Capnography: A support tool for the detection of return of spontaneous circulation in out-of-hospital cardiac arrest

Elola, Andoni; Aramendi, Elisabete; Irusta, Unai; Alonso, Erik; Lu, Yuanzheng; Chang, Mary P.; Owens, Pamela; Idris, Ahamed H.

doi:10.1016/j.resuscitation.2019.03.048

Cited by 24 publications

(34 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the TI provides additional information, an accurate distinction is not possible with F1-scores of 80.6% and 86.2%, for PEA and PR respectively. A further increase may be expected adding information from other OHCA sources, such as the capnogram [9], although this information may not always be available in the defibrillator. Figure 4 shows a PR rhythm segment misclassified as PEA.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Multimodal Biosignal Analysis Algorithm for the Classification of Cardiac Rhythms During Resuscitation

Lasa

Irusta

Eftestøl

et al. 2020

2020 Computing in Cardiology Conference (CinC)

Self Cite

View full text Add to dashboard Cite

Monitoring the heart rhythm during out-of-hospital cardiac arrest (OHCA) is important to improve treatment quality. OHCA rhythms fall into five categories: asystole (AS), pulseless electrical activity (PEA), pulse-generating rhythms (PR), ventricular fibrillation (VF) and ventricular tachycardia (VT). This paper introduces an algorithm to classify these OHCA rhythms using the ECG and the thorax impedance (TI) signals recorded by the defibrillation pads. The dataset consisted of 100 OHCA patient files from which 2833 4-s signal segments were extracted: 423 AS, 912 PE, 689 PR, 643 VF, and 166 VT. The Stationary Wavelet Transform (SWT) was used to obtain 95 features from the ECG and the TI. Random Forest classifiers were used, features were ranked during training using random forest importance, and models with increasing number of features were evaluated. The optimal classifier was obtained combining 50 ECG and TI features, with a median (80% confidence interval) average recall of 86.5%

show abstract

Section: Discussionmentioning

confidence: 99%

“…That is, the distinction between PEA (no pulse) and PR (pulse). PEA/PR classification improves when other signals such as the thoracic impedance (TI) or the capnogram are also used [8], [9]. Defibrillators currently record the TI to adjust defibrillation energy levels and to monitor the quality of cardiopulmonary resuscitation (CPR) [10].…”

Section: Introductionmentioning

confidence: 99%

Multimodal Biosignal Analysis Algorithm for the Classification of Cardiac Rhythms During Resuscitation

Lasa

Irusta

Eftestøl

et al. 2020

2020 Computing in Cardiology Conference (CinC)

Self Cite

View full text Add to dashboard Cite

show abstract

“…In steady state, exhaled CO 2 bears no relationship to cardiac output, but changes, such as due to the return of spontaneous circulation, are typically signaled by a clear rise in the P ETCO 2 . 46,47 The values of P ETCO 2 at the onset of chest compressions have some value for predicting whether return of spontaneous circulation will be achieved, presumably because they relate to how effectively compressions are generating blood flow, although current guidelines discourage using this in isolation to terminate resuscitation attempts. 48 Capnography as a Predictor of Fluid Responsiveness.…”

Section: Capnographymentioning

confidence: 99%

Monitoring Gas Exchange

Schmidt

2020

Respir Care

View full text Add to dashboard Cite

Critical illness can threaten the adequacy of O 2 delivery or CO 2 excretion. Monitoring seeks to identify the adequacy of oxygenation and ventilation and to detect deterioration early. Advances in oximetry, capnography, and transcutaneous CO 2 monitoring offer new opportunities for more accurate estimation of gas exchange, noninvasive monitoring of parameters previously not amenable (eg, total hemoglobin measurement), detection of disease, and prediction of fluid responsiveness.

show abstract

“…A similar behavior was observed for the sensitivities of VT and PR in the 5-class problem, although in this case the sensitivity of PEA, the rhythm that borders PR and VT, decreased considerably from 83.1 % to 25.1 %. PEA sensitivity could be better addressed using multimodal analysis by adding information on perfusion from other signals like pulse oximetry, invasive blood pressure, brain oximetry or expired CO 2 when available [54], [55].…”

Section: A Selection Of Parametersmentioning

confidence: 99%

Automatic Cardiac Rhythm Classification With Concurrent Manual Chest Compressions

et al. 2019

Self Cite

View full text Add to dashboard Cite

Electrocardiogram (EKG) based classification of out-of-hospital cardiac arrest (OHCA) rhythms is important to guide treatment and to retrospectively elucidate the effects of therapy on patient response. OHCA rhythms are grouped into five categories: ventricular fibrillation (VF) and tachycardia (VT), asystole (AS), pulseless electrical activity (PEA), and pulse-generating rhythms (PR). Clinically these rhythms are grouped into broader categories like shockable (VF/VT), non-shockable (AS/PEA/PR), or organized (ORG, PEA/PR). OHCA rhythm classification is further complicated because EKGs are corrupted by cardiopulmonary resuscitation (CPR) artifacts. The objective of this study was to demonstrate a framework for automatic multiclass OHCA rhythm classification in the presence of CPR artifacts. In total, 2133 EKG segments from 272 OHCA patients were used: 580 AS, 94 PR, 953 PEA, 479 VF, and 27 VT. CPR artifacts were adaptively filtered, 93 features were computed from the stationary wavelet transform analysis, and random forests were used for classification. A repeated stratified nested cross-validation procedure was used for feature selection, parameter tuning, and model assessment. Data were partitioned patient-wise. The classifiers were evaluated using per class sensitivity, and the unweighted mean of sensitivities (UMS) as a global performance metric. Four levels of clinical detail were studied: shock/no-shock, shock/AS/ORG, VF/VT/AS/ORG, and VF/VT/AS/PEA/PR. The median UMS (interdecile range) for the 2, 3, 4, and 5-class classifiers were: 95.4% (95.1-95.6), 87.6% (87.3-88.1), 80.6% (79.3-81.8), and 71.9% (69.5-74.6), respectively. For shock/no-shock decisions sensitivities were 93.5% (93.0-93.9) and 97.2% (97.0-97.4), meeting clinical standards for artifact-free EKG. The UMS for five classes with CPR artifacts was 5.8-points below that of the best algorithms without CPR artifacts, but improved the UMS of latter by over 19-points for EKG with CPR artifacts. A robust and accurate approach for multiclass OHCA rhythm classification during CPR has been demonstrated, improving the accuracy of the current state-of-the-art methods.INDEX TERMS Out-of-hospital cardiac arrest (OHCA), electrocardiogram (EKG), cardiopulmonary resuscitation (CPR), adaptive filter, stationary wavelet transform (SWT), random forest (RF) classifier. I. INTRODUCTIONOut-of-hospital cardiac arrest (OHCA) is a leading cause of death in the industrialized world. In Europe the estimated annual average incidence of ambulance treated casesThe associate editor coordinating the review of this manuscript and approving it for publication was Nuno Garcia. is 41 (range 19-104) per 100 000 persons [1]. Patients in cardiac arrest lose their cardiac and respiratory function, and die within minutes if not treated. Treatment consists of highly time-sensitive interventions such as: recognition, call for help, cardiopulmonary resuscitation (CPR), defibrillation, and post-resuscitation care. Bystanders and lay rescuers can provide CPR to maintain an artificial perfus...

show abstract

Capnography: A support tool for the detection of return of spontaneous circulation in out-of-hospital cardiac arrest

Cited by 24 publications

References 41 publications

Multimodal Biosignal Analysis Algorithm for the Classification of Cardiac Rhythms During Resuscitation

Multimodal Biosignal Analysis Algorithm for the Classification of Cardiac Rhythms During Resuscitation

Monitoring Gas Exchange

Automatic Cardiac Rhythm Classification With Concurrent Manual Chest Compressions

Contact Info

Product

Resources

About