TY - GEN
T1 - Multiscale properties of instantaneous parasympathetic activity in severe congestive heart failure
T2 - 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2017
AU - Valenza, G.
AU - Wendt, H.
AU - Kiyono, K.
AU - Hayano, J.
AU - Watanabe, E.
AU - Yamamoto, Y.
AU - Abry, P.
AU - Barbieri, R.
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/9/13
Y1 - 2017/9/13
N2 - Multifractal analysis of cardiovascular variability series is an effective tool for the characterization of pathological states associated with congestive heart failure (CHF). Consequently, variations of heartbeat scaling properties have been associated with the dynamical balancing of nonlinear sympathetic/vagal activity. Nevertheless, whether vagal dynamics has multifractal properties yet alone is currently unknown. In this study, we answer this question by conducting multifractal analysis through wavelet leader-based multiscale representations of instantaneous series of vagal activity as estimated from inhomogeneous point process models. Experimental tests were performed on data gathered from 57 CHF patients, aiming to investigate the automatic recognition accuracy in predicting survivor and non-survivor patients after a 4 years follow up. Results clearly indicate that, on both CHF groups, the instantaneous vagal activity displays power-law scaling for a large range of scales, from ≃ 0.5s to ≃ 100s. Using standard SVM algorithms, this information also allows for a prediction of mortality at a single-subject level with an accuracy of 72.72%.
AB - Multifractal analysis of cardiovascular variability series is an effective tool for the characterization of pathological states associated with congestive heart failure (CHF). Consequently, variations of heartbeat scaling properties have been associated with the dynamical balancing of nonlinear sympathetic/vagal activity. Nevertheless, whether vagal dynamics has multifractal properties yet alone is currently unknown. In this study, we answer this question by conducting multifractal analysis through wavelet leader-based multiscale representations of instantaneous series of vagal activity as estimated from inhomogeneous point process models. Experimental tests were performed on data gathered from 57 CHF patients, aiming to investigate the automatic recognition accuracy in predicting survivor and non-survivor patients after a 4 years follow up. Results clearly indicate that, on both CHF groups, the instantaneous vagal activity displays power-law scaling for a large range of scales, from ≃ 0.5s to ≃ 100s. Using standard SVM algorithms, this information also allows for a prediction of mortality at a single-subject level with an accuracy of 72.72%.
UR - http://www.scopus.com/inward/record.url?scp=85032198777&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85032198777&partnerID=8YFLogxK
U2 - 10.1109/EMBC.2017.8037675
DO - 10.1109/EMBC.2017.8037675
M3 - Conference contribution
C2 - 29060716
AN - SCOPUS:85032198777
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 3761
EP - 3764
BT - 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 11 July 2017 through 15 July 2017
ER -