An online sleep apnea detection method based on recurrence quantification analysis

Hoa Dinh Nguyen, Brek A. Wilkins, Qi Cheng, Bruce Allen Benjamin

Research output: Contribution to journalArticle

39 Citations (Scopus)

Abstract

This paper introduces an online sleep apnea detection method based on heart rate complexity as measured by recurrence quantification analysis (RQA) statistics of heart rate variability (HRV) data. RQA statistics can capture nonlinear dynamics of a complex cardiorespiratory system during obstructive sleep apnea. In order to obtain a more robust measurement of the nonstationarity of the cardiorespiratory system, we use different fixed amount of neighbor thresholdings for recurrence plot calculation. We integrate a feature selection algorithm based on conditional mutual information to select the most informative RQA features for classification, and hence, to speed up the real-time classification process without degrading the performance of the system. Two types of binary classifiers, i.e., support vector machine and neural network, are used to differentiate apnea from normal sleep. A soft decision fusion rule is developed to combine the results of these classifiers in order to improve the classification performance of the whole system. Experimental results show that our proposed method achieves better classification results compared with the previous recurrence analysis-based approach. We also show that our method is flexible and a strong candidate for a real efficient sleep apnea detection system.

Original languageEnglish
Article number6676792
Pages (from-to)1285-1293
Number of pages9
JournalIEEE Journal of Biomedical and Health Informatics
Volume18
Issue number4
DOIs
StatePublished - Jul 2014

Fingerprint

Sleep Apnea Syndromes
Recurrence
Classifiers
Statistics
Heart Rate
Nonlinear Dynamics
Support vector machines
Large scale systems
Feature extraction
Obstructive Sleep Apnea
Fusion reactions
Neural networks
Sleep

Keywords

  • Feature selection
  • recurrence quantification analysis (RQA)
  • sleep apnea detection
  • soft decision fusion

Cite this

@article{423bba0c551c417c979630df28251998,
title = "An online sleep apnea detection method based on recurrence quantification analysis",
abstract = "This paper introduces an online sleep apnea detection method based on heart rate complexity as measured by recurrence quantification analysis (RQA) statistics of heart rate variability (HRV) data. RQA statistics can capture nonlinear dynamics of a complex cardiorespiratory system during obstructive sleep apnea. In order to obtain a more robust measurement of the nonstationarity of the cardiorespiratory system, we use different fixed amount of neighbor thresholdings for recurrence plot calculation. We integrate a feature selection algorithm based on conditional mutual information to select the most informative RQA features for classification, and hence, to speed up the real-time classification process without degrading the performance of the system. Two types of binary classifiers, i.e., support vector machine and neural network, are used to differentiate apnea from normal sleep. A soft decision fusion rule is developed to combine the results of these classifiers in order to improve the classification performance of the whole system. Experimental results show that our proposed method achieves better classification results compared with the previous recurrence analysis-based approach. We also show that our method is flexible and a strong candidate for a real efficient sleep apnea detection system.",
keywords = "Feature selection, recurrence quantification analysis (RQA), sleep apnea detection, soft decision fusion",
author = "Nguyen, {Hoa Dinh} and Wilkins, {Brek A.} and Qi Cheng and Benjamin, {Bruce Allen}",
year = "2014",
month = "7",
doi = "10.1109/JBHI.2013.2292928",
language = "English",
volume = "18",
pages = "1285--1293",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

An online sleep apnea detection method based on recurrence quantification analysis. / Nguyen, Hoa Dinh; Wilkins, Brek A.; Cheng, Qi; Benjamin, Bruce Allen.

In: IEEE Journal of Biomedical and Health Informatics, Vol. 18, No. 4, 6676792, 07.2014, p. 1285-1293.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An online sleep apnea detection method based on recurrence quantification analysis

AU - Nguyen, Hoa Dinh

AU - Wilkins, Brek A.

AU - Cheng, Qi

AU - Benjamin, Bruce Allen

PY - 2014/7

Y1 - 2014/7

N2 - This paper introduces an online sleep apnea detection method based on heart rate complexity as measured by recurrence quantification analysis (RQA) statistics of heart rate variability (HRV) data. RQA statistics can capture nonlinear dynamics of a complex cardiorespiratory system during obstructive sleep apnea. In order to obtain a more robust measurement of the nonstationarity of the cardiorespiratory system, we use different fixed amount of neighbor thresholdings for recurrence plot calculation. We integrate a feature selection algorithm based on conditional mutual information to select the most informative RQA features for classification, and hence, to speed up the real-time classification process without degrading the performance of the system. Two types of binary classifiers, i.e., support vector machine and neural network, are used to differentiate apnea from normal sleep. A soft decision fusion rule is developed to combine the results of these classifiers in order to improve the classification performance of the whole system. Experimental results show that our proposed method achieves better classification results compared with the previous recurrence analysis-based approach. We also show that our method is flexible and a strong candidate for a real efficient sleep apnea detection system.

AB - This paper introduces an online sleep apnea detection method based on heart rate complexity as measured by recurrence quantification analysis (RQA) statistics of heart rate variability (HRV) data. RQA statistics can capture nonlinear dynamics of a complex cardiorespiratory system during obstructive sleep apnea. In order to obtain a more robust measurement of the nonstationarity of the cardiorespiratory system, we use different fixed amount of neighbor thresholdings for recurrence plot calculation. We integrate a feature selection algorithm based on conditional mutual information to select the most informative RQA features for classification, and hence, to speed up the real-time classification process without degrading the performance of the system. Two types of binary classifiers, i.e., support vector machine and neural network, are used to differentiate apnea from normal sleep. A soft decision fusion rule is developed to combine the results of these classifiers in order to improve the classification performance of the whole system. Experimental results show that our proposed method achieves better classification results compared with the previous recurrence analysis-based approach. We also show that our method is flexible and a strong candidate for a real efficient sleep apnea detection system.

KW - Feature selection

KW - recurrence quantification analysis (RQA)

KW - sleep apnea detection

KW - soft decision fusion

UR - http://www.scopus.com/inward/record.url?scp=84904292837&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2013.2292928

DO - 10.1109/JBHI.2013.2292928

M3 - Article

C2 - 25014935

AN - SCOPUS:84904292837

VL - 18

SP - 1285

EP - 1293

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 4

M1 - 6676792

ER -