situated under a bed mattress. SIGNIFICANCE: An open source infant deep sleep detector of this kind allows quantitative, continuous bedside assessment of infant's sleep cycling.
Authors: Juha M Kortelainen; Martin O Mendez; Anna Maria Bianchi; Matteo Matteucci; Sergio Cerutti Journal: IEEE Trans Inf Technol Biomed Date: 2010-04-15
Authors: Philip Ian Terrill; Stephen James Wilson; Sadasivam Suresh; David M Cooper; Carolyn Dakin Journal: IEEE Trans Biomed Eng Date: 2010-02-17 Impact factor: 4.538
Authors: Madeleine Grigg-Damberger; David Gozal; Carole L Marcus; Stuart F Quan; Carol L Rosen; Ronald D Chervin; Merill Wise; Daniel L Picchietti; Stephan H Sheldon; Conrad Iber Journal: J Clin Sleep Med Date: 2007-03-15 Impact factor: 4.062
Authors: Jan Werth; Louis Atallah; Peter Andriessen; Xi Long; Elly Zwartkruis-Pelgrim; Ronald M Aarts Journal: Sleep Med Rev Date: 2016-04-05 Impact factor: 11.609