Multi-Task Gaussian Process Regression for the Detection of Sleep Cycles in Premature Infants

Nele Brugge; Jan Graßhoff; Arne Weigenand; Philipp Rostalski

doi:10.1109/ICASSP43922.2022.9747086

Multi-Task Gaussian Process Regression for the Detection of Sleep Cycles in Premature Infants

Nele Brugge, Jan Graßhoff, Arne Weigenand, Philipp Rostalski

Dräger Medical

1 Citation (Scopus)

Abstract

Preterm birth is the leading cause of infant mortality. Consequently, preterm infants require special attention and medical care, with sleep being a central element for the development of cognitive functions. Studies on neonatal sleep suggest that the pattern of their sleep stages is determined by an endogenous ultradian rhythm, superimposed by other rhythms and external influences. In this article, we propose the use of multi-task Gaussian process regression as a flexible nonparametric approach to analyze this kind of sleep data while incorporating prior knowledge, such as of correlations between signals, signal periodicity, information from manual annotations and certain other signal properties. As a result of the regression of heart and respiratory rate data of preterm infants, ultradian rhythms with a period of 58±5min could be extracted. Together with other model parameters, knowledge about the characteristics of ultradian rhythms potentially provides insights into the maturational and health status of the preterm infants. These, in turn, could be used to optimize the care of critically ill patients.

Original language	English
Title of host publication	Proceedings of ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing
Publisher	IEEE
Publication date	27.04.2022
DOIs	https://doi.org/10.1109/ICASSP43922.2022.9747086
Publication status	Published - 27.04.2022
Event	2022 IEEE International Conference on Acoustics, Speech and Signal Processing - , Singapore Duration: 23.05.2022 → 27.05.2022 https://ieeexplore.ieee.org/xpl/conhome/9745891/proceeding

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being
SDG 4 Quality Education
SDG 9 Industry, Innovation, and Infrastructure
SDG 11 Sustainable Cities and Communities
SDG 12 Responsible Consumption and Production
SDG 14 Life Below Water
SDG 15 Life on Land

Research Areas and Centers

Centers: Center for Artificial Intelligence Luebeck (ZKIL)

Access to Document

10.1109/ICASSP43922.2022.9747086

Cite this

@inproceedings{a95e1f44b0654f5685b3088dd6a2dfeb,

title = "Multi-Task Gaussian Process Regression for the Detection of Sleep Cycles in Premature Infants",

abstract = "Preterm birth is the leading cause of infant mortality. Consequently, preterm infants require special attention and medical care, with sleep being a central element for the development of cognitive functions. Studies on neonatal sleep suggest that the pattern of their sleep stages is determined by an endogenous ultradian rhythm, superimposed by other rhythms and external influences. In this article, we propose the use of multi-task Gaussian process regression as a flexible nonparametric approach to analyze this kind of sleep data while incorporating prior knowledge, such as of correlations between signals, signal periodicity, information from manual annotations and certain other signal properties. As a result of the regression of heart and respiratory rate data of preterm infants, ultradian rhythms with a period of 58±5min could be extracted. Together with other model parameters, knowledge about the characteristics of ultradian rhythms potentially provides insights into the maturational and health status of the preterm infants. These, in turn, could be used to optimize the care of critically ill patients.",

author = "Nele Brugge and Jan Gra{\ss}hoff and Arne Weigenand and Philipp Rostalski",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE; 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022 ; Conference date: 23-05-2022 Through 27-05-2022",

year = "2022",

month = apr,

day = "27",

doi = "10.1109/ICASSP43922.2022.9747086",

language = "English",

booktitle = "Proceedings of ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing",

publisher = "IEEE",

url = "https://ieeexplore.ieee.org/xpl/conhome/9745891/proceeding",

}

Brugge, N, Graßhoff, J, Weigenand, A & Rostalski, P 2022, Multi-Task Gaussian Process Regression for the Detection of Sleep Cycles in Premature Infants. in Proceedings of ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, Singapore, 23.05.22. https://doi.org/10.1109/ICASSP43922.2022.9747086

Multi-Task Gaussian Process Regression for the Detection of Sleep Cycles in Premature Infants. / Brugge, Nele; Graßhoff, Jan; Weigenand, Arne et al.
Proceedings of ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, 2022.

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Multi-Task Gaussian Process Regression for the Detection of Sleep Cycles in Premature Infants

AU - Brugge, Nele

AU - Graßhoff, Jan

AU - Weigenand, Arne

AU - Rostalski, Philipp

PY - 2022/4/27

Y1 - 2022/4/27

N2 - Preterm birth is the leading cause of infant mortality. Consequently, preterm infants require special attention and medical care, with sleep being a central element for the development of cognitive functions. Studies on neonatal sleep suggest that the pattern of their sleep stages is determined by an endogenous ultradian rhythm, superimposed by other rhythms and external influences. In this article, we propose the use of multi-task Gaussian process regression as a flexible nonparametric approach to analyze this kind of sleep data while incorporating prior knowledge, such as of correlations between signals, signal periodicity, information from manual annotations and certain other signal properties. As a result of the regression of heart and respiratory rate data of preterm infants, ultradian rhythms with a period of 58±5min could be extracted. Together with other model parameters, knowledge about the characteristics of ultradian rhythms potentially provides insights into the maturational and health status of the preterm infants. These, in turn, could be used to optimize the care of critically ill patients.

AB - Preterm birth is the leading cause of infant mortality. Consequently, preterm infants require special attention and medical care, with sleep being a central element for the development of cognitive functions. Studies on neonatal sleep suggest that the pattern of their sleep stages is determined by an endogenous ultradian rhythm, superimposed by other rhythms and external influences. In this article, we propose the use of multi-task Gaussian process regression as a flexible nonparametric approach to analyze this kind of sleep data while incorporating prior knowledge, such as of correlations between signals, signal periodicity, information from manual annotations and certain other signal properties. As a result of the regression of heart and respiratory rate data of preterm infants, ultradian rhythms with a period of 58±5min could be extracted. Together with other model parameters, knowledge about the characteristics of ultradian rhythms potentially provides insights into the maturational and health status of the preterm infants. These, in turn, could be used to optimize the care of critically ill patients.

UR - https://ieeexplore.ieee.org/document/9747086

U2 - 10.1109/ICASSP43922.2022.9747086

DO - 10.1109/ICASSP43922.2022.9747086

M3 - Conference contribution

BT - Proceedings of ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing

PB - IEEE

T2 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing

Y2 - 23 May 2022 through 27 May 2022

ER -

Multi-Task Gaussian Process Regression for the Detection of Sleep Cycles in Premature Infants

Abstract

UN SDGs

Research Areas and Centers

Access to Document

Other files and links

Fingerprint

Cite this