Classifying healthy women and preeclamptic patients from cardiovascular data using recurrence and complex network methods

G. M. Ramirez Avila, A. Gapelyuk, N. Marwan, H. Stepan, J. Kurths, Th Walther, N. Wessel*

*Corresponding author for this work

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

It is urgently aimed in prenatal medicine to identify pregnancies, which develop life-threatening preeclampsia prior to the manifestation of the disease. Here, we use recurrence-based methods to distinguish such pregnancies already in the second trimester, using the following cardiovascular time series: the variability of heart rate and systolic and diastolic blood pressures. We perform recurrence quantification analysis (RQA), in addition to a novel approach, & recurrence networks, applied to a phase space constructed by means of these time series. We examine all possible coupling structures in a phase space constructed with the above-mentioned biosignals. Several measures including recurrence rate, determinism, laminarity, trapping time, and longest diagonal and vertical lines for the recurrence quantification analysis and average path length, mean coreness, global clustering coefficient, assortativity, and scale local transitivity dimension for the network measures are considered as parameters for our analysis. With these quantities, we perform a quadratic discriminant analysis that allows us to classify healthy pregnancies and upcoming preeclamptic patients with a sensitivity of 91.7% and a specificity of 45.8% in the case of RQA and 91.7% and 68% when using &recurrence networks, respectively. (C) 2013 Elsevier B.V. All rights reserved.

Original languageEnglish
Pages (from-to)103-110
Number of pages8
JournalAutonomic Neuroscience: Basic & Clinical
Volume178
Issue number1-2
Early online date30 May 2013
DOIs
Publication statusPublished - Nov 2013

Keywords

  • heart rate
  • blood pressure
  • cardiac dynamics
  • preeclampsia
  • recurrences
  • networks
  • time series analysis
  • time-series
  • variability
  • plots

Cite this

Classifying healthy women and preeclamptic patients from cardiovascular data using recurrence and complex network methods. / Ramirez Avila, G. M.; Gapelyuk, A.; Marwan, N.; Stepan, H.; Kurths, J.; Walther, Th; Wessel, N.

In: Autonomic Neuroscience: Basic & Clinical, Vol. 178, No. 1-2, 11.2013, p. 103-110.

Research output: Contribution to journalArticle

Ramirez Avila, G. M. ; Gapelyuk, A. ; Marwan, N. ; Stepan, H. ; Kurths, J. ; Walther, Th ; Wessel, N. / Classifying healthy women and preeclamptic patients from cardiovascular data using recurrence and complex network methods. In: Autonomic Neuroscience: Basic & Clinical. 2013 ; Vol. 178, No. 1-2. pp. 103-110.
@article{288e7ab688af4f169ace9b0ae7d00ccc,
title = "Classifying healthy women and preeclamptic patients from cardiovascular data using recurrence and complex network methods",
abstract = "It is urgently aimed in prenatal medicine to identify pregnancies, which develop life-threatening preeclampsia prior to the manifestation of the disease. Here, we use recurrence-based methods to distinguish such pregnancies already in the second trimester, using the following cardiovascular time series: the variability of heart rate and systolic and diastolic blood pressures. We perform recurrence quantification analysis (RQA), in addition to a novel approach, & recurrence networks, applied to a phase space constructed by means of these time series. We examine all possible coupling structures in a phase space constructed with the above-mentioned biosignals. Several measures including recurrence rate, determinism, laminarity, trapping time, and longest diagonal and vertical lines for the recurrence quantification analysis and average path length, mean coreness, global clustering coefficient, assortativity, and scale local transitivity dimension for the network measures are considered as parameters for our analysis. With these quantities, we perform a quadratic discriminant analysis that allows us to classify healthy pregnancies and upcoming preeclamptic patients with a sensitivity of 91.7{\%} and a specificity of 45.8{\%} in the case of RQA and 91.7{\%} and 68{\%} when using &recurrence networks, respectively. (C) 2013 Elsevier B.V. All rights reserved.",
keywords = "heart rate, blood pressure, cardiac dynamics, preeclampsia, recurrences, networks, time series analysis, time-series, variability, plots",
author = "{Ramirez Avila}, {G. M.} and A. Gapelyuk and N. Marwan and H. Stepan and J. Kurths and Th Walther and N. Wessel",
year = "2013",
month = "11",
doi = "10.1016/j.autneu.2013.05.003",
language = "English",
volume = "178",
pages = "103--110",
journal = "Autonomic Neuroscience: Basic & Clinical",
issn = "1566-0702",
publisher = "Elsevier",
number = "1-2",

}

TY - JOUR

T1 - Classifying healthy women and preeclamptic patients from cardiovascular data using recurrence and complex network methods

AU - Ramirez Avila, G. M.

AU - Gapelyuk, A.

AU - Marwan, N.

AU - Stepan, H.

AU - Kurths, J.

AU - Walther, Th

AU - Wessel, N.

PY - 2013/11

Y1 - 2013/11

N2 - It is urgently aimed in prenatal medicine to identify pregnancies, which develop life-threatening preeclampsia prior to the manifestation of the disease. Here, we use recurrence-based methods to distinguish such pregnancies already in the second trimester, using the following cardiovascular time series: the variability of heart rate and systolic and diastolic blood pressures. We perform recurrence quantification analysis (RQA), in addition to a novel approach, & recurrence networks, applied to a phase space constructed by means of these time series. We examine all possible coupling structures in a phase space constructed with the above-mentioned biosignals. Several measures including recurrence rate, determinism, laminarity, trapping time, and longest diagonal and vertical lines for the recurrence quantification analysis and average path length, mean coreness, global clustering coefficient, assortativity, and scale local transitivity dimension for the network measures are considered as parameters for our analysis. With these quantities, we perform a quadratic discriminant analysis that allows us to classify healthy pregnancies and upcoming preeclamptic patients with a sensitivity of 91.7% and a specificity of 45.8% in the case of RQA and 91.7% and 68% when using &recurrence networks, respectively. (C) 2013 Elsevier B.V. All rights reserved.

AB - It is urgently aimed in prenatal medicine to identify pregnancies, which develop life-threatening preeclampsia prior to the manifestation of the disease. Here, we use recurrence-based methods to distinguish such pregnancies already in the second trimester, using the following cardiovascular time series: the variability of heart rate and systolic and diastolic blood pressures. We perform recurrence quantification analysis (RQA), in addition to a novel approach, & recurrence networks, applied to a phase space constructed by means of these time series. We examine all possible coupling structures in a phase space constructed with the above-mentioned biosignals. Several measures including recurrence rate, determinism, laminarity, trapping time, and longest diagonal and vertical lines for the recurrence quantification analysis and average path length, mean coreness, global clustering coefficient, assortativity, and scale local transitivity dimension for the network measures are considered as parameters for our analysis. With these quantities, we perform a quadratic discriminant analysis that allows us to classify healthy pregnancies and upcoming preeclamptic patients with a sensitivity of 91.7% and a specificity of 45.8% in the case of RQA and 91.7% and 68% when using &recurrence networks, respectively. (C) 2013 Elsevier B.V. All rights reserved.

KW - heart rate

KW - blood pressure

KW - cardiac dynamics

KW - preeclampsia

KW - recurrences

KW - networks

KW - time series analysis

KW - time-series

KW - variability

KW - plots

U2 - 10.1016/j.autneu.2013.05.003

DO - 10.1016/j.autneu.2013.05.003

M3 - Article

VL - 178

SP - 103

EP - 110

JO - Autonomic Neuroscience: Basic & Clinical

JF - Autonomic Neuroscience: Basic & Clinical

SN - 1566-0702

IS - 1-2

ER -