Mortality prediction in severe congestive heart failure patients with multifractal point-process modeling of heartbeat dynamics

Gaetano Valenza, Herwig Wendt, Ken Kiyono, Junichro Hayano, Eiichi Watanabe, Yoshiharu Yamamoto, Patrice Abry, Riccardo Barbieri

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Background: Multifractal analysis of human heartbeat dynamics has been demonstrated to provide promising markers of congestive heart failure (CHF). Yet, it crucially builds on the interpolation of RR interval series which has been generically performed with limited links to CHF pathophysiology. Objective: We devise a novel methodology estimating multifractal autonomic dynamics from heartbeat-derived series defined in the continuous time. We hypothesize that markers estimated from our novel framework are also effective for mortality prediction in severe CHF. Methods: We merge multifractal analysis within a methodological framework based on inhomogeneous point process models of heartbeat dynamics. Specifically, wavelet coefficients and wavelet leaders are computed over measures extracted from instantaneous statistics of probability density functions characterizing and predicting the time until the next heartbeat event occurs. The proposed approach is tested on data from 94 CHF patients aiming at predicting survivor and nonsurvivor individuals as determined after a four years follow up. Results and Discussion: Instantaneous markers of vagal and sympatho-vagal dynamics display power-law scaling for a large range of scales, from \simeq 0.5 to \simeq 100 s. Using standard support vector machine algorithms, the proposed inhomogeneous point-process representation-based multifractal analysis achieved the best CHF mortality prediction accuracy of 79.11% (sensitivity 90.48%, specificity 67.74%). Conclusion: Our results suggest that heartbeat scaling and multifractal properties in CHF patients are not generated at the sinus-node level, but rather by the intrinsic action of vagal short-term control and of sympatho-vagal fluctuations associated with circadian cardiovascular control especially within the very low frequency band. These markers might provide critical information in devising a clinical tool for individualized prediction of survivor and nonsurvivor CHF patients.

Original languageEnglish
Article number8267243
Pages (from-to)2345-2354
Number of pages10
JournalIEEE Transactions on Biomedical Engineering
Volume65
Issue number10
DOIs
Publication statusPublished - 10-2018

Fingerprint

Scaling laws
Probability density function
Frequency bands
Support vector machines
Interpolation
Statistics

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

Cite this

Valenza, Gaetano ; Wendt, Herwig ; Kiyono, Ken ; Hayano, Junichro ; Watanabe, Eiichi ; Yamamoto, Yoshiharu ; Abry, Patrice ; Barbieri, Riccardo. / Mortality prediction in severe congestive heart failure patients with multifractal point-process modeling of heartbeat dynamics. In: IEEE Transactions on Biomedical Engineering. 2018 ; Vol. 65, No. 10. pp. 2345-2354.
@article{e44c3919bd274f2f9267f8ce2112049c,
title = "Mortality prediction in severe congestive heart failure patients with multifractal point-process modeling of heartbeat dynamics",
abstract = "Background: Multifractal analysis of human heartbeat dynamics has been demonstrated to provide promising markers of congestive heart failure (CHF). Yet, it crucially builds on the interpolation of RR interval series which has been generically performed with limited links to CHF pathophysiology. Objective: We devise a novel methodology estimating multifractal autonomic dynamics from heartbeat-derived series defined in the continuous time. We hypothesize that markers estimated from our novel framework are also effective for mortality prediction in severe CHF. Methods: We merge multifractal analysis within a methodological framework based on inhomogeneous point process models of heartbeat dynamics. Specifically, wavelet coefficients and wavelet leaders are computed over measures extracted from instantaneous statistics of probability density functions characterizing and predicting the time until the next heartbeat event occurs. The proposed approach is tested on data from 94 CHF patients aiming at predicting survivor and nonsurvivor individuals as determined after a four years follow up. Results and Discussion: Instantaneous markers of vagal and sympatho-vagal dynamics display power-law scaling for a large range of scales, from \simeq 0.5 to \simeq 100 s. Using standard support vector machine algorithms, the proposed inhomogeneous point-process representation-based multifractal analysis achieved the best CHF mortality prediction accuracy of 79.11{\%} (sensitivity 90.48{\%}, specificity 67.74{\%}). Conclusion: Our results suggest that heartbeat scaling and multifractal properties in CHF patients are not generated at the sinus-node level, but rather by the intrinsic action of vagal short-term control and of sympatho-vagal fluctuations associated with circadian cardiovascular control especially within the very low frequency band. These markers might provide critical information in devising a clinical tool for individualized prediction of survivor and nonsurvivor CHF patients.",
author = "Gaetano Valenza and Herwig Wendt and Ken Kiyono and Junichro Hayano and Eiichi Watanabe and Yoshiharu Yamamoto and Patrice Abry and Riccardo Barbieri",
year = "2018",
month = "10",
doi = "10.1109/TBME.2018.2797158",
language = "English",
volume = "65",
pages = "2345--2354",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "10",

}

Mortality prediction in severe congestive heart failure patients with multifractal point-process modeling of heartbeat dynamics. / Valenza, Gaetano; Wendt, Herwig; Kiyono, Ken; Hayano, Junichro; Watanabe, Eiichi; Yamamoto, Yoshiharu; Abry, Patrice; Barbieri, Riccardo.

In: IEEE Transactions on Biomedical Engineering, Vol. 65, No. 10, 8267243, 10.2018, p. 2345-2354.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Mortality prediction in severe congestive heart failure patients with multifractal point-process modeling of heartbeat dynamics

AU - Valenza, Gaetano

AU - Wendt, Herwig

AU - Kiyono, Ken

AU - Hayano, Junichro

AU - Watanabe, Eiichi

AU - Yamamoto, Yoshiharu

AU - Abry, Patrice

AU - Barbieri, Riccardo

PY - 2018/10

Y1 - 2018/10

N2 - Background: Multifractal analysis of human heartbeat dynamics has been demonstrated to provide promising markers of congestive heart failure (CHF). Yet, it crucially builds on the interpolation of RR interval series which has been generically performed with limited links to CHF pathophysiology. Objective: We devise a novel methodology estimating multifractal autonomic dynamics from heartbeat-derived series defined in the continuous time. We hypothesize that markers estimated from our novel framework are also effective for mortality prediction in severe CHF. Methods: We merge multifractal analysis within a methodological framework based on inhomogeneous point process models of heartbeat dynamics. Specifically, wavelet coefficients and wavelet leaders are computed over measures extracted from instantaneous statistics of probability density functions characterizing and predicting the time until the next heartbeat event occurs. The proposed approach is tested on data from 94 CHF patients aiming at predicting survivor and nonsurvivor individuals as determined after a four years follow up. Results and Discussion: Instantaneous markers of vagal and sympatho-vagal dynamics display power-law scaling for a large range of scales, from \simeq 0.5 to \simeq 100 s. Using standard support vector machine algorithms, the proposed inhomogeneous point-process representation-based multifractal analysis achieved the best CHF mortality prediction accuracy of 79.11% (sensitivity 90.48%, specificity 67.74%). Conclusion: Our results suggest that heartbeat scaling and multifractal properties in CHF patients are not generated at the sinus-node level, but rather by the intrinsic action of vagal short-term control and of sympatho-vagal fluctuations associated with circadian cardiovascular control especially within the very low frequency band. These markers might provide critical information in devising a clinical tool for individualized prediction of survivor and nonsurvivor CHF patients.

AB - Background: Multifractal analysis of human heartbeat dynamics has been demonstrated to provide promising markers of congestive heart failure (CHF). Yet, it crucially builds on the interpolation of RR interval series which has been generically performed with limited links to CHF pathophysiology. Objective: We devise a novel methodology estimating multifractal autonomic dynamics from heartbeat-derived series defined in the continuous time. We hypothesize that markers estimated from our novel framework are also effective for mortality prediction in severe CHF. Methods: We merge multifractal analysis within a methodological framework based on inhomogeneous point process models of heartbeat dynamics. Specifically, wavelet coefficients and wavelet leaders are computed over measures extracted from instantaneous statistics of probability density functions characterizing and predicting the time until the next heartbeat event occurs. The proposed approach is tested on data from 94 CHF patients aiming at predicting survivor and nonsurvivor individuals as determined after a four years follow up. Results and Discussion: Instantaneous markers of vagal and sympatho-vagal dynamics display power-law scaling for a large range of scales, from \simeq 0.5 to \simeq 100 s. Using standard support vector machine algorithms, the proposed inhomogeneous point-process representation-based multifractal analysis achieved the best CHF mortality prediction accuracy of 79.11% (sensitivity 90.48%, specificity 67.74%). Conclusion: Our results suggest that heartbeat scaling and multifractal properties in CHF patients are not generated at the sinus-node level, but rather by the intrinsic action of vagal short-term control and of sympatho-vagal fluctuations associated with circadian cardiovascular control especially within the very low frequency band. These markers might provide critical information in devising a clinical tool for individualized prediction of survivor and nonsurvivor CHF patients.

UR - http://www.scopus.com/inward/record.url?scp=85041013694&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041013694&partnerID=8YFLogxK

U2 - 10.1109/TBME.2018.2797158

DO - 10.1109/TBME.2018.2797158

M3 - Article

C2 - 29993522

AN - SCOPUS:85041013694

VL - 65

SP - 2345

EP - 2354

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 10

M1 - 8267243

ER -