Evaluating physiological dynamics via synchrosqueezing: Prediction of ventilator weaning

Hau Tieng Wu, Shu Shua Hseu, Mauo Ying Bien, Yu Ru Kou, Ingrid Daubechies

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

Oscillatory phenomena abound in many types of signals. Identifying the individual oscillatory components that constitute an observed biological signal leads to profound understanding about the biological system. The instantaneous frequency (IF), the amplitude modulation (AM), and their temporal variability are widely used to describe these oscillatory phenomena. In addition, the shape of the oscillatory pattern, repeated in time for an oscillatory component, is also an important characteristic that can be parametrized appropriately. These parameters can be viewed as phenomenological surrogates for the hidden dynamics of the biological system. To estimate jointly the IF, AM, and shape, this paper applies a novel and robust time-frequency analysis tool, referred to as the synchrosqueezing transform (SST). The usefulness of the model and SST are shown directly in predicting the clinical outcome of ventilator weaning. Compared with traditional respiration parameters, the breath-to-breath variability has been reported to be a better predictor of the outcome of the weaning procedure. So far, however, all these indices normally require at least 20 min of data acquisition to ensure predictive power. Moreover, the robustness of these indices to the inevitable noise is rarely discussed. We find that based on the proposed model, SST and only 3 min of respiration data, the ROC area under curve of the prediction accuracy is 0.76. The high predictive power that is achieved in the weaning problem, despite a shorter evaluation period, and the stability to noise suggest that other similar kinds of signal may likewise benefit from the proposed model and SST.

Original languageEnglish
Article number6654279
Pages (from-to)736-744
Number of pages9
JournalIEEE Transactions on Biomedical Engineering
Volume61
Issue number3
DOIs
Publication statusPublished - Mar 2014

Fingerprint

Amplitude modulation
Biological systems
Data acquisition

Keywords

  • Heart rate variability (HRV)
  • instantaneous frequency
  • physiological dynamics
  • respiratory rate variability (RRV)
  • synchrosqueezing transform
  • ventilation weaning prediction

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Evaluating physiological dynamics via synchrosqueezing : Prediction of ventilator weaning. / Wu, Hau Tieng; Hseu, Shu Shua; Bien, Mauo Ying; Kou, Yu Ru; Daubechies, Ingrid.

In: IEEE Transactions on Biomedical Engineering, Vol. 61, No. 3, 6654279, 03.2014, p. 736-744.

Research output: Contribution to journalArticle

Wu, Hau Tieng ; Hseu, Shu Shua ; Bien, Mauo Ying ; Kou, Yu Ru ; Daubechies, Ingrid. / Evaluating physiological dynamics via synchrosqueezing : Prediction of ventilator weaning. In: IEEE Transactions on Biomedical Engineering. 2014 ; Vol. 61, No. 3. pp. 736-744.
@article{f0039cafabdf48899b649a8eec292238,
title = "Evaluating physiological dynamics via synchrosqueezing: Prediction of ventilator weaning",
abstract = "Oscillatory phenomena abound in many types of signals. Identifying the individual oscillatory components that constitute an observed biological signal leads to profound understanding about the biological system. The instantaneous frequency (IF), the amplitude modulation (AM), and their temporal variability are widely used to describe these oscillatory phenomena. In addition, the shape of the oscillatory pattern, repeated in time for an oscillatory component, is also an important characteristic that can be parametrized appropriately. These parameters can be viewed as phenomenological surrogates for the hidden dynamics of the biological system. To estimate jointly the IF, AM, and shape, this paper applies a novel and robust time-frequency analysis tool, referred to as the synchrosqueezing transform (SST). The usefulness of the model and SST are shown directly in predicting the clinical outcome of ventilator weaning. Compared with traditional respiration parameters, the breath-to-breath variability has been reported to be a better predictor of the outcome of the weaning procedure. So far, however, all these indices normally require at least 20 min of data acquisition to ensure predictive power. Moreover, the robustness of these indices to the inevitable noise is rarely discussed. We find that based on the proposed model, SST and only 3 min of respiration data, the ROC area under curve of the prediction accuracy is 0.76. The high predictive power that is achieved in the weaning problem, despite a shorter evaluation period, and the stability to noise suggest that other similar kinds of signal may likewise benefit from the proposed model and SST.",
keywords = "Heart rate variability (HRV), instantaneous frequency, physiological dynamics, respiratory rate variability (RRV), synchrosqueezing transform, ventilation weaning prediction",
author = "Wu, {Hau Tieng} and Hseu, {Shu Shua} and Bien, {Mauo Ying} and Kou, {Yu Ru} and Ingrid Daubechies",
year = "2014",
month = "3",
doi = "10.1109/TBME.2013.2288497",
language = "English",
volume = "61",
pages = "736--744",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "3",

}

TY - JOUR

T1 - Evaluating physiological dynamics via synchrosqueezing

T2 - Prediction of ventilator weaning

AU - Wu, Hau Tieng

AU - Hseu, Shu Shua

AU - Bien, Mauo Ying

AU - Kou, Yu Ru

AU - Daubechies, Ingrid

PY - 2014/3

Y1 - 2014/3

N2 - Oscillatory phenomena abound in many types of signals. Identifying the individual oscillatory components that constitute an observed biological signal leads to profound understanding about the biological system. The instantaneous frequency (IF), the amplitude modulation (AM), and their temporal variability are widely used to describe these oscillatory phenomena. In addition, the shape of the oscillatory pattern, repeated in time for an oscillatory component, is also an important characteristic that can be parametrized appropriately. These parameters can be viewed as phenomenological surrogates for the hidden dynamics of the biological system. To estimate jointly the IF, AM, and shape, this paper applies a novel and robust time-frequency analysis tool, referred to as the synchrosqueezing transform (SST). The usefulness of the model and SST are shown directly in predicting the clinical outcome of ventilator weaning. Compared with traditional respiration parameters, the breath-to-breath variability has been reported to be a better predictor of the outcome of the weaning procedure. So far, however, all these indices normally require at least 20 min of data acquisition to ensure predictive power. Moreover, the robustness of these indices to the inevitable noise is rarely discussed. We find that based on the proposed model, SST and only 3 min of respiration data, the ROC area under curve of the prediction accuracy is 0.76. The high predictive power that is achieved in the weaning problem, despite a shorter evaluation period, and the stability to noise suggest that other similar kinds of signal may likewise benefit from the proposed model and SST.

AB - Oscillatory phenomena abound in many types of signals. Identifying the individual oscillatory components that constitute an observed biological signal leads to profound understanding about the biological system. The instantaneous frequency (IF), the amplitude modulation (AM), and their temporal variability are widely used to describe these oscillatory phenomena. In addition, the shape of the oscillatory pattern, repeated in time for an oscillatory component, is also an important characteristic that can be parametrized appropriately. These parameters can be viewed as phenomenological surrogates for the hidden dynamics of the biological system. To estimate jointly the IF, AM, and shape, this paper applies a novel and robust time-frequency analysis tool, referred to as the synchrosqueezing transform (SST). The usefulness of the model and SST are shown directly in predicting the clinical outcome of ventilator weaning. Compared with traditional respiration parameters, the breath-to-breath variability has been reported to be a better predictor of the outcome of the weaning procedure. So far, however, all these indices normally require at least 20 min of data acquisition to ensure predictive power. Moreover, the robustness of these indices to the inevitable noise is rarely discussed. We find that based on the proposed model, SST and only 3 min of respiration data, the ROC area under curve of the prediction accuracy is 0.76. The high predictive power that is achieved in the weaning problem, despite a shorter evaluation period, and the stability to noise suggest that other similar kinds of signal may likewise benefit from the proposed model and SST.

KW - Heart rate variability (HRV)

KW - instantaneous frequency

KW - physiological dynamics

KW - respiratory rate variability (RRV)

KW - synchrosqueezing transform

KW - ventilation weaning prediction

UR - http://www.scopus.com/inward/record.url?scp=84896855886&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896855886&partnerID=8YFLogxK

U2 - 10.1109/TBME.2013.2288497

DO - 10.1109/TBME.2013.2288497

M3 - Article

C2 - 24235294

AN - SCOPUS:84896855886

VL - 61

SP - 736

EP - 744

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 3

M1 - 6654279

ER -