Cardiorespiratory Model-Based Data-Driven Approach for Sleep Apnea Detection

Sandeep Gutta, Qi Cheng, Hoa Dinh Nguyen, Bruce Benjamin

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Obstructive sleep apnea (OSA) is a chronic sleep disorder affecting millions of people worldwide. Individuals with OSA are rarely aware of the condition and are often left untreated, which can lead to some serious health problems. Nowadays, several low-cost wearable health sensors are available that can be used to conveniently and noninvasively collect a wide range of physiological signals. In this paper, we propose a new framework for OSA detection in which we combine the wearable sensor measurement signals with the mathematical models of the cardiorespiratory system. Vector-valued Gaussian processes (GPs) are adopted to model the physiological variations among different individuals. The GP covariance is constructed using the sum of separable kernel functions, and the GP hyperparameters are estimated by maximizing the marginal likelihood function. A likelihood ratio test is proposed to detect OSA using the widely available heart rate and peripheral oxygen saturation (SpO2) measurement signals. We conduct experiments on both synthetic and real data to show the effectiveness of the proposed OSA detection framework compared to purely data-driven approaches.

Original languageEnglish
Pages (from-to)1036-1045
Number of pages10
JournalIEEE Journal of Biomedical and Health Informatics
Volume22
Issue number4
DOIs
StatePublished - 1 Jul 2018

Fingerprint

Sleep Apnea Syndromes
Obstructive Sleep Apnea
Likelihood Functions
Health Care Costs
Medical problems
Theoretical Models
Heart Rate
Sleep
Oxygen
Health
Mathematical models
Sensors
Costs
Experiments

Keywords

  • Cardiorespiratory system mathematical model
  • Gaussian process state-space model
  • multimodal sensor fusion
  • sleep apnea detection

Cite this

@article{e3aaa59d678a45f8a240ec1e2cbeddf7,
title = "Cardiorespiratory Model-Based Data-Driven Approach for Sleep Apnea Detection",
abstract = "Obstructive sleep apnea (OSA) is a chronic sleep disorder affecting millions of people worldwide. Individuals with OSA are rarely aware of the condition and are often left untreated, which can lead to some serious health problems. Nowadays, several low-cost wearable health sensors are available that can be used to conveniently and noninvasively collect a wide range of physiological signals. In this paper, we propose a new framework for OSA detection in which we combine the wearable sensor measurement signals with the mathematical models of the cardiorespiratory system. Vector-valued Gaussian processes (GPs) are adopted to model the physiological variations among different individuals. The GP covariance is constructed using the sum of separable kernel functions, and the GP hyperparameters are estimated by maximizing the marginal likelihood function. A likelihood ratio test is proposed to detect OSA using the widely available heart rate and peripheral oxygen saturation (SpO2) measurement signals. We conduct experiments on both synthetic and real data to show the effectiveness of the proposed OSA detection framework compared to purely data-driven approaches.",
keywords = "Cardiorespiratory system mathematical model, Gaussian process state-space model, multimodal sensor fusion, sleep apnea detection",
author = "Sandeep Gutta and Qi Cheng and Nguyen, {Hoa Dinh} and Bruce Benjamin",
year = "2018",
month = "7",
day = "1",
doi = "10.1109/JBHI.2017.2740120",
language = "English",
volume = "22",
pages = "1036--1045",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

Cardiorespiratory Model-Based Data-Driven Approach for Sleep Apnea Detection. / Gutta, Sandeep; Cheng, Qi; Nguyen, Hoa Dinh; Benjamin, Bruce.

In: IEEE Journal of Biomedical and Health Informatics, Vol. 22, No. 4, 01.07.2018, p. 1036-1045.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Cardiorespiratory Model-Based Data-Driven Approach for Sleep Apnea Detection

AU - Gutta, Sandeep

AU - Cheng, Qi

AU - Nguyen, Hoa Dinh

AU - Benjamin, Bruce

PY - 2018/7/1

Y1 - 2018/7/1

N2 - Obstructive sleep apnea (OSA) is a chronic sleep disorder affecting millions of people worldwide. Individuals with OSA are rarely aware of the condition and are often left untreated, which can lead to some serious health problems. Nowadays, several low-cost wearable health sensors are available that can be used to conveniently and noninvasively collect a wide range of physiological signals. In this paper, we propose a new framework for OSA detection in which we combine the wearable sensor measurement signals with the mathematical models of the cardiorespiratory system. Vector-valued Gaussian processes (GPs) are adopted to model the physiological variations among different individuals. The GP covariance is constructed using the sum of separable kernel functions, and the GP hyperparameters are estimated by maximizing the marginal likelihood function. A likelihood ratio test is proposed to detect OSA using the widely available heart rate and peripheral oxygen saturation (SpO2) measurement signals. We conduct experiments on both synthetic and real data to show the effectiveness of the proposed OSA detection framework compared to purely data-driven approaches.

AB - Obstructive sleep apnea (OSA) is a chronic sleep disorder affecting millions of people worldwide. Individuals with OSA are rarely aware of the condition and are often left untreated, which can lead to some serious health problems. Nowadays, several low-cost wearable health sensors are available that can be used to conveniently and noninvasively collect a wide range of physiological signals. In this paper, we propose a new framework for OSA detection in which we combine the wearable sensor measurement signals with the mathematical models of the cardiorespiratory system. Vector-valued Gaussian processes (GPs) are adopted to model the physiological variations among different individuals. The GP covariance is constructed using the sum of separable kernel functions, and the GP hyperparameters are estimated by maximizing the marginal likelihood function. A likelihood ratio test is proposed to detect OSA using the widely available heart rate and peripheral oxygen saturation (SpO2) measurement signals. We conduct experiments on both synthetic and real data to show the effectiveness of the proposed OSA detection framework compared to purely data-driven approaches.

KW - Cardiorespiratory system mathematical model

KW - Gaussian process state-space model

KW - multimodal sensor fusion

KW - sleep apnea detection

UR - http://www.scopus.com/inward/record.url?scp=85028416529&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2017.2740120

DO - 10.1109/JBHI.2017.2740120

M3 - Article

C2 - 28816683

AN - SCOPUS:85028416529

VL - 22

SP - 1036

EP - 1045

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 4

ER -