Shock Advisory System for Heart Rhythm Analysis During Cardiopulmonary Resuscitation Using a Single ECG Input of Automated External Defibrillators

Survival from out-of-hospital cardiac arrests depends on an accurate defibrillatory shock decision during cardiopulmonary resuscitation (CPR). Since chest compressions induce severe motion artifact in the electrocardiogram (ECG), current automatic external defibrillators (AEDs) do not perform CPR during the rhythm analysis period. However, performing continuous CPR is vital and dramatically increases the chance of survival. Hence, we demonstrate a novel application of a deep convolutional neural network encoder-decoder (CNNED) method in suppressing CPR artifact in near real-time using only ECG data. The encoder portion of the CNNED uses the frequency and phase contents derived via time-varying spectral analysis to learn distinct features that are representative of both the ECG signal and CPR artifact. The decoder portion takes the results from the encoder and reconstructs what is perceived as the motion artifact removed ECG data. These procedures are done via multitude of training of CNNED using many different arrhythmia contaminated with CPR. In this study, CPR-contaminated ECGs were generated by combining clean ECG with CPR artifacts from 52 different performers. ECG data from CUDB, VFDB, and SDDB datasets which belong to the Physionet’s Physiobank archive were used to create the training set containing 89,984 14-second ECG segments. The performance of the proposed CNNED was evaluated on a separate test set comprising of 23,816 CPR-contaminated 14-second ECG segments from 458 subjects. The results were evaluated by two metrics: signal-to-noise ratio (SNR), and Defibtech’s AED rhythm analysis algorithm. CNNED resulted in the increase of the mean SNR value from -3 dB to 5.63 dB and 6.3 dB for shockable and non-shockable rhythms, respectively. Comparing Defibtech’s AED rhythm classifier before and after applying CNNED on the CPR-contaminated ECG, the specificity improved from 96.57% to 99.31% for normal sinus rhythm, and from 91.5% to 96.57% for other non-shockable rhythms. The sensitivity of shockable detection also increased from 67.68% to 87.76% for ventricular fibrillation, and from 62.71% to 81.27% for ventricular tachycardia. These results indicate continuous and accurate AED rhythm analysis without stoppage of CPR using only ECG data.

Download Full-text

Abstract 32: Chest Compression Fraction Increased When Police Used AED That Analyses Heart Rhythm During CPR

Circulation ◽

10.1161/circ.140.suppl_2.32 ◽

2019 ◽

Vol 140 (Suppl_2) ◽

Author(s):

Corina de Graaf ◽

Stefanie G Beesems ◽

Ronald E Stickney ◽

Fred W Chapman ◽

Rudolph W Koster

Keyword(s):

Cardiac Arrest ◽

Cardiopulmonary Resuscitation ◽

Chest Compression ◽

Heart Rhythm ◽

Chest Compressions ◽

Automated External Defibrillators ◽

Ecg Analysis ◽

Conventional Analysis

Introduction: Conventional automated external defibrillators (AED) prompt rescuers to stop cardiopulmonary resuscitation (CPR) for ECG analysis during cardiac arrest (CA), but pauses in CPR are associated with worse outcome. A new AED algorithm, cprINSIGHT™ Analysis Technology, analyses the ECG while rescuers continue chest compressions. Hypothesis: Compared to conventional AEDs, AEDs with the cprINSIGHT algorithm will lead to fewer and shorter interruptions of chest compressions for ECG analysis and, thereby, a higher chest compression fraction (CCF). Methods: Amsterdam Police used conventional AEDs in 2016 (LIFEPAK® 1000 defibrillator) and AEDs with cprINSIGHT in 2018 (LIFEPAK CR2 AED); in the CR2 AED, cprINSIGHT is activated after the first conventional analysis. We analysed AED data from control CA cases in 2016 and intervention CA cases in 2018, comparing pre-shock pause, median CCF and CCF categories. CCF was defined as the proportion of time with chest compressions in the period from the start of CPR after analysis 1 to the start of CPR after analysis 2. The CCF analysis included only cases where CPR was provided with a ratio of 30 compressions to 2 ventilations. Results: Data from 111 control and 87 intervention cases were analysed. The initial recorded rhythm was shockable in 42 control cases (38%) and 36 intervention cases (41%). Rhythm during analysis 2 was shockable in 28/103 (27%) control and 19/80 (24%) intervention cases; 15 cases had no second analysis. In 67/80 (84%) intervention cases, analysis 2 reached a decision without prompting for a CPR pause. Intervention cases had a significantly shorter pre-shock pause than control cases (7 sec vs 22 sec, p < 0.001) and significantly higher median CCF (87% vs 77%, P<0.001). CCF was ≥90% in 38% of intervention cases and 10% of control cases (figure). Conclusion: The use of the cprINSIGHT algorithm in AEDs leads to a shorter pre-shock pause, fewer analysis pauses and an increase in CCF compared to conventional AEDs.

Download Full-text

Essentials of Heart Rhythm Analysis

JAMA ◽

10.1001/jama.1973.03230110050029 ◽

1973 ◽

Vol 226 (11) ◽

pp. 1362

Author(s):

Massimo Calabresi

Keyword(s):

Heart Rhythm ◽

Rhythm Analysis

Download Full-text

Abstract 125: Automated External Defibrillator Shock Advisement Performance Among Multiple Human Electrocardiographic Rhythms and Devices

Circulation ◽

10.1161/circ.140.suppl_2.125 ◽

2019 ◽

Vol 140 (Suppl_2) ◽

Author(s):

Xavier J Szigethy ◽

Connor J Willson ◽

David D Salcido ◽

Dylan A Defilippi ◽

James J Menegazzi

Keyword(s):

Sensitivity And Specificity ◽

Real World ◽

Peak Frequency ◽

Lead Wire ◽

Digital To Analog Converter ◽

Automated External Defibrillators ◽

Signal Characteristics ◽

Rhythm Analysis ◽

High Degree ◽

Median Slope

Background: Automated external defibrillators (AEDs) perform rhythm analysis in order to facilitate defibrillation. The effectiveness of AEDs is dependent on the accuracy of their rhythm classification, which includes differentiation of shockable rhythms from non-shockable rhythms Independent (i.e. non-industry) evaluation of the performance of AEDs against real-world ECG could lead to improvements in their performance. Objective: To evaluate the sensitivity and specificity characteristics of commercial AEDs with respect to quantitative properties of the ECG waveform in several rhythm presentations using real world ECG data. Methods: We conducted a prospective simulation study evaluating three commercially available AEDs from Defibtech, Phillips, and Zoll on the determination of ECG rhythm shockability. Performance was evaluated for 181 human ECG recordings (101 ventricular fibrillation-VF, 55 PEA, and 25 asystole) ranging widely in signal characteristics, obtained from the Pittsburgh site of the Resuscitation Outcomes Consortium. We used a commercially available digital-to-analog converter (National Instruments USB-6001) to inject the recordings into each AED through a direct lead-wire interface, recording shock advisement decisions in a best-out-of-three approach for each device/rhythm pairing. We calculated the sensitivity and specificity for discriminating VF and non-VF rhythms for each device and overall. VF signal characteristics were calculated, including peak frequency, median amplitude, and peak amplitude, and the VF quantitative waveform measures AMSA and median slope. Results: The 101 VF trials featured signals with mean peak frequency 10.02 Hz(IQR 4.80 Hz), mean AMSA 9.13(IQR 7.29), mean median slope 6.72 (IQR 3.66). The sensitivities were: Defibtech 99.0%; Philips 97.0%; Zoll 98.0%. The specificities were: Defibtech 98.7%; Philips 96.2%; Zoll 97.4%. Defibtech recorded 5 discordant advisements and Philips and Zoll recorded eight each. The overall sensitivity was 98.0%, and the specificity 97.4%. Conclusion: Evaluated against a wide variety of real-world signal presentations, commercial AEDs demonstrated a high degree of sensitivity and specificity for shockable ECG rhythms.

Download Full-text

Abstract 2688: Automated Rhythm Analysis To Reduce Pauses During Cardiopulmonary Resuscitation

Circulation ◽

10.1161/circ.118.suppl_18.s_765-c ◽

2008 ◽

Vol 118 (suppl_18) ◽

Author(s):

Joseph L Sullivan ◽

Robert G Walker ◽

Isabelle L Banville ◽

Thomas D Rea ◽

Fred W Chapman

Keyword(s):

Cardiopulmonary Resuscitation ◽

American Heart Association ◽

American Heart ◽

Heart Association ◽

Current Approach ◽

Adjacent Segment ◽

Automatic External Defibrillator ◽

Predictive Values ◽

Rhythm Analysis ◽

External Defibrillator

Background : Pauses in cardiopulmonary resuscitation (CPR) for Automatic External Defibrillator (AED) ECG analysis may adversely affect cardiac arrest resuscitation. Thus, approaches that analyze the ECG rhythm during CPR may improve outcomes. We developed and tested an Analysis During CPR (ADC) algorithm to determine if it would meet the American Heart Association recommended 90% sensitivity for coarse (>0.2 mV peak-peak) ventricular fibrillation (VF) and 95% specificity for non-shockable rhythms. Methods : Defibrillator ECG and impedance recordings from 162 patients were retrospectively gathered from 3 EMS systems. 1047 15-second CPR-artifacted segments (274 coarse VF + 773 non-shockable) were identified for analysis; their artifact and rhythm distributions reflect those found in the 162 patients. Each CPR artifacted segment was paired with an adjacent segment free of CPR artifact for reference. Independent reviewers manually annotated and verified Shock/No-Shock rhythm designations blinded to the ADC determination. The ADC algorithm automatically classified each segment into categories of Shock/No Shock/Pause CPR For Clean Analysis, where the last category is segments recognized by the ADC as too noisy for accurate Shock/No Shock determination. In those situations the device would revert to the current approach of a CPR pause for AED rhythm analysis. Results : Of the 1047 CPR-artifacted segments, the ADC recommended to “Pause CPR For Clean Analysis” in 10% (n=109), including 4.4% of VF segments (12/274) and 12% (97/773) of non-shockable segments. Of the 938 remaining segments, the ADC correctly identified VF in 97% (sensitivity: 255/262) and correctly identified nonshockable rhythms in 96% (specificity: 650/676). Corresponding positive and negative predictive values were 91% and 99% respectively. Conclusions : The ADC is the first algorithm for automated ECG rhythm analysis during ongoing CPR that has been demonstrated to meet the existing AHA sensitivity and specificity recommendations designed for traditional rhythm analysis during hands-off pauses. Incorporation of this algorithm into an AED may eliminate about 90% of analysis pauses without compromising analysis accuracy and in turn may improve the likelihood of resuscitation.

Download Full-text

Abstract 18: Analyzing Heart Rhythm During Chest Compressions in Out-of-Hospital Cardiac Arrest Patients Using New Algorithm for Automated External Defibrillators

Circulation ◽

10.1161/circ.138.suppl_2.18 ◽

2018 ◽

Vol 138 (Suppl_2) ◽

Author(s):

Corina de Graaf ◽

Stefanie G Beesems ◽

Ronald E Stickney ◽

Paula Lank ◽

Fred W Chapman ◽

...

Keyword(s):

Cardiac Arrest ◽

Negative Impact ◽

Pulseless Electrical Activity ◽

Heart Rhythm ◽

Chest Compressions ◽

Study Region ◽

Automated External Defibrillators ◽

Conventional Analysis ◽

Hospital Cardiac Arrest ◽

Conventional Algorithm

Purpose: Automated external defibrillators (AED) prompt the rescuer to stop cardiopulmonary resuscitation (CPR) for ECG analysis. Any interruption of CPR has a negative impact on outcome. We prospectively evaluated a new algorithm (cprINSIGHT) which can analyse the ECG while rescuers continue CPR. Methods: We analysed data from patients with attempted resuscitation from OHCA who were connected to an AED with cprINSIGHT (Stryker Physio-Control LIFEPAK CR2) between June 2017 and June 2018 in the Amsterdam Resuscitation Study region. The first analysis in the CR2 is a conventional analysis; subsequent analyses use the cprINSIGHT algorithm. This algorithm classifies the rhythm as shockable (S), non-shockable (NS), or no decision. If no decision, the AED prompts for a pause in CPR and uses its conventional algorithm. The characteristics of the first 3 cprINSIGHT analyses (analyses 2-4) were analysed. Ventricular fibrillation (VF) cases were both coarse and fine VF with a lower threshold of 0.08 mV. Results: Data from 132 consecutive OHCA cases were analysed. The initial recorded rhythm was VF or pulseless ventricular tachycardia (VT) in 35 cases (27%), pulseless electrical activity in 34 cases (25%) and asystole in 63 cases (48%). In 114 cases (86%), 1 or more cprINSIGHT analyses were done. Analyses 2-4 covered 90% of all cprINSIGHT analyses. The analyzed rhythm was VF/VT in 12-17%, organised QRS rhythm in 29-35% and asystole in 51-56% (see table). cprINSIGHT reached a S or NS decision in 65-74% of cases, with a sensitivity of 90-100% and a specificity of 100%. When it reached no decision, the rhythm was asystole in 65-79% of analyses, VF/VT in 0-9% and QRS rhythm in 18-27%; conventional analysis followed. Chest compression fraction was 85-88%, CPR fraction was 99%. Conclusion: This new algorithm analysed the ECG without need for a pause in chest compressions 65-74% of the time and had 90-100% sensitivity and 100% specificity when it made a shock or a no shock decision.

Download Full-text

Resuscitation on the field: basic and advanced life support and automatic external defibrillators

The ESC Textbook of Sports Cardiology ◽

10.1093/med/9780198779742.003.0044 ◽

2019 ◽

pp. 403-410

Author(s):

Mark S. Link ◽

Mark Estes III

Keyword(s):

Cardiac Arrest ◽

Cardiopulmonary Resuscitation ◽

Basic Life Support ◽

Life Support ◽

Action Plan ◽

Advanced Life Support ◽

Advanced Cardiac Life Support ◽

Screening Strategy ◽

Automated External Defibrillators ◽

Playing Field

Resuscitation on the playing field is at least as important as screening in the prevention of death. Even if a screening strategy is largely effective, individuals will suffer sudden cardiac arrests. Timely recognition of a cardiac arrest with rapid implementation of cardiopulmonary resuscitation (CPR) and deployment and use of automated external defibrillators (AEDs) will save lives. Basic life support, including CPR and AED use, should be a requirement for all those involved in sports, including athletes. An emergency action plan is important in order to render advanced cardiac life support and arrange for transport to medical centres.

Download Full-text