Analysis of the respiratory flow signal for the diagnosis of patients with chronic heart failure using artificial intelligence techniques

J. C. Rodríguez; Carlos J. Arizmendi; C. A. Forero; S. K. Lopez; B. F. Giraldo

doi:10.1007/978-981-10-4086-3_121

Analysis of the respiratory flow signal for the diagnosis of patients with chronic heart failure using artificial intelligence techniques

J. C. Rodríguez, Carlos J. Arizmendi, C. A. Forero, S. K. Lopez, B. F. Giraldo

Research output: Book / Book Chapter / Report › Research Books › peer-review

Abstract

Patients with Chronic Heart Failure (CHF) often develop oscillatory breathing patterns. This work proposes the characterization of respiratory pattern by Wavelet Transform (WT) technique to identify Periodic Breathing pattern (PB) and Non-Periodic Breathing pattern (nPB) through the respiratory flow signal. A total of 62 subjects were analyzed: 27 CHF patients and 35 healthy subjects. Respiratory time series were extracted, and statistical methods were applied to obtain the most relevant information to classify patients. Support Vector Machine (SVM) were applied using forward selection technique to discriminate patients, considering four kernel functions. Differences between these parameters are assessed by investigating the following four classification issues: healthy subjects versus CHF patients, PB versus nPB patients, PB patients versus healthy subjects, and nPB patients versus healthy subjects. The results are presented in terms of average accuracy for each kernel function, and comparison groups.

Original language	English
Title of host publication	7th Latin American Congress on Biomedical Engineering, CLAIB 2016
Editors	John Bustamante, Daniel A. Sierra, Isnardo Torres
Publisher	Springer Verlag
Pages	46-49
Number of pages	4
ISBN (Print)	9789811040856
DOIs	https://doi.org/10.1007/978-981-10-4086-3_121
State	Published - 2016
Event	7th Latin American Congress on Biomedical Engineering, CLAIB 2016 - Bucaramanga, Santander, Colombia Duration: 26 Oct 2016 → 28 Oct 2016

Publication series

Name	IFMBE Proceedings
Volume	60
ISSN (Print)	1680-0737

Conference

Conference	7th Latin American Congress on Biomedical Engineering, CLAIB 2016
Country/Territory	Colombia
City	Bucaramanga, Santander
Period	26/10/16 → 28/10/16

Keywords

Chronic heart failure
Forward selection
Non-periodic breathing
Periodic breathing
Support vector machine

Research Areas UNAB

Automatización y Control

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-981-10-4086-3_121

Cite this

Rodríguez, J. C., Arizmendi, C. J., Forero, C. A., Lopez, S. K., & Giraldo, B. F. (2016). Analysis of the respiratory flow signal for the diagnosis of patients with chronic heart failure using artificial intelligence techniques. In J. Bustamante, D. A. Sierra, & I. Torres (Eds.), 7th Latin American Congress on Biomedical Engineering, CLAIB 2016 (pp. 46-49). (IFMBE Proceedings; Vol. 60). Springer Verlag. https://doi.org/10.1007/978-981-10-4086-3_121

Rodríguez, J. C. ; Arizmendi, Carlos J. ; Forero, C. A. et al. / Analysis of the respiratory flow signal for the diagnosis of patients with chronic heart failure using artificial intelligence techniques. 7th Latin American Congress on Biomedical Engineering, CLAIB 2016. editor / John Bustamante ; Daniel A. Sierra ; Isnardo Torres. Springer Verlag, 2016. pp. 46-49 (IFMBE Proceedings).

@inproceedings{c5ac08bed0bb4f6eb3a27b45fb6991b5,

title = "Analysis of the respiratory flow signal for the diagnosis of patients with chronic heart failure using artificial intelligence techniques",

abstract = "Patients with Chronic Heart Failure (CHF) often develop oscillatory breathing patterns. This work proposes the characterization of respiratory pattern by Wavelet Transform (WT) technique to identify Periodic Breathing pattern (PB) and Non-Periodic Breathing pattern (nPB) through the respiratory flow signal. A total of 62 subjects were analyzed: 27 CHF patients and 35 healthy subjects. Respiratory time series were extracted, and statistical methods were applied to obtain the most relevant information to classify patients. Support Vector Machine (SVM) were applied using forward selection technique to discriminate patients, considering four kernel functions. Differences between these parameters are assessed by investigating the following four classification issues: healthy subjects versus CHF patients, PB versus nPB patients, PB patients versus healthy subjects, and nPB patients versus healthy subjects. The results are presented in terms of average accuracy for each kernel function, and comparison groups.",

keywords = "Chronic heart failure, Forward selection, Non-periodic breathing, Periodic breathing, Support vector machine",

author = "Rodr{\'i}guez, {J. C.} and Arizmendi, {Carlos J.} and Forero, {C. A.} and Lopez, {S. K.} and Giraldo, {B. F.}",

note = "Publisher Copyright: {\textcopyright} Springer Nature Singapore Pte Ltd. 2017.; 7th Latin American Congress on Biomedical Engineering, CLAIB 2016 ; Conference date: 26-10-2016 Through 28-10-2016",

year = "2016",

doi = "10.1007/978-981-10-4086-3_121",

language = "Ingl{\'e}s",

isbn = "9789811040856",

series = "IFMBE Proceedings",

publisher = "Springer Verlag",

pages = "46--49",

editor = "John Bustamante and Sierra, {Daniel A.} and Isnardo Torres",

booktitle = "7th Latin American Congress on Biomedical Engineering, CLAIB 2016",

}

Rodríguez, JC, Arizmendi, CJ , Forero, CA, Lopez, SK & Giraldo, BF 2016, Analysis of the respiratory flow signal for the diagnosis of patients with chronic heart failure using artificial intelligence techniques. in J Bustamante, DA Sierra & I Torres (eds), 7th Latin American Congress on Biomedical Engineering, CLAIB 2016. IFMBE Proceedings, vol. 60, Springer Verlag, pp. 46-49, 7th Latin American Congress on Biomedical Engineering, CLAIB 2016, Bucaramanga, Santander, Colombia, 26/10/16. https://doi.org/10.1007/978-981-10-4086-3_121

Analysis of the respiratory flow signal for the diagnosis of patients with chronic heart failure using artificial intelligence techniques. / Rodríguez, J. C.; Arizmendi, Carlos J.; Forero, C. A. et al.
7th Latin American Congress on Biomedical Engineering, CLAIB 2016. ed. / John Bustamante; Daniel A. Sierra; Isnardo Torres. Springer Verlag, 2016. p. 46-49 (IFMBE Proceedings; Vol. 60).

Research output: Book / Book Chapter / Report › Research Books › peer-review

TY - GEN

T1 - Analysis of the respiratory flow signal for the diagnosis of patients with chronic heart failure using artificial intelligence techniques

AU - Rodríguez, J. C.

AU - Arizmendi, Carlos J.

AU - Forero, C. A.

AU - Lopez, S. K.

AU - Giraldo, B. F.

N1 - Publisher Copyright: © Springer Nature Singapore Pte Ltd. 2017.

PY - 2016

Y1 - 2016

N2 - Patients with Chronic Heart Failure (CHF) often develop oscillatory breathing patterns. This work proposes the characterization of respiratory pattern by Wavelet Transform (WT) technique to identify Periodic Breathing pattern (PB) and Non-Periodic Breathing pattern (nPB) through the respiratory flow signal. A total of 62 subjects were analyzed: 27 CHF patients and 35 healthy subjects. Respiratory time series were extracted, and statistical methods were applied to obtain the most relevant information to classify patients. Support Vector Machine (SVM) were applied using forward selection technique to discriminate patients, considering four kernel functions. Differences between these parameters are assessed by investigating the following four classification issues: healthy subjects versus CHF patients, PB versus nPB patients, PB patients versus healthy subjects, and nPB patients versus healthy subjects. The results are presented in terms of average accuracy for each kernel function, and comparison groups.

AB - Patients with Chronic Heart Failure (CHF) often develop oscillatory breathing patterns. This work proposes the characterization of respiratory pattern by Wavelet Transform (WT) technique to identify Periodic Breathing pattern (PB) and Non-Periodic Breathing pattern (nPB) through the respiratory flow signal. A total of 62 subjects were analyzed: 27 CHF patients and 35 healthy subjects. Respiratory time series were extracted, and statistical methods were applied to obtain the most relevant information to classify patients. Support Vector Machine (SVM) were applied using forward selection technique to discriminate patients, considering four kernel functions. Differences between these parameters are assessed by investigating the following four classification issues: healthy subjects versus CHF patients, PB versus nPB patients, PB patients versus healthy subjects, and nPB patients versus healthy subjects. The results are presented in terms of average accuracy for each kernel function, and comparison groups.

KW - Chronic heart failure

KW - Forward selection

KW - Non-periodic breathing

KW - Periodic breathing

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=85018434036&partnerID=8YFLogxK

U2 - 10.1007/978-981-10-4086-3_121

DO - 10.1007/978-981-10-4086-3_121

M3 - Libros de Investigación

AN - SCOPUS:85018434036

SN - 9789811040856

T3 - IFMBE Proceedings

SP - 46

EP - 49

BT - 7th Latin American Congress on Biomedical Engineering, CLAIB 2016

A2 - Bustamante, John

A2 - Sierra, Daniel A.

A2 - Torres, Isnardo

PB - Springer Verlag

T2 - 7th Latin American Congress on Biomedical Engineering, CLAIB 2016

Y2 - 26 October 2016 through 28 October 2016

ER -

Rodríguez JC, Arizmendi CJ , Forero CA, Lopez SK, Giraldo BF. Analysis of the respiratory flow signal for the diagnosis of patients with chronic heart failure using artificial intelligence techniques. In Bustamante J, Sierra DA, Torres I, editors, 7th Latin American Congress on Biomedical Engineering, CLAIB 2016. Springer Verlag. 2016. p. 46-49. (IFMBE Proceedings). doi: 10.1007/978-981-10-4086-3_121

Analysis of the respiratory flow signal for the diagnosis of patients with chronic heart failure using artificial intelligence techniques

Abstract

Publication series

Conference

Keywords

Research Areas UNAB

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this