Regularity analysis of nocturnal oximetry recordings to assist in the diagnosis of sleep apnoea syndrome

J. Víctor Marcos, Roberto Hornero, Ian T. Nabney, Daniel Álvarez, Gonzalo C. Gutiérrez-Tobal, Félix del Campo

Research output: Contribution to journalArticle

Abstract

The relationship between sleep apnoea–hypopnoea syndrome (SAHS) severity and the regularity of nocturnal oxygen saturation (SaO2) recordings was analysed. Three different methods were proposed to quantify regularity: approximate entropy (AEn), sample entropy (SEn) and kernel entropy (KEn). A total of 240 subjects suspected of suffering from SAHS took part in the study. They were randomly divided into a training set (96 subjects) and a test set (144 subjects) for the adjustment and assessment of the proposed methods, respectively. According to the measurements provided by AEn, SEn and KEn, higher irregularity of oximetry signals is associated with SAHS-positive patients. Receiver operating characteristic (ROC) and Pearson correlation analyses showed that KEn was the most reliable predictor of SAHS. It provided an area under the ROC curve of 0.91 in two-class classification of subjects as SAHS-negative or SAHS-positive. Moreover, KEn measurements from oximetry data exhibited a linear dependence on the apnoea–hypopnoea index, as shown by a correlation coefficient of 0.87. Therefore, these measurements could be used for the development of simplified diagnostic techniques in order to reduce the demand for polysomnographies. Furthermore, KEn represents a convincing alternative to AEn and SEn for the diagnostic analysis of noisy biomedical signals.
Original languageEnglish
Pages (from-to)216-224
Number of pages9
JournalMedical Engineering and Physics
Volume38
Issue number3
Early online date21 Dec 2015
DOIs
Publication statusPublished - Mar 2016

Fingerprint

Oximetry
Sleep
Sleep Apnea Syndromes
Entropy
Regularity
Approximate Entropy
kernel
Diagnostics
ROC Curve
Pearson Correlation
Linear dependence
Operating Characteristics
Receiver Operating Characteristic Curve
Irregularity
Correlation coefficient
Social Adjustment
Saturation
Oxygen
Predictors
Polysomnography

Bibliographical note

© 2016, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/

Keywords

  • oxygen saturation
  • entropy rate
  • approximate entropy
  • sample entropy
  • kernel entropy
  • density estimation

Cite this

Marcos, J. V., Hornero, R., Nabney, I. T., Álvarez, D., Gutiérrez-Tobal, G. C., & del Campo, F. (2016). Regularity analysis of nocturnal oximetry recordings to assist in the diagnosis of sleep apnoea syndrome. Medical Engineering and Physics, 38(3), 216-224. https://doi.org/10.1016/j.medengphy.2015.11.010
Marcos, J. Víctor ; Hornero, Roberto ; Nabney, Ian T. ; Álvarez, Daniel ; Gutiérrez-Tobal, Gonzalo C. ; del Campo, Félix. / Regularity analysis of nocturnal oximetry recordings to assist in the diagnosis of sleep apnoea syndrome. In: Medical Engineering and Physics. 2016 ; Vol. 38, No. 3. pp. 216-224.
@article{248873d8aee94d2ba699408a038a76ec,
title = "Regularity analysis of nocturnal oximetry recordings to assist in the diagnosis of sleep apnoea syndrome",
abstract = "The relationship between sleep apnoea–hypopnoea syndrome (SAHS) severity and the regularity of nocturnal oxygen saturation (SaO2) recordings was analysed. Three different methods were proposed to quantify regularity: approximate entropy (AEn), sample entropy (SEn) and kernel entropy (KEn). A total of 240 subjects suspected of suffering from SAHS took part in the study. They were randomly divided into a training set (96 subjects) and a test set (144 subjects) for the adjustment and assessment of the proposed methods, respectively. According to the measurements provided by AEn, SEn and KEn, higher irregularity of oximetry signals is associated with SAHS-positive patients. Receiver operating characteristic (ROC) and Pearson correlation analyses showed that KEn was the most reliable predictor of SAHS. It provided an area under the ROC curve of 0.91 in two-class classification of subjects as SAHS-negative or SAHS-positive. Moreover, KEn measurements from oximetry data exhibited a linear dependence on the apnoea–hypopnoea index, as shown by a correlation coefficient of 0.87. Therefore, these measurements could be used for the development of simplified diagnostic techniques in order to reduce the demand for polysomnographies. Furthermore, KEn represents a convincing alternative to AEn and SEn for the diagnostic analysis of noisy biomedical signals.",
keywords = "oxygen saturation, entropy rate, approximate entropy, sample entropy, kernel entropy, density estimation",
author = "Marcos, {J. V{\'i}ctor} and Roberto Hornero and Nabney, {Ian T.} and Daniel {\'A}lvarez and Guti{\'e}rrez-Tobal, {Gonzalo C.} and {del Campo}, F{\'e}lix",
note = "{\circledC} 2016, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/",
year = "2016",
month = "3",
doi = "10.1016/j.medengphy.2015.11.010",
language = "English",
volume = "38",
pages = "216--224",
journal = "Medical Engineering and Physics",
issn = "1350-4533",
publisher = "Elsevier",
number = "3",

}

Marcos, JV, Hornero, R, Nabney, IT, Álvarez, D, Gutiérrez-Tobal, GC & del Campo, F 2016, 'Regularity analysis of nocturnal oximetry recordings to assist in the diagnosis of sleep apnoea syndrome', Medical Engineering and Physics, vol. 38, no. 3, pp. 216-224. https://doi.org/10.1016/j.medengphy.2015.11.010

Regularity analysis of nocturnal oximetry recordings to assist in the diagnosis of sleep apnoea syndrome. / Marcos, J. Víctor; Hornero, Roberto; Nabney, Ian T.; Álvarez, Daniel; Gutiérrez-Tobal, Gonzalo C.; del Campo, Félix.

In: Medical Engineering and Physics, Vol. 38, No. 3, 03.2016, p. 216-224.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Regularity analysis of nocturnal oximetry recordings to assist in the diagnosis of sleep apnoea syndrome

AU - Marcos, J. Víctor

AU - Hornero, Roberto

AU - Nabney, Ian T.

AU - Álvarez, Daniel

AU - Gutiérrez-Tobal, Gonzalo C.

AU - del Campo, Félix

N1 - © 2016, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/

PY - 2016/3

Y1 - 2016/3

N2 - The relationship between sleep apnoea–hypopnoea syndrome (SAHS) severity and the regularity of nocturnal oxygen saturation (SaO2) recordings was analysed. Three different methods were proposed to quantify regularity: approximate entropy (AEn), sample entropy (SEn) and kernel entropy (KEn). A total of 240 subjects suspected of suffering from SAHS took part in the study. They were randomly divided into a training set (96 subjects) and a test set (144 subjects) for the adjustment and assessment of the proposed methods, respectively. According to the measurements provided by AEn, SEn and KEn, higher irregularity of oximetry signals is associated with SAHS-positive patients. Receiver operating characteristic (ROC) and Pearson correlation analyses showed that KEn was the most reliable predictor of SAHS. It provided an area under the ROC curve of 0.91 in two-class classification of subjects as SAHS-negative or SAHS-positive. Moreover, KEn measurements from oximetry data exhibited a linear dependence on the apnoea–hypopnoea index, as shown by a correlation coefficient of 0.87. Therefore, these measurements could be used for the development of simplified diagnostic techniques in order to reduce the demand for polysomnographies. Furthermore, KEn represents a convincing alternative to AEn and SEn for the diagnostic analysis of noisy biomedical signals.

AB - The relationship between sleep apnoea–hypopnoea syndrome (SAHS) severity and the regularity of nocturnal oxygen saturation (SaO2) recordings was analysed. Three different methods were proposed to quantify regularity: approximate entropy (AEn), sample entropy (SEn) and kernel entropy (KEn). A total of 240 subjects suspected of suffering from SAHS took part in the study. They were randomly divided into a training set (96 subjects) and a test set (144 subjects) for the adjustment and assessment of the proposed methods, respectively. According to the measurements provided by AEn, SEn and KEn, higher irregularity of oximetry signals is associated with SAHS-positive patients. Receiver operating characteristic (ROC) and Pearson correlation analyses showed that KEn was the most reliable predictor of SAHS. It provided an area under the ROC curve of 0.91 in two-class classification of subjects as SAHS-negative or SAHS-positive. Moreover, KEn measurements from oximetry data exhibited a linear dependence on the apnoea–hypopnoea index, as shown by a correlation coefficient of 0.87. Therefore, these measurements could be used for the development of simplified diagnostic techniques in order to reduce the demand for polysomnographies. Furthermore, KEn represents a convincing alternative to AEn and SEn for the diagnostic analysis of noisy biomedical signals.

KW - oxygen saturation

KW - entropy rate

KW - approximate entropy

KW - sample entropy

KW - kernel entropy

KW - density estimation

UR - http://www.scopus.com/inward/record.url?scp=84958942756&partnerID=8YFLogxK

U2 - 10.1016/j.medengphy.2015.11.010

DO - 10.1016/j.medengphy.2015.11.010

M3 - Article

VL - 38

SP - 216

EP - 224

JO - Medical Engineering and Physics

JF - Medical Engineering and Physics

SN - 1350-4533

IS - 3

ER -