Radial basis function neural networks for the characterization of heart rate variability dynamics

A. Bezerianos, S. Papadimitriou, D. Alexopoulos

Research output: Contribution to journalArticle

Abstract

This study introduces new neural network based methods for the assessment of the dynamics of the heart rate variability (HRV) signal. The heart rate regulation is assessed as a dynamical system operating in chaotic regimes. Radial-basis function (RBF) networks are applied as a tool for learning and predicting the HRV dynamics. HRV signals are analyzed from normal subjects before and after pharmacological autonomic nervous system (ANS) blockade and from diabetic patients with dysfunctional ANS. The heart rate of normal subjects presents notable predictability. The prediction error is minimized, in fewer degrees of freedom, in the case of diabetic patients. However, for the case of pharmacological ANS blockade, although correlation dimension approaches indicate significant reduction in complexity, the RBF networks fail to reconstruct adequately the underlying dynamics. The transient attributes of the HRV dynamics under the pharmacological disturbance is elucidated as the explanation for the prediction inability.

Original languageEnglish (US)
Pages (from-to)215-234
Number of pages20
JournalArtificial Intelligence in Medicine
Volume15
Issue number3
DOIs
StatePublished - Mar 1999
Externally publishedYes

Fingerprint

Heart Rate
Neural networks
Autonomic Nervous System
Neurology
Radial basis function networks
Pharmacology
Dynamical systems
Learning

Keywords

  • Autonomic nervous system
  • Heart rate
  • Heart rate variability
  • Neural network learning
  • Nonlinear dynamics
  • Nonlinear prediction

ASJC Scopus subject areas

  • Artificial Intelligence
  • Medicine(all)

Cite this

Radial basis function neural networks for the characterization of heart rate variability dynamics. / Bezerianos, A.; Papadimitriou, S.; Alexopoulos, D.

In: Artificial Intelligence in Medicine, Vol. 15, No. 3, 03.1999, p. 215-234.

Research output: Contribution to journalArticle

Bezerianos, A. ; Papadimitriou, S. ; Alexopoulos, D. / Radial basis function neural networks for the characterization of heart rate variability dynamics. In: Artificial Intelligence in Medicine. 1999 ; Vol. 15, No. 3. pp. 215-234.
@article{0cb65a99f25b4d4293f2c498644ae69c,
title = "Radial basis function neural networks for the characterization of heart rate variability dynamics",
abstract = "This study introduces new neural network based methods for the assessment of the dynamics of the heart rate variability (HRV) signal. The heart rate regulation is assessed as a dynamical system operating in chaotic regimes. Radial-basis function (RBF) networks are applied as a tool for learning and predicting the HRV dynamics. HRV signals are analyzed from normal subjects before and after pharmacological autonomic nervous system (ANS) blockade and from diabetic patients with dysfunctional ANS. The heart rate of normal subjects presents notable predictability. The prediction error is minimized, in fewer degrees of freedom, in the case of diabetic patients. However, for the case of pharmacological ANS blockade, although correlation dimension approaches indicate significant reduction in complexity, the RBF networks fail to reconstruct adequately the underlying dynamics. The transient attributes of the HRV dynamics under the pharmacological disturbance is elucidated as the explanation for the prediction inability.",
keywords = "Autonomic nervous system, Heart rate, Heart rate variability, Neural network learning, Nonlinear dynamics, Nonlinear prediction",
author = "A. Bezerianos and S. Papadimitriou and D. Alexopoulos",
year = "1999",
month = "3",
doi = "10.1016/S0933-3657(98)00055-4",
language = "English (US)",
volume = "15",
pages = "215--234",
journal = "Artificial Intelligence in Medicine",
issn = "0933-3657",
publisher = "Elsevier",
number = "3",

}

TY - JOUR

T1 - Radial basis function neural networks for the characterization of heart rate variability dynamics

AU - Bezerianos, A.

AU - Papadimitriou, S.

AU - Alexopoulos, D.

PY - 1999/3

Y1 - 1999/3

N2 - This study introduces new neural network based methods for the assessment of the dynamics of the heart rate variability (HRV) signal. The heart rate regulation is assessed as a dynamical system operating in chaotic regimes. Radial-basis function (RBF) networks are applied as a tool for learning and predicting the HRV dynamics. HRV signals are analyzed from normal subjects before and after pharmacological autonomic nervous system (ANS) blockade and from diabetic patients with dysfunctional ANS. The heart rate of normal subjects presents notable predictability. The prediction error is minimized, in fewer degrees of freedom, in the case of diabetic patients. However, for the case of pharmacological ANS blockade, although correlation dimension approaches indicate significant reduction in complexity, the RBF networks fail to reconstruct adequately the underlying dynamics. The transient attributes of the HRV dynamics under the pharmacological disturbance is elucidated as the explanation for the prediction inability.

AB - This study introduces new neural network based methods for the assessment of the dynamics of the heart rate variability (HRV) signal. The heart rate regulation is assessed as a dynamical system operating in chaotic regimes. Radial-basis function (RBF) networks are applied as a tool for learning and predicting the HRV dynamics. HRV signals are analyzed from normal subjects before and after pharmacological autonomic nervous system (ANS) blockade and from diabetic patients with dysfunctional ANS. The heart rate of normal subjects presents notable predictability. The prediction error is minimized, in fewer degrees of freedom, in the case of diabetic patients. However, for the case of pharmacological ANS blockade, although correlation dimension approaches indicate significant reduction in complexity, the RBF networks fail to reconstruct adequately the underlying dynamics. The transient attributes of the HRV dynamics under the pharmacological disturbance is elucidated as the explanation for the prediction inability.

KW - Autonomic nervous system

KW - Heart rate

KW - Heart rate variability

KW - Neural network learning

KW - Nonlinear dynamics

KW - Nonlinear prediction

UR - http://www.scopus.com/inward/record.url?scp=0033104431&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033104431&partnerID=8YFLogxK

U2 - 10.1016/S0933-3657(98)00055-4

DO - 10.1016/S0933-3657(98)00055-4

M3 - Article

C2 - 10206108

AN - SCOPUS:0033104431

VL - 15

SP - 215

EP - 234

JO - Artificial Intelligence in Medicine

JF - Artificial Intelligence in Medicine

SN - 0933-3657

IS - 3

ER -