Evaluation of chest compression artefact removal based on rhythm assessments made by clinicians

Erik Alonso, Elisabete Aramendi, Unai Irusta, Mohamud Ramzan Daya, Carlos Corcuera, Yuanzheng Lu, Ahamed H. Idris

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Aim: To evaluate the performance of a state-of-the-art cardiopulmonary resuscitation (CPR) artefact suppression method by assessing to what extent the filtered electrocardiogram (ECG) can be correctly diagnosed by emergency medicine doctors. Methods: A total of 819 ECG segments were used. Each segment contained two consecutive 10 s intervals, an artefact free interval and an interval corrupted by CPR artefacts. Each ECG segment was digitally processed to remove CPR artefacts using an adaptive filter. Each ECG segment was split into artefact-free and filtered intervals, randomly reordered for dissociation, and independently offered to four reviewers for rhythm annotation. The rhythm annotations of the artefact-free intervals were considered as the gold standard against which the rhythm annotations of the filtered intervals were evaluated. For the filtered intervals, the rater agreement (κ Kappa score) with the gold standard, the sensitivity and the specificity were computed individually for each reviewer, and jointly through the majority decision of the pool of reviewers (DPR). These results were also compared to those obtained using a commercial shock advisory algorithm (SAA). Results: The agreement between each reviewer and the gold standard was moderate ranging between κ = 0.41–0.64. The sensitivities and specificities ranged between 64.3–95.0%, and 70.0–95.9%, respectively. The agreement for the DPR was substantial with κ = 0.64 (0.62–0.66), a sensitivity of 90.6%, and a specificity of 85.6%. For the SAA, the agreement was fair with κ = 0.33 (0.31–0.35), a sensitivity of 90.3%, and a specificity of 66.4%. Conclusion: Clinicians outperformed the SAA, but specificities remained below the specifications recommended by the American Heart Association. Visual assessment of the filtered ECG by clinicians is not reliable enough, and varies greatly among clinicians. Results considerably improve by considering the consensus decision of a pool of clinicians.

Original languageEnglish (US)
Pages (from-to)104-110
Number of pages7
JournalResuscitation
Volume125
DOIs
StatePublished - Apr 1 2018

Fingerprint

Artifacts
Thorax
Electrocardiography
Cardiopulmonary Resuscitation
Shock
Sensitivity and Specificity
Emergency Medicine

Keywords

  • Adaptive filter
  • Cardiopulmonary resuscitation (CPR)
  • CPR artefact suppression
  • Rhythm analysis during CPR

ASJC Scopus subject areas

  • Emergency Medicine
  • Emergency
  • Cardiology and Cardiovascular Medicine

Cite this

Evaluation of chest compression artefact removal based on rhythm assessments made by clinicians. / Alonso, Erik; Aramendi, Elisabete; Irusta, Unai; Daya, Mohamud Ramzan; Corcuera, Carlos; Lu, Yuanzheng; Idris, Ahamed H.

In: Resuscitation, Vol. 125, 01.04.2018, p. 104-110.

Research output: Contribution to journalArticle

Alonso, Erik ; Aramendi, Elisabete ; Irusta, Unai ; Daya, Mohamud Ramzan ; Corcuera, Carlos ; Lu, Yuanzheng ; Idris, Ahamed H. / Evaluation of chest compression artefact removal based on rhythm assessments made by clinicians. In: Resuscitation. 2018 ; Vol. 125. pp. 104-110.
@article{0cc32ea3759a4becbcbc101b31b51d39,
title = "Evaluation of chest compression artefact removal based on rhythm assessments made by clinicians",
abstract = "Aim: To evaluate the performance of a state-of-the-art cardiopulmonary resuscitation (CPR) artefact suppression method by assessing to what extent the filtered electrocardiogram (ECG) can be correctly diagnosed by emergency medicine doctors. Methods: A total of 819 ECG segments were used. Each segment contained two consecutive 10 s intervals, an artefact free interval and an interval corrupted by CPR artefacts. Each ECG segment was digitally processed to remove CPR artefacts using an adaptive filter. Each ECG segment was split into artefact-free and filtered intervals, randomly reordered for dissociation, and independently offered to four reviewers for rhythm annotation. The rhythm annotations of the artefact-free intervals were considered as the gold standard against which the rhythm annotations of the filtered intervals were evaluated. For the filtered intervals, the rater agreement (κ Kappa score) with the gold standard, the sensitivity and the specificity were computed individually for each reviewer, and jointly through the majority decision of the pool of reviewers (DPR). These results were also compared to those obtained using a commercial shock advisory algorithm (SAA). Results: The agreement between each reviewer and the gold standard was moderate ranging between κ = 0.41–0.64. The sensitivities and specificities ranged between 64.3–95.0{\%}, and 70.0–95.9{\%}, respectively. The agreement for the DPR was substantial with κ = 0.64 (0.62–0.66), a sensitivity of 90.6{\%}, and a specificity of 85.6{\%}. For the SAA, the agreement was fair with κ = 0.33 (0.31–0.35), a sensitivity of 90.3{\%}, and a specificity of 66.4{\%}. Conclusion: Clinicians outperformed the SAA, but specificities remained below the specifications recommended by the American Heart Association. Visual assessment of the filtered ECG by clinicians is not reliable enough, and varies greatly among clinicians. Results considerably improve by considering the consensus decision of a pool of clinicians.",
keywords = "Adaptive filter, Cardiopulmonary resuscitation (CPR), CPR artefact suppression, Rhythm analysis during CPR",
author = "Erik Alonso and Elisabete Aramendi and Unai Irusta and Daya, {Mohamud Ramzan} and Carlos Corcuera and Yuanzheng Lu and Idris, {Ahamed H.}",
year = "2018",
month = "4",
day = "1",
doi = "10.1016/j.resuscitation.2018.01.056",
language = "English (US)",
volume = "125",
pages = "104--110",
journal = "Resuscitation",
issn = "0300-9572",
publisher = "Elsevier Ireland Ltd",

}

TY - JOUR

T1 - Evaluation of chest compression artefact removal based on rhythm assessments made by clinicians

AU - Alonso, Erik

AU - Aramendi, Elisabete

AU - Irusta, Unai

AU - Daya, Mohamud Ramzan

AU - Corcuera, Carlos

AU - Lu, Yuanzheng

AU - Idris, Ahamed H.

PY - 2018/4/1

Y1 - 2018/4/1

N2 - Aim: To evaluate the performance of a state-of-the-art cardiopulmonary resuscitation (CPR) artefact suppression method by assessing to what extent the filtered electrocardiogram (ECG) can be correctly diagnosed by emergency medicine doctors. Methods: A total of 819 ECG segments were used. Each segment contained two consecutive 10 s intervals, an artefact free interval and an interval corrupted by CPR artefacts. Each ECG segment was digitally processed to remove CPR artefacts using an adaptive filter. Each ECG segment was split into artefact-free and filtered intervals, randomly reordered for dissociation, and independently offered to four reviewers for rhythm annotation. The rhythm annotations of the artefact-free intervals were considered as the gold standard against which the rhythm annotations of the filtered intervals were evaluated. For the filtered intervals, the rater agreement (κ Kappa score) with the gold standard, the sensitivity and the specificity were computed individually for each reviewer, and jointly through the majority decision of the pool of reviewers (DPR). These results were also compared to those obtained using a commercial shock advisory algorithm (SAA). Results: The agreement between each reviewer and the gold standard was moderate ranging between κ = 0.41–0.64. The sensitivities and specificities ranged between 64.3–95.0%, and 70.0–95.9%, respectively. The agreement for the DPR was substantial with κ = 0.64 (0.62–0.66), a sensitivity of 90.6%, and a specificity of 85.6%. For the SAA, the agreement was fair with κ = 0.33 (0.31–0.35), a sensitivity of 90.3%, and a specificity of 66.4%. Conclusion: Clinicians outperformed the SAA, but specificities remained below the specifications recommended by the American Heart Association. Visual assessment of the filtered ECG by clinicians is not reliable enough, and varies greatly among clinicians. Results considerably improve by considering the consensus decision of a pool of clinicians.

AB - Aim: To evaluate the performance of a state-of-the-art cardiopulmonary resuscitation (CPR) artefact suppression method by assessing to what extent the filtered electrocardiogram (ECG) can be correctly diagnosed by emergency medicine doctors. Methods: A total of 819 ECG segments were used. Each segment contained two consecutive 10 s intervals, an artefact free interval and an interval corrupted by CPR artefacts. Each ECG segment was digitally processed to remove CPR artefacts using an adaptive filter. Each ECG segment was split into artefact-free and filtered intervals, randomly reordered for dissociation, and independently offered to four reviewers for rhythm annotation. The rhythm annotations of the artefact-free intervals were considered as the gold standard against which the rhythm annotations of the filtered intervals were evaluated. For the filtered intervals, the rater agreement (κ Kappa score) with the gold standard, the sensitivity and the specificity were computed individually for each reviewer, and jointly through the majority decision of the pool of reviewers (DPR). These results were also compared to those obtained using a commercial shock advisory algorithm (SAA). Results: The agreement between each reviewer and the gold standard was moderate ranging between κ = 0.41–0.64. The sensitivities and specificities ranged between 64.3–95.0%, and 70.0–95.9%, respectively. The agreement for the DPR was substantial with κ = 0.64 (0.62–0.66), a sensitivity of 90.6%, and a specificity of 85.6%. For the SAA, the agreement was fair with κ = 0.33 (0.31–0.35), a sensitivity of 90.3%, and a specificity of 66.4%. Conclusion: Clinicians outperformed the SAA, but specificities remained below the specifications recommended by the American Heart Association. Visual assessment of the filtered ECG by clinicians is not reliable enough, and varies greatly among clinicians. Results considerably improve by considering the consensus decision of a pool of clinicians.

KW - Adaptive filter

KW - Cardiopulmonary resuscitation (CPR)

KW - CPR artefact suppression

KW - Rhythm analysis during CPR

UR - http://www.scopus.com/inward/record.url?scp=85042218644&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042218644&partnerID=8YFLogxK

U2 - 10.1016/j.resuscitation.2018.01.056

DO - 10.1016/j.resuscitation.2018.01.056

M3 - Article

C2 - 29412147

AN - SCOPUS:85042218644

VL - 125

SP - 104

EP - 110

JO - Resuscitation

JF - Resuscitation

SN - 0300-9572

ER -