K-nearest-neighbor conditional entropy approach for the assessment of the short-term complexity of cardiovascular control

A. Porta, P. Castiglioni, V. Bari, T. Bassani, A. Marchi, A. Cividjian, L. Quintin, M. Di Rienzo

Research output: Contribution to journalArticle

36 Citations (Scopus)

Abstract

Complexity analysis of short-term cardiovascular control is traditionally performed using entropy-based approaches including corrective terms or strategies to cope with the loss of reliability of conditional distributions with pattern length. This study proposes a new approach aiming at the estimation of conditional entropy (CE) from short data segments (about 250 samples) based on the k-nearest-neighbor technique. The main advantages are: (i) the control of the loss of reliability of the conditional distributions with the pattern length without introducing a priori information; (ii) the assessment of complexity indexes without fixing the pattern length to an arbitrary low value. The approach, referred to as k-nearest-neighbor conditional entropy (KNNCE), was contrasted with corrected approximate entropy (CApEn), sample entropy (SampEn) and corrected CE (CCE), being the most frequently exploited approaches for entropy-based complexity analysis of short cardiovascular series. Complexity indexes were evaluated during the selective pharmacological blockade of the vagal and/or sympathetic branches of the autonomic nervous system. We found that KNNCE was more powerful than CCE in detecting the decrease of complexity of heart period variability imposed by double autonomic blockade. In addition, KNNCE provides indexes indistinguishable from those derived from CApEn and SampEn. Since this result was obtained without using strategies to correct the CE estimate and without fixing the embedding dimension to an arbitrary low value, KNNCE is potentially more valuable than CCE, CApEn and SampEn when the number of past samples most useful to reduce the uncertainty of future behaviors is high and/or variable among conditions and/or groups.

Original languageEnglish
Article number17
Pages (from-to)17-33
Number of pages17
JournalPhysiological Measurement
Volume34
Issue number1
DOIs
Publication statusPublished - Jan 2013

Fingerprint

Entropy
Systems Analysis
Autonomic Nervous System
Neurology
Uncertainty

Keywords

  • autonomic nervous system
  • cardiovascular control
  • corrected approximate entropy
  • corrected conditional entropy
  • heart rate variability
  • sample entropy

ASJC Scopus subject areas

  • Biophysics
  • Physiology
  • Physiology (medical)

Cite this

K-nearest-neighbor conditional entropy approach for the assessment of the short-term complexity of cardiovascular control. / Porta, A.; Castiglioni, P.; Bari, V.; Bassani, T.; Marchi, A.; Cividjian, A.; Quintin, L.; Di Rienzo, M.

In: Physiological Measurement, Vol. 34, No. 1, 17, 01.2013, p. 17-33.

Research output: Contribution to journalArticle

@article{9431c59b9bb94136989146b8909d36e8,
title = "K-nearest-neighbor conditional entropy approach for the assessment of the short-term complexity of cardiovascular control",
abstract = "Complexity analysis of short-term cardiovascular control is traditionally performed using entropy-based approaches including corrective terms or strategies to cope with the loss of reliability of conditional distributions with pattern length. This study proposes a new approach aiming at the estimation of conditional entropy (CE) from short data segments (about 250 samples) based on the k-nearest-neighbor technique. The main advantages are: (i) the control of the loss of reliability of the conditional distributions with the pattern length without introducing a priori information; (ii) the assessment of complexity indexes without fixing the pattern length to an arbitrary low value. The approach, referred to as k-nearest-neighbor conditional entropy (KNNCE), was contrasted with corrected approximate entropy (CApEn), sample entropy (SampEn) and corrected CE (CCE), being the most frequently exploited approaches for entropy-based complexity analysis of short cardiovascular series. Complexity indexes were evaluated during the selective pharmacological blockade of the vagal and/or sympathetic branches of the autonomic nervous system. We found that KNNCE was more powerful than CCE in detecting the decrease of complexity of heart period variability imposed by double autonomic blockade. In addition, KNNCE provides indexes indistinguishable from those derived from CApEn and SampEn. Since this result was obtained without using strategies to correct the CE estimate and without fixing the embedding dimension to an arbitrary low value, KNNCE is potentially more valuable than CCE, CApEn and SampEn when the number of past samples most useful to reduce the uncertainty of future behaviors is high and/or variable among conditions and/or groups.",
keywords = "autonomic nervous system, cardiovascular control, corrected approximate entropy, corrected conditional entropy, heart rate variability, sample entropy",
author = "A. Porta and P. Castiglioni and V. Bari and T. Bassani and A. Marchi and A. Cividjian and L. Quintin and {Di Rienzo}, M.",
year = "2013",
month = "1",
doi = "10.1088/0967-3334/34/1/17",
language = "English",
volume = "34",
pages = "17--33",
journal = "Physiological Measurement",
issn = "0967-3334",
publisher = "Institute of Physics Publishing",
number = "1",

}

TY - JOUR

T1 - K-nearest-neighbor conditional entropy approach for the assessment of the short-term complexity of cardiovascular control

AU - Porta, A.

AU - Castiglioni, P.

AU - Bari, V.

AU - Bassani, T.

AU - Marchi, A.

AU - Cividjian, A.

AU - Quintin, L.

AU - Di Rienzo, M.

PY - 2013/1

Y1 - 2013/1

N2 - Complexity analysis of short-term cardiovascular control is traditionally performed using entropy-based approaches including corrective terms or strategies to cope with the loss of reliability of conditional distributions with pattern length. This study proposes a new approach aiming at the estimation of conditional entropy (CE) from short data segments (about 250 samples) based on the k-nearest-neighbor technique. The main advantages are: (i) the control of the loss of reliability of the conditional distributions with the pattern length without introducing a priori information; (ii) the assessment of complexity indexes without fixing the pattern length to an arbitrary low value. The approach, referred to as k-nearest-neighbor conditional entropy (KNNCE), was contrasted with corrected approximate entropy (CApEn), sample entropy (SampEn) and corrected CE (CCE), being the most frequently exploited approaches for entropy-based complexity analysis of short cardiovascular series. Complexity indexes were evaluated during the selective pharmacological blockade of the vagal and/or sympathetic branches of the autonomic nervous system. We found that KNNCE was more powerful than CCE in detecting the decrease of complexity of heart period variability imposed by double autonomic blockade. In addition, KNNCE provides indexes indistinguishable from those derived from CApEn and SampEn. Since this result was obtained without using strategies to correct the CE estimate and without fixing the embedding dimension to an arbitrary low value, KNNCE is potentially more valuable than CCE, CApEn and SampEn when the number of past samples most useful to reduce the uncertainty of future behaviors is high and/or variable among conditions and/or groups.

AB - Complexity analysis of short-term cardiovascular control is traditionally performed using entropy-based approaches including corrective terms or strategies to cope with the loss of reliability of conditional distributions with pattern length. This study proposes a new approach aiming at the estimation of conditional entropy (CE) from short data segments (about 250 samples) based on the k-nearest-neighbor technique. The main advantages are: (i) the control of the loss of reliability of the conditional distributions with the pattern length without introducing a priori information; (ii) the assessment of complexity indexes without fixing the pattern length to an arbitrary low value. The approach, referred to as k-nearest-neighbor conditional entropy (KNNCE), was contrasted with corrected approximate entropy (CApEn), sample entropy (SampEn) and corrected CE (CCE), being the most frequently exploited approaches for entropy-based complexity analysis of short cardiovascular series. Complexity indexes were evaluated during the selective pharmacological blockade of the vagal and/or sympathetic branches of the autonomic nervous system. We found that KNNCE was more powerful than CCE in detecting the decrease of complexity of heart period variability imposed by double autonomic blockade. In addition, KNNCE provides indexes indistinguishable from those derived from CApEn and SampEn. Since this result was obtained without using strategies to correct the CE estimate and without fixing the embedding dimension to an arbitrary low value, KNNCE is potentially more valuable than CCE, CApEn and SampEn when the number of past samples most useful to reduce the uncertainty of future behaviors is high and/or variable among conditions and/or groups.

KW - autonomic nervous system

KW - cardiovascular control

KW - corrected approximate entropy

KW - corrected conditional entropy

KW - heart rate variability

KW - sample entropy

UR - http://www.scopus.com/inward/record.url?scp=84871406177&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871406177&partnerID=8YFLogxK

U2 - 10.1088/0967-3334/34/1/17

DO - 10.1088/0967-3334/34/1/17

M3 - Article

VL - 34

SP - 17

EP - 33

JO - Physiological Measurement

JF - Physiological Measurement

SN - 0967-3334

IS - 1

M1 - 17

ER -