Analysis of nocturnal oxygen saturation recordings using kernel entropy to assist in sleep apnea-hypopnea diagnosis

J. Victor Marcos, Roberto Hornero, Ian T. Nabney, Daniel Álvarez, Félix del Campo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this study, a new entropy measure known as kernel entropy (KerEnt), which quantifies the irregularity in a series, was applied to nocturnal oxygen saturation (SaO 2) recordings. A total of 96 subjects suspected of suffering from sleep apnea-hypopnea syndrome (SAHS) took part in the study: 32 SAHS-negative and 64 SAHS-positive subjects. Their SaO 2 signals were separately processed by means of KerEnt. Our results show that a higher degree of irregularity is associated to SAHS-positive subjects. Statistical analysis revealed significant differences between the KerEnt values of SAHS-negative and SAHS-positive groups. The diagnostic utility of this parameter was studied by means of receiver operating characteristic (ROC) analysis. A classification accuracy of 81.25% (81.25% sensitivity and 81.25% specificity) was achieved. Repeated apneas during sleep increase irregularity in SaO 2 data. This effect can be measured by KerEnt in order to detect SAHS. This non-linear measure can provide useful information for the development of alternative diagnostic techniques in order to reduce the demand for conventional polysomnography (PSG).

Original languageEnglish
Title of host publicationAnnual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC, 2011
PublisherIEEE
Pages1745-1748
Number of pages4
ISBN (Electronic)978-1-4244-4122-8
ISBN (Print)978-1-4244-4121-1
DOIs
Publication statusPublished - 2011
Event33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Boston (MA), United States
Duration: 30 Aug 20113 Sep 2011

Publication series

NameConference proceedings IEEE Engineering in Medicine and Biology Society
PublisherIEEE
ISSN (Print)1557-170X

Conference

Conference33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Abbreviated titleEMBC ’11
CountryUnited States
CityBoston (MA)
Period30/08/113/09/11

Fingerprint

Sleep Apnea Syndromes
Entropy
Obstructive Sleep Apnea
Oxygen
Polysomnography
Sleep
ROC Curve
Statistical methods
Sensitivity and Specificity

Keywords

  • kernel entropy
  • bayesian

Cite this

Marcos, J. V., Hornero, R., Nabney, I. T., Álvarez, D., & del Campo, F. (2011). Analysis of nocturnal oxygen saturation recordings using kernel entropy to assist in sleep apnea-hypopnea diagnosis. In Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC, 2011 (pp. 1745-1748). (Conference proceedings IEEE Engineering in Medicine and Biology Society). IEEE. https://doi.org/10.1109/IEMBS.2011.6090499
Marcos, J. Victor ; Hornero, Roberto ; Nabney, Ian T. ; Álvarez, Daniel ; del Campo, Félix. / Analysis of nocturnal oxygen saturation recordings using kernel entropy to assist in sleep apnea-hypopnea diagnosis. Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC, 2011. IEEE, 2011. pp. 1745-1748 (Conference proceedings IEEE Engineering in Medicine and Biology Society).
@inproceedings{f9258333e6f4467ea02387ba629ac846,
title = "Analysis of nocturnal oxygen saturation recordings using kernel entropy to assist in sleep apnea-hypopnea diagnosis",
abstract = "In this study, a new entropy measure known as kernel entropy (KerEnt), which quantifies the irregularity in a series, was applied to nocturnal oxygen saturation (SaO 2) recordings. A total of 96 subjects suspected of suffering from sleep apnea-hypopnea syndrome (SAHS) took part in the study: 32 SAHS-negative and 64 SAHS-positive subjects. Their SaO 2 signals were separately processed by means of KerEnt. Our results show that a higher degree of irregularity is associated to SAHS-positive subjects. Statistical analysis revealed significant differences between the KerEnt values of SAHS-negative and SAHS-positive groups. The diagnostic utility of this parameter was studied by means of receiver operating characteristic (ROC) analysis. A classification accuracy of 81.25{\%} (81.25{\%} sensitivity and 81.25{\%} specificity) was achieved. Repeated apneas during sleep increase irregularity in SaO 2 data. This effect can be measured by KerEnt in order to detect SAHS. This non-linear measure can provide useful information for the development of alternative diagnostic techniques in order to reduce the demand for conventional polysomnography (PSG).",
keywords = "kernel entropy, bayesian",
author = "Marcos, {J. Victor} and Roberto Hornero and Nabney, {Ian T.} and Daniel {\'A}lvarez and {del Campo}, F{\'e}lix",
note = "MEDLINE{\circledR} is the source for the citation and abstract of this record.",
year = "2011",
doi = "10.1109/IEMBS.2011.6090499",
language = "English",
isbn = "978-1-4244-4121-1",
series = "Conference proceedings IEEE Engineering in Medicine and Biology Society",
publisher = "IEEE",
pages = "1745--1748",
booktitle = "Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC, 2011",
address = "United States",

}

Marcos, JV, Hornero, R, Nabney, IT, Álvarez, D & del Campo, F 2011, Analysis of nocturnal oxygen saturation recordings using kernel entropy to assist in sleep apnea-hypopnea diagnosis. in Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC, 2011. Conference proceedings IEEE Engineering in Medicine and Biology Society, IEEE, pp. 1745-1748, 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Boston (MA), United States, 30/08/11. https://doi.org/10.1109/IEMBS.2011.6090499

Analysis of nocturnal oxygen saturation recordings using kernel entropy to assist in sleep apnea-hypopnea diagnosis. / Marcos, J. Victor; Hornero, Roberto; Nabney, Ian T.; Álvarez, Daniel; del Campo, Félix.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC, 2011. IEEE, 2011. p. 1745-1748 (Conference proceedings IEEE Engineering in Medicine and Biology Society).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Analysis of nocturnal oxygen saturation recordings using kernel entropy to assist in sleep apnea-hypopnea diagnosis

AU - Marcos, J. Victor

AU - Hornero, Roberto

AU - Nabney, Ian T.

AU - Álvarez, Daniel

AU - del Campo, Félix

N1 - MEDLINE® is the source for the citation and abstract of this record.

PY - 2011

Y1 - 2011

N2 - In this study, a new entropy measure known as kernel entropy (KerEnt), which quantifies the irregularity in a series, was applied to nocturnal oxygen saturation (SaO 2) recordings. A total of 96 subjects suspected of suffering from sleep apnea-hypopnea syndrome (SAHS) took part in the study: 32 SAHS-negative and 64 SAHS-positive subjects. Their SaO 2 signals were separately processed by means of KerEnt. Our results show that a higher degree of irregularity is associated to SAHS-positive subjects. Statistical analysis revealed significant differences between the KerEnt values of SAHS-negative and SAHS-positive groups. The diagnostic utility of this parameter was studied by means of receiver operating characteristic (ROC) analysis. A classification accuracy of 81.25% (81.25% sensitivity and 81.25% specificity) was achieved. Repeated apneas during sleep increase irregularity in SaO 2 data. This effect can be measured by KerEnt in order to detect SAHS. This non-linear measure can provide useful information for the development of alternative diagnostic techniques in order to reduce the demand for conventional polysomnography (PSG).

AB - In this study, a new entropy measure known as kernel entropy (KerEnt), which quantifies the irregularity in a series, was applied to nocturnal oxygen saturation (SaO 2) recordings. A total of 96 subjects suspected of suffering from sleep apnea-hypopnea syndrome (SAHS) took part in the study: 32 SAHS-negative and 64 SAHS-positive subjects. Their SaO 2 signals were separately processed by means of KerEnt. Our results show that a higher degree of irregularity is associated to SAHS-positive subjects. Statistical analysis revealed significant differences between the KerEnt values of SAHS-negative and SAHS-positive groups. The diagnostic utility of this parameter was studied by means of receiver operating characteristic (ROC) analysis. A classification accuracy of 81.25% (81.25% sensitivity and 81.25% specificity) was achieved. Repeated apneas during sleep increase irregularity in SaO 2 data. This effect can be measured by KerEnt in order to detect SAHS. This non-linear measure can provide useful information for the development of alternative diagnostic techniques in order to reduce the demand for conventional polysomnography (PSG).

KW - kernel entropy

KW - bayesian

UR - http://www.scopus.com/inward/record.url?scp=84862263291&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/record.url?scp=84055190459&partnerID=8YFLogxK

U2 - 10.1109/IEMBS.2011.6090499

DO - 10.1109/IEMBS.2011.6090499

M3 - Conference contribution

SN - 978-1-4244-4121-1

T3 - Conference proceedings IEEE Engineering in Medicine and Biology Society

SP - 1745

EP - 1748

BT - Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC, 2011

PB - IEEE

ER -

Marcos JV, Hornero R, Nabney IT, Álvarez D, del Campo F. Analysis of nocturnal oxygen saturation recordings using kernel entropy to assist in sleep apnea-hypopnea diagnosis. In Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC, 2011. IEEE. 2011. p. 1745-1748. (Conference proceedings IEEE Engineering in Medicine and Biology Society). https://doi.org/10.1109/IEMBS.2011.6090499