Classification of cardiovascular time series based on different coupling structures using recurrence networks analysis

Gonzalo Marcelo Ramirez Avila, Andrej Gapelyuk, Norbert Marwan, Thomas Walther, Holger Stepan, Juergen Kurths, Niels Wessel*

*Corresponding author for this work

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

We analyse cardiovascular time series with the aim of performing early prediction of preeclampsia (PE), a pregnancy-specific disorder causing maternal and foetal morbidity and mortality. The analysis is made using a novel approach, namely the epsilon-recurrence networks applied to a phase space constructed by means of the time series of the variabilities of the heart rate and the blood pressure (systolic and diastolic). All the possible coupling structures among these variables are considered for the analysis. Network measures such as average path length, mean coreness, global clustering coefficient and scale-local transitivity dimension are computed and constitute the parameters for the subsequent quadratic discriminant analysis. This allows us to predict PE with a sensitivity of 91.7 per cent and a specificity of 68.1 per cent, thus validating the use of this method for classifying healthy and preeclamptic patients.

Original languageEnglish
Article number20110623
Number of pages15
JournalPhilosophical Transactions of the Royal Society A: Mathematical, Physical & Engineering Sciences
Volume371
Issue number1997
Early online date15 Jul 2013
DOIs
Publication statusPublished - 28 Aug 2013

Keywords

  • time-series analysis
  • cardiac dynamics
  • networks and genealogical trees
  • hemodynamics
  • blood flow in cardiovascular system
  • coupling analysis
  • heart-rate-variability
  • predicting preeclampsia
  • complex networks
  • uterine perfusion
  • early-pregnancy
  • blood-pressure
  • systems
  • oscillations
  • threshold
  • causality

Cite this

Classification of cardiovascular time series based on different coupling structures using recurrence networks analysis. / Avila, Gonzalo Marcelo Ramirez; Gapelyuk, Andrej; Marwan, Norbert; Walther, Thomas; Stepan, Holger; Kurths, Juergen; Wessel, Niels.

In: Philosophical Transactions of the Royal Society A: Mathematical, Physical & Engineering Sciences, Vol. 371, No. 1997, 20110623, 28.08.2013.

Research output: Contribution to journalArticle

Avila, Gonzalo Marcelo Ramirez ; Gapelyuk, Andrej ; Marwan, Norbert ; Walther, Thomas ; Stepan, Holger ; Kurths, Juergen ; Wessel, Niels. / Classification of cardiovascular time series based on different coupling structures using recurrence networks analysis. In: Philosophical Transactions of the Royal Society A: Mathematical, Physical & Engineering Sciences. 2013 ; Vol. 371, No. 1997.
@article{dca891da923741a3a986a8be4ac53460,
title = "Classification of cardiovascular time series based on different coupling structures using recurrence networks analysis",
abstract = "We analyse cardiovascular time series with the aim of performing early prediction of preeclampsia (PE), a pregnancy-specific disorder causing maternal and foetal morbidity and mortality. The analysis is made using a novel approach, namely the epsilon-recurrence networks applied to a phase space constructed by means of the time series of the variabilities of the heart rate and the blood pressure (systolic and diastolic). All the possible coupling structures among these variables are considered for the analysis. Network measures such as average path length, mean coreness, global clustering coefficient and scale-local transitivity dimension are computed and constitute the parameters for the subsequent quadratic discriminant analysis. This allows us to predict PE with a sensitivity of 91.7 per cent and a specificity of 68.1 per cent, thus validating the use of this method for classifying healthy and preeclamptic patients.",
keywords = "time-series analysis, cardiac dynamics, networks and genealogical trees, hemodynamics, blood flow in cardiovascular system, coupling analysis, heart-rate-variability, predicting preeclampsia, complex networks, uterine perfusion, early-pregnancy, blood-pressure, systems, oscillations, threshold, causality",
author = "Avila, {Gonzalo Marcelo Ramirez} and Andrej Gapelyuk and Norbert Marwan and Thomas Walther and Holger Stepan and Juergen Kurths and Niels Wessel",
year = "2013",
month = "8",
day = "28",
doi = "10.1098/rsta.2011.0623",
language = "English",
volume = "371",
journal = "Philosophical Transactions of the Royal Society A: Mathematical, Physical & Engineering Sciences",
issn = "1364-503X",
publisher = "Royal Society Publishing",
number = "1997",

}

TY - JOUR

T1 - Classification of cardiovascular time series based on different coupling structures using recurrence networks analysis

AU - Avila, Gonzalo Marcelo Ramirez

AU - Gapelyuk, Andrej

AU - Marwan, Norbert

AU - Walther, Thomas

AU - Stepan, Holger

AU - Kurths, Juergen

AU - Wessel, Niels

PY - 2013/8/28

Y1 - 2013/8/28

N2 - We analyse cardiovascular time series with the aim of performing early prediction of preeclampsia (PE), a pregnancy-specific disorder causing maternal and foetal morbidity and mortality. The analysis is made using a novel approach, namely the epsilon-recurrence networks applied to a phase space constructed by means of the time series of the variabilities of the heart rate and the blood pressure (systolic and diastolic). All the possible coupling structures among these variables are considered for the analysis. Network measures such as average path length, mean coreness, global clustering coefficient and scale-local transitivity dimension are computed and constitute the parameters for the subsequent quadratic discriminant analysis. This allows us to predict PE with a sensitivity of 91.7 per cent and a specificity of 68.1 per cent, thus validating the use of this method for classifying healthy and preeclamptic patients.

AB - We analyse cardiovascular time series with the aim of performing early prediction of preeclampsia (PE), a pregnancy-specific disorder causing maternal and foetal morbidity and mortality. The analysis is made using a novel approach, namely the epsilon-recurrence networks applied to a phase space constructed by means of the time series of the variabilities of the heart rate and the blood pressure (systolic and diastolic). All the possible coupling structures among these variables are considered for the analysis. Network measures such as average path length, mean coreness, global clustering coefficient and scale-local transitivity dimension are computed and constitute the parameters for the subsequent quadratic discriminant analysis. This allows us to predict PE with a sensitivity of 91.7 per cent and a specificity of 68.1 per cent, thus validating the use of this method for classifying healthy and preeclamptic patients.

KW - time-series analysis

KW - cardiac dynamics

KW - networks and genealogical trees

KW - hemodynamics

KW - blood flow in cardiovascular system

KW - coupling analysis

KW - heart-rate-variability

KW - predicting preeclampsia

KW - complex networks

KW - uterine perfusion

KW - early-pregnancy

KW - blood-pressure

KW - systems

KW - oscillations

KW - threshold

KW - causality

U2 - 10.1098/rsta.2011.0623

DO - 10.1098/rsta.2011.0623

M3 - Article

VL - 371

JO - Philosophical Transactions of the Royal Society A: Mathematical, Physical & Engineering Sciences

JF - Philosophical Transactions of the Royal Society A: Mathematical, Physical & Engineering Sciences

SN - 1364-503X

IS - 1997

M1 - 20110623

ER -