Sensitivity and specificity of two different automated external defibrillators

The diagnostic accuracy of a shock advisory algorithm in automated external defibrillators in the presence of real-world artifacts

BACKGROUND

The current standards for shock advisory algorithms in AEDs require performance testing on artifact-free ECGs. However, AED analysis in the real world is more challenging due to potential artifacts from various sources (e.g., patient handling, and electromagnetic interference). This retrospective data analysis reports the real-world performance and behavior of a shock advisory algorithm used in three AED models with the presence of artifacts.

METHODS

ECG rhythm analyses recorded during the use of three AED models (HS1, FRx and FR3) were reviewed. The shock recommendations made in the AEDs were compared to the expert annotations of reviewers. The effects of real-world artifacts and the handling by the algorithm were analyzed.

RESULTS

Among the 3,941 analyses, 619 were annotated as shockable rhythms, and 2,912 were non-shockable. The overall sensitivity and specificity were 97.1% (601/619), and 99.9% (2,908/2,912), respectively. Artifacts were detected by the algorithm in 23.3% (918/3,941) of the analysis periods. The algorithm performance for the analysis periods with artifacts detected was 95.2% (80/84) for sensitivity and 100.0% (687/687) for specificity. In the remaining analysis periods with no artifacts detected, the sensitivity was 97.4% (521/535), and specificity was 99.8% (2,221/2,225).

CONCLUSIONS

The performance of this shock advisory algorithm during real-world resuscitations with or without artifacts, exceeded AHA recommendations and the requirements in international standards. The high sensitivity and specificity demonstrate the effectiveness and safety of this algorithm in all three AED models.

In-hospital cardiac arrest rhythm analysis by anesthesiologists: a diagnostic performance study

PURPOSE

In-hospital cardiac arrest is associated with high morbidity and mortality, with an overall survival rate at one year of approximately 13%. The first cardiac rhythm is often analyzed by anesthesiologist-intensivists. We aimed to determine the diagnostic performance of anesthesiologist-intensivists when distinguishing between shockable and nonshockable rhythms.

METHODS

We conducted a simulation-based, multicentre, prospective, observational study between May 2019 and March 2020. The responses of the participants were used to calculate individual sensitivity (defined as the proportion of decisions to shock for shockable rhythms) and individual specificity (defined as the proportion of decisions not to shock for nonshockable rhythms). The main outcome measure was the overall diagnostic performance, defined as the overall sensitivity and specificity. Secondary outcome measures were the sensitivity and specificity of participants' decisions for each type of cardiac arrest rhythm and their decision-making times.

RESULTS

Among the 267 physicians contacted, 179 (67%) completed the test. The median [interquartile range (IQR)] overall sensitivity was 88 [79-95]% and the median overall specificity was 86 [77-92]%. Among shockable rhythms, the median [IQR] sensitivity was 100 [100-100]% for ventricular tachycardia (VT), 100 [100-100]% for coarse ventricular fibrillation (VF), and 60 [20-100]% for fine VF. The median [IQR] specificities for nonshockable rhythms were 93 [86-100]% for asystole and 83 [72-86]% for pulseless electrical activity. The median decision times ranged from 2.0 to 3.5 sec.

CONCLUSION

Anesthesiologist-intensivists were quickly and effectively able to analyze rhythms in this simulation-based study. Participants' sensitivity in deciding to deliver shocks for VT and coarse VF was excellent, while specificity of their decisions for pulseless electrical activity was insufficient.

Assessment of emergency physicians' performance in identifying shockable rhythm in out-of-hospital cardiac arrest: an observational simulation study

BACKGROUND

Emergency physicians can use a manual or an automated defibrillator to provide defibrillation of patients who had out-of-hospital cardiac arrest (OHCA). Performance of emergency physicians in identifying shockable rhythm with a manual defibrillator has been poorly explored whereas that of automated defibrillators is well known (sensitivity 0.91-1.00, specificity 0.96-0.99). We conducted this study to estimate the sensitivity/specificity and speed of shock/no-shock decision-making by prehospital emergency physicians for shockable or non-shockable rhythm, and their preference for manual versus automated defibrillation.

METHODS

We developed a web application that simulates a manual defibrillator (https://simul-shock.firebaseapp.com/). In 2019, all (262) emergency physicians of six French emergency medical services were invited to participate in a study in which 60 ECG rhythms from real OHCA recordings were successively presented to the physicians for determination of whether they would or would not administer a shock. Time to decision was recorded. Answers were compared with a gold standard (concordant answers of three experts). We report sensitivity for shockable rhythms (decision to shock) and specificity for non-shockable rhythms (decision not to shock). Physicians were also asked whether they preferred manual or automated defibrillation.

RESULTS

Among 215 respondents, we were able to analyse results for 190 physicians. 57% of emergency physicians preferred manual defibrillation. Median (IQR) sensitivity for a shock delivery for shockable rhythm was 0.91 (0.81-1.00); median specificity for no-shock delivery for non-shockable rhythms was 0.91 (0.80-0.96). More precisely, sensitivities for shock delivery for ventricular tachycardia (VT) and coarse ventricular fibrillation (VF) were both 1.0 (1.0-1.0); sensitivity for fine VF was 0.6 (0.2-1). Specificity for not shocking a pulseless electrical activity (PEA) was 0.83 (0.72-0.86), and for asystole, specificity was 0.93 (0.86-1). Median speed of decision-making (in seconds) were: VT 2.0 (1.6-2.7), coarse VF 2.1 (1.7-2.9), asystole 2.4 (1.8-3.5), PEA 2.8 (2.0-4.2) and fine VF 2.8 (2.1-4.3).

CONCLUSIONS

Global sensitivity and specificity were comparable with published automated external defibrillator studies. Shockable rhythms with the best clinical prognoses (VT and coarse VF) were very rapidly recognised with very good sensitivity. The decision-making for fine VF or asystole and PEA was less accurate.

Optimizing Outcomes After Out-of-Hospital Cardiac Arrest With Innovative Approaches to Public-Access Defibrillation: A Scientific Statement From the International Liaison Committee on Resuscitation

Out-of-hospital cardiac arrest is a global public health issue experienced by ≈3.8 million people annually. Only 8% to 12% survive to hospital discharge. Early defibrillation of shockable rhythms is associated with improved survival, but ensuring timely access to defibrillators has been a significant challenge. To date, the development of public-access defibrillation programs, involving the deployment of automated external defibrillators into the public space, has been the main strategy to address this challenge. Public-access defibrillator programs have been associated with improved outcomes for out-of-hospital cardiac arrest; however, the devices are used in <3% of episodes of out-of-hospital cardiac arrest. This scientific statement was commissioned by the International Liaison Committee on Resuscitation with 3 objectives: (1) identify known barriers to public-access defibrillator use and early defibrillation, (2) discuss established and novel strategies to address those barriers, and (3) identify high-priority knowledge gaps for future research to address. The writing group undertook systematic searches of the literature to inform this statement. Innovative strategies were identified that relate to enhanced public outreach, behavior change approaches, optimization of static public-access defibrillator deployment and housing, evolved automated external defibrillator technology and functionality, improved integration of public-access defibrillation with existing emergency dispatch protocols, and exploration of novel automated external defibrillator delivery vectors. We provide evidence- and consensus-based policy suggestions to enhance public-access defibrillation and guidance for future research in this area.

Optimizing outcomes after out-of-hospital cardiac arrest with innovative approaches to public-access defibrillation: A scientific statement from the International Liaison Committee on Resuscitation

Out-of-hospital cardiac arrest is a global public health issue experienced by ≈3.8 million people annually. Only 8% to 12% survive to hospital discharge. Early defibrillation of shockable rhythms is associated with improved survival, but ensuring timely access to defibrillators has been a significant challenge. To date, the development of public-access defibrillation programs, involving the deployment of automated external defibrillators into the public space, has been the main strategy to address this challenge. Public-access defibrillator programs have been associated with improved outcomes for out-of-hospital cardiac arrest; however, the devices are used in <3% of episodes of out-of-hospital cardiac arrest. This scientific statement was commissioned by the International Liaison Committee on Resuscitation with 3 objectives: (1) identify known barriers to public-access defibrillator use and early defibrillation, (2) discuss established and novel strategies to address those barriers, and (3) identify high-priority knowledge gaps for future research to address. The writing group undertook systematic searches of the literature to inform this statement. Innovative strategies were identified that relate to enhanced public outreach, behavior change approaches, optimization of static public-access defibrillator deployment and housing, evolved automated external defibrillator technology and functionality, improved integration of public-access defibrillation with existing emergency dispatch protocols, and exploration of novel automated external defibrillator delivery vectors. We provide evidence- and consensus-based policy suggestions to enhance public-access defibrillation and guidance for future research in this area.

Adult Advanced Life Support: 2020 International Consensus on Cardiopulmonary Resuscitation and Emergency Cardiovascular Care Science with Treatment Recommendations

This 2020 International Consensus on Cardiopulmonary Resuscitation and Emergency Cardiovascular Care Science With Treatment Recommendations for advanced life support includes updates on multiple advanced life support topics addressed with 3 different types of reviews. Topics were prioritized on the basis of both recent interest within the resuscitation community and the amount of new evidence available since any previous review. Systematic reviews addressed higher-priority topics, and included double-sequential defibrillation, intravenous versus intraosseous route for drug administration during cardiac arrest, point-of-care echocardiography for intra-arrest prognostication, cardiac arrest caused by pulmonary embolism, postresuscitation oxygenation and ventilation, prophylactic antibiotics after resuscitation, postresuscitation seizure prophylaxis and treatment, and neuroprognostication. New or updated treatment recommendations on these topics are presented. Scoping reviews were conducted for anticipatory charging and monitoring of physiological parameters during cardiopulmonary resuscitation. Topics for which systematic reviews and new Consensuses on Science With Treatment Recommendations were completed since 2015 are also summarized here. All remaining topics reviewed were addressed with evidence updates to identify any new evidence and to help determine which topics should be the highest priority for systematic reviews in the next 1 to 2 years.

Adult Advanced Life Support: 2020 International Consensus on Cardiopulmonary Resuscitation and Emergency Cardiovascular Care Science With Treatment Recommendations

This 2020 International Consensus on Cardiopulmonary Resuscitation and Emergency Cardiovascular Care Science With Treatment Recommendations for advanced life support includes updates on multiple advanced life support topics addressed with 3 different types of reviews. Topics were prioritized on the basis of both recent interest within the resuscitation community and the amount of new evidence available since any previous review. Systematic reviews addressed higher-priority topics, and included double-sequential defibrillation, intravenous versus intraosseous route for drug administration during cardiac arrest, point-of-care echocardiography for intra-arrest prognostication, cardiac arrest caused by pulmonary embolism, postresuscitation oxygenation and ventilation, prophylactic antibiotics after resuscitation, postresuscitation seizure prophylaxis and treatment, and neuroprognostication. New or updated treatment recommendations on these topics are presented. Scoping reviews were conducted for anticipatory charging and monitoring of physiological parameters during cardiopulmonary resuscitation. Topics for which systematic reviews and new Consensuses on Science With Treatment Recommendations were completed since 2015 are also summarized here. All remaining topics reviewed were addressed with evidence updates to identify any new evidence and to help determine which topics should be the highest priority for systematic reviews in the next 1 to 2 years.

Fully Convolutional Deep Neural Networks with Optimized Hyperparameters for Detection of Shockable and Non-Shockable Rhythms

Deep neural networks (DNN) are state-of-the-art machine learning algorithms that can be learned to self-extract significant features of the electrocardiogram (ECG) and can generally provide high-output diagnostic accuracy if subjected to robust training and optimization on large datasets at high computational cost. So far, limited research and optimization of DNNs in shock advisory systems is found on large ECG arrhythmia databases from out-of-hospital cardiac arrests (OHCA). The objective of this study is to optimize the hyperparameters (HPs) of deep convolutional neural networks (CNN) for detection of shockable (Sh) and nonshockable (NSh) rhythms, and to validate the best HP settings for short and long analysis durations (2-10 s). Large numbers of (Sh + NSh) ECG samples were used for training (720 + 3170) and validation (739 + 5921) from Holters and defibrillators in OHCA. An end-to-end deep CNN architecture was implemented with one-lead raw ECG input layer (5 s, 125 Hz, 2.5 uV/LSB), configurable number of 5 to 23 hidden layers and output layer with diagnostic probability p ∈ [0: Sh,1: NSh]. The hidden layers contain N convolutional blocks × 3 layers (Conv1D (filters = Fi, kernel size = Ki), max-pooling (pool size = 2), dropout (rate = 0.3)), one global max-pooling and one dense layer. Random search optimization of HPs = {N, Fi, Ki}, i = 1, … N in a large grid of N = [1, 2, … 7], Fi = [5;50], Ki = [5;100] was performed. During training, the model with maximal balanced accuracy BAC = (Sensitivity + Specificity)/2 over 400 epochs was stored. The optimization principle is based on finding the common HPs space of a few top-ranked models and prediction of a robust HP setting by their median value. The optimal models for 1-7 CNN layers were trained with different learning rates LR = [10-5; 10-2] and the best model was finally validated on 2-10 s analysis durations. A number of 4216 random search models were trained. The optimal models with more than three convolutional layers did not exhibit substantial differences in performance BAC = (99.31-99.5%). Among them, the best model was found with {N = 5, Fi = {20, 15, 15, 10, 5}, Ki = {10, 10, 10, 10, 10}, 7521 trainable parameters} with maximal validation performance for 5-s analysis (BAC = 99.5%, Se = 99.6%, Sp = 99.4%) and tolerable drop in performance (<2% points) for very short 2-s analysis (BAC = 98.2%, Se = 97.6%, Sp = 98.7%). DNN application in future-generation shock advisory systems can improve the detection performance of Sh and NSh rhythms and can considerably shorten the analysis duration complying with resuscitation guidelines for minimal hands-off pauses.

Automated External Defibrillator Shock Advisement Discordance Among Multiple Electrocardiographic Rhythms and Devices: A Preliminary Report

Background: The early use of automated external defibrillators (AEDs) can save lives by correcting lethal ventricular arrhythmias with minimal operator intervention. AED shock advisements also play a role in termination of resuscitation strategies. AED function is dependent on the accuracy of their shock advisement algorithms, which may differ between manufacturers. We sought to compare the shock advisement performance characteristics of several AEDs. Methods: We conducted a prospective, laboratory-based simulation study evaluating five commercially available AEDs from Cardiac Science, Defibtech, Medtronic, Philips, and Zoll. Shock advisement performance was evaluated for eight ECG rhythms {ventricular fibrillation (VF), ventricular tachycardia (VT), toursades de pointes (TdP), sinus rhythm (SR), atrial fibrillation (AF), atrial flutter (AFL), idioventricular rhythm (IDV), and asystole} that were generated using the SimMan Classic Manikin and the LLEAP Simulator software (Laerdal Medical Inc., Norway). We recorded shock advisement decisions for each of the ECG rhythms three times per device. Shock advisements were coded as discordant if a shock was advised for a non-shockable rhythm or not advised for a shockable rhythm. Results: We analyzed 330 rhythm trials in total (66 per device), finding 28 (8.5%) discordant shock advisements overall. Discordance ranged from 6% to 11% among the five AED models. VF rhythm variants were the most frequent (43%) source of discordant advisements. No shocks were advised for any of the sinus rhythms, AFL, AF with QRS > 40, IDV, or asystole. Conclusions: Discordant shock advisements were observed for each AED and varied between manufacturers, most often involving VF. There may be implications for termination of resuscitation decision making.