TY - JOUR
T1 - The Sleep Well Baby project
T2 - an automated real-time sleep-wake state prediction algorithm in preterm infants
AU - Sentner, Thom
AU - Wang, Xiaowan
AU - de Groot, Eline R
AU - van Schaijk, Lieke
AU - Tataranno, Maria Luisa
AU - Vijlbrief, Daniel C
AU - Benders, Manon J N L
AU - Bartels, Richard
AU - Dudink, Jeroen
N1 - Funding Information:
This work was supported by the European Commission, Horizon 2020 Marie Skłodowska-Curie Actions [Grant agreement number: EU H2020 MSCA-ITN-2018-#813483, INtegrating Functional Assessment measures for Neonatal Safeguard (INFANS)].
Publisher Copyright:
© 2022 Sleep Research Society.
PY - 2022/10/1
Y1 - 2022/10/1
N2 - STUDY OBJECTIVES: Sleep is an important driver of early brain development. However, sleep is often disturbed in preterm infants admitted to the neonatal intensive care unit (NICU). We aimed to develop an automated algorithm based on routinely measured vital parameters to classify sleep-wake states of preterm infants in real-time at the bedside.METHODS: In this study, sleep-wake state observations were obtained in 1-minute epochs using a behavioral scale developed in-house while vital signs were recorded simultaneously. Three types of vital parameter data, namely, heart rate, respiratory rate, and oxygen saturation, were collected at a low-frequency sampling rate of 0.4 Hz. A supervised machine learning workflow was used to train a classifier to predict sleep-wake states. Independent training (n = 37) and validation datasets were validation n = 9) datasets were used. Finally, a setup was designed for real-time implementation at the bedside.RESULTS: The macro-averaged area-under-the-receiver-operator-characteristic (AUROC) of the automated sleep staging algorithm ranged between 0.69 and 0.82 for the training data, and 0.61 and 0.78 for the validation data. The algorithm provided the most accurate prediction for wake states (AUROC = 0.80). These findings were well validated on an independent sample (AUROC = 0.77).CONCLUSIONS: With this study, to the best of our knowledge, a reliable, nonobtrusive, and real-time sleep staging algorithm was developed for the first time for preterm infants. Deploying this algorithm in the NICU environment may assist and adapt bedside clinical work based on infants' sleep-wake states, potentially promoting the early brain development and well-being of preterm infants.
AB - STUDY OBJECTIVES: Sleep is an important driver of early brain development. However, sleep is often disturbed in preterm infants admitted to the neonatal intensive care unit (NICU). We aimed to develop an automated algorithm based on routinely measured vital parameters to classify sleep-wake states of preterm infants in real-time at the bedside.METHODS: In this study, sleep-wake state observations were obtained in 1-minute epochs using a behavioral scale developed in-house while vital signs were recorded simultaneously. Three types of vital parameter data, namely, heart rate, respiratory rate, and oxygen saturation, were collected at a low-frequency sampling rate of 0.4 Hz. A supervised machine learning workflow was used to train a classifier to predict sleep-wake states. Independent training (n = 37) and validation datasets were validation n = 9) datasets were used. Finally, a setup was designed for real-time implementation at the bedside.RESULTS: The macro-averaged area-under-the-receiver-operator-characteristic (AUROC) of the automated sleep staging algorithm ranged between 0.69 and 0.82 for the training data, and 0.61 and 0.78 for the validation data. The algorithm provided the most accurate prediction for wake states (AUROC = 0.80). These findings were well validated on an independent sample (AUROC = 0.77).CONCLUSIONS: With this study, to the best of our knowledge, a reliable, nonobtrusive, and real-time sleep staging algorithm was developed for the first time for preterm infants. Deploying this algorithm in the NICU environment may assist and adapt bedside clinical work based on infants' sleep-wake states, potentially promoting the early brain development and well-being of preterm infants.
KW - Algorithm
KW - Algorithms
KW - Hospitalization
KW - Humans
KW - Infant
KW - Infant, Newborn
KW - Infant, Premature/physiology
KW - Intensive Care Units, Neonatal
KW - NICU
KW - Sleep/physiology
KW - automated sleep staging
KW - brain
KW - machine learning
KW - neonatal intensive care
KW - preterm
KW - sleep
UR - http://www.scopus.com/inward/record.url?scp=85139571597&partnerID=8YFLogxK
U2 - 10.1093/sleep/zsac143
DO - 10.1093/sleep/zsac143
M3 - Article
C2 - 35749799
SN - 0161-8105
VL - 45
SP - 1
EP - 11
JO - Sleep
JF - Sleep
IS - 10
M1 - zsac143
ER -