A simple algorithm for ventilation detection in the capnography signal during cardiopulmonary resuscitation

Mikel Leturiondo, Jesús Ruiz, Sofía Ruiz De Gauna, Digna M. González-Otero, José M. Bastida, Mohamud Ramzan Daya

Research output: Contribution to journalConference article

2 Citations (Scopus)

Abstract

During cardiopulmonary resuscitation, excessive ventilation rates reduce the chance of survival. We have developed a simple method to automatically detect ventilations based on the analysis of the capnography signal recorded with monitor-defibrillators. We used 60 out-of-hospital cardiac arrest episodes that contained both clean and chest compressions (CC) corrupted capnograms. The detection algorithm first identified ventilation candidates in the capnography signal. Then, it characterized every candidate by features related to inspiration and expiration durations, and finally a decision system based on static thresholds was applied in order to determine whether each candidate corresponded to a true ventilation. Sensitivity (Se) and positive predictive value (PPV) for the clean set (3905 ventilations) were 99.8% and 99.1%, respectively. With the corrupted set (6778 ventilations) Se and PPV decreased to 85.3% and 85.6%, respectively. For the whole test set (10683 ventilations) Se and PPV were 90.6% and 90.6%, respectively. Detector's performance clearly degraded when applied to corrupted episodes, this demonstrates the need for techniques to suppress CC artefact to improve ventilation detection.

Original languageEnglish (US)
Pages (from-to)1-4
Number of pages4
JournalComputing in Cardiology
Volume44
DOIs
StatePublished - Jan 1 2017
Event44th Computing in Cardiology Conference, CinC 2017 - Rennes, France
Duration: Sep 24 2017Sep 27 2017

Fingerprint

Capnography
Resuscitation
Cardiopulmonary Resuscitation
Ventilation
Thorax
Defibrillators
Out-of-Hospital Cardiac Arrest
Artifacts
Detectors

ASJC Scopus subject areas

  • Computer Science(all)
  • Cardiology and Cardiovascular Medicine

Cite this

A simple algorithm for ventilation detection in the capnography signal during cardiopulmonary resuscitation. / Leturiondo, Mikel; Ruiz, Jesús; De Gauna, Sofía Ruiz; González-Otero, Digna M.; Bastida, José M.; Daya, Mohamud Ramzan.

In: Computing in Cardiology, Vol. 44, 01.01.2017, p. 1-4.

Research output: Contribution to journalConference article

Leturiondo, Mikel ; Ruiz, Jesús ; De Gauna, Sofía Ruiz ; González-Otero, Digna M. ; Bastida, José M. ; Daya, Mohamud Ramzan. / A simple algorithm for ventilation detection in the capnography signal during cardiopulmonary resuscitation. In: Computing in Cardiology. 2017 ; Vol. 44. pp. 1-4.
@article{70a90b63d1dc4eb4a229e1404e5be802,
title = "A simple algorithm for ventilation detection in the capnography signal during cardiopulmonary resuscitation",
abstract = "During cardiopulmonary resuscitation, excessive ventilation rates reduce the chance of survival. We have developed a simple method to automatically detect ventilations based on the analysis of the capnography signal recorded with monitor-defibrillators. We used 60 out-of-hospital cardiac arrest episodes that contained both clean and chest compressions (CC) corrupted capnograms. The detection algorithm first identified ventilation candidates in the capnography signal. Then, it characterized every candidate by features related to inspiration and expiration durations, and finally a decision system based on static thresholds was applied in order to determine whether each candidate corresponded to a true ventilation. Sensitivity (Se) and positive predictive value (PPV) for the clean set (3905 ventilations) were 99.8{\%} and 99.1{\%}, respectively. With the corrupted set (6778 ventilations) Se and PPV decreased to 85.3{\%} and 85.6{\%}, respectively. For the whole test set (10683 ventilations) Se and PPV were 90.6{\%} and 90.6{\%}, respectively. Detector's performance clearly degraded when applied to corrupted episodes, this demonstrates the need for techniques to suppress CC artefact to improve ventilation detection.",
author = "Mikel Leturiondo and Jes{\'u}s Ruiz and {De Gauna}, {Sof{\'i}a Ruiz} and Gonz{\'a}lez-Otero, {Digna M.} and Bastida, {Jos{\'e} M.} and Daya, {Mohamud Ramzan}",
year = "2017",
month = "1",
day = "1",
doi = "10.22489/CinC.2017.005-072",
language = "English (US)",
volume = "44",
pages = "1--4",
journal = "Computing in Cardiology",
issn = "2325-8861",
publisher = "IEEE Computer Society",

}

TY - JOUR

T1 - A simple algorithm for ventilation detection in the capnography signal during cardiopulmonary resuscitation

AU - Leturiondo, Mikel

AU - Ruiz, Jesús

AU - De Gauna, Sofía Ruiz

AU - González-Otero, Digna M.

AU - Bastida, José M.

AU - Daya, Mohamud Ramzan

PY - 2017/1/1

Y1 - 2017/1/1

N2 - During cardiopulmonary resuscitation, excessive ventilation rates reduce the chance of survival. We have developed a simple method to automatically detect ventilations based on the analysis of the capnography signal recorded with monitor-defibrillators. We used 60 out-of-hospital cardiac arrest episodes that contained both clean and chest compressions (CC) corrupted capnograms. The detection algorithm first identified ventilation candidates in the capnography signal. Then, it characterized every candidate by features related to inspiration and expiration durations, and finally a decision system based on static thresholds was applied in order to determine whether each candidate corresponded to a true ventilation. Sensitivity (Se) and positive predictive value (PPV) for the clean set (3905 ventilations) were 99.8% and 99.1%, respectively. With the corrupted set (6778 ventilations) Se and PPV decreased to 85.3% and 85.6%, respectively. For the whole test set (10683 ventilations) Se and PPV were 90.6% and 90.6%, respectively. Detector's performance clearly degraded when applied to corrupted episodes, this demonstrates the need for techniques to suppress CC artefact to improve ventilation detection.

AB - During cardiopulmonary resuscitation, excessive ventilation rates reduce the chance of survival. We have developed a simple method to automatically detect ventilations based on the analysis of the capnography signal recorded with monitor-defibrillators. We used 60 out-of-hospital cardiac arrest episodes that contained both clean and chest compressions (CC) corrupted capnograms. The detection algorithm first identified ventilation candidates in the capnography signal. Then, it characterized every candidate by features related to inspiration and expiration durations, and finally a decision system based on static thresholds was applied in order to determine whether each candidate corresponded to a true ventilation. Sensitivity (Se) and positive predictive value (PPV) for the clean set (3905 ventilations) were 99.8% and 99.1%, respectively. With the corrupted set (6778 ventilations) Se and PPV decreased to 85.3% and 85.6%, respectively. For the whole test set (10683 ventilations) Se and PPV were 90.6% and 90.6%, respectively. Detector's performance clearly degraded when applied to corrupted episodes, this demonstrates the need for techniques to suppress CC artefact to improve ventilation detection.

UR - http://www.scopus.com/inward/record.url?scp=85045094702&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045094702&partnerID=8YFLogxK

U2 - 10.22489/CinC.2017.005-072

DO - 10.22489/CinC.2017.005-072

M3 - Conference article

AN - SCOPUS:85045094702

VL - 44

SP - 1

EP - 4

JO - Computing in Cardiology

JF - Computing in Cardiology

SN - 2325-8861

ER -