Deep Neural Network Approach for Continuous ECG‐Based Automated External Defibrillator Shock Advisory System During Cardiopulmonary Resuscitation

Abstract

Background Because chest compressions induce artifacts in the ECG, current automated external defibrillators instruct the user to stop cardiopulmonary resuscitation (CPR) while an automated rhythm analysis is performed. It has been shown that minimizing interruptions in CPR increases the chance of survival. Methods and Results The objective of this study was to apply a deep‐learning algorithm using convolutional layers, residual networks, and bidirectional long short‐term memory method to classify shockable versus nonshockable rhythms in the presence and absence of CPR artifact. Forty subjects' data from Physionet with 1131 shockable and 2741 nonshockable samples contaminated with 43 different CPR artifacts that were acquired from a commercial automated external defibrillator during asystole were used. We had separate data as train and test sets. Using our deep neural network model, the sensitivity and specificity of the shock versus no‐shock decision for the entire data set over the 4‐fold cross‐validation sets were 95.21% and 86.03%, respectively. This result was based on the training and testing of the model using ECG data in both the presence and the absence of CPR artifact. For ECG without CPR artifact, the sensitivity was 99.04% and the specificity was 95.2%. A sensitivity of 94.21% and a specificity of 86.14% were obtained for ECG with CPR artifact. In addition to 4‐fold cross‐validation sets, we also examined leave‐one‐subject‐out validation. The sensitivity and specificity for the case of leave‐one‐subject‐out validation were 92.71% and 97.6%, respectively. Conclusions The proposed trained model can make shock versus nonshock decision in automated external defibrillators, regardless of CPR status. The results meet the American Heart Association's sensitivity requirement (>90%).

Optimization of End-to-End Convolutional Neural Networks for Analysis of Out-of-Hospital Cardiac Arrest Rhythms during Cardiopulmonary Resuscitation

“…Therefore, the presented CNN architectures are not optimized to directly process CC artifacts. The latter important optimization is shown in the study of Hajeb-M et al [49] for a hybrid DNN architecture, including a combination of convolutional layers, residual blocks and bidirectional LSTM layers. The classification of Sh/NSh rhythms is relying on redundant input information from time and frequency domain ECG representations, such as concatenation of raw ECG samples with amplitude and phase coefficients of short-time Fourier transform.…”

“…Hybrid architectures, including recurrent long short-term memory (LSTM) layers have also been applied, although LSTM is computationally expensive and alone has not demonstrated better performance than fully CNN [38]. In conditions of CPR artifacts, only three recent publications were found to investigate DNNs for detection of shockable (Sh) and non-shockable (NSh) rhythms [47][48][49]. Similarly to their previous studies [15,16,50], Isasi et al [47,48] rely on the strategy for pre-filtering of CC artifacts by a recursive least squares filter using information for instantaneous CC periods derived either through compression depth signal from external accelerometer sensor or strictly controlled by a mechanical chest compression device.…”

Automated Condition-Based Suppression of the CPR Artifact in ECG Data to Make a Reliable Shock Decision for AEDs during CPR

“…Recently, methods have been introduced based on deep learning approaches to directly analyze CPR-contaminated ECG rhythms without filtering the CPR artifact [17,28]. These algorithms provide a relatively accurate shock versus no-shock classification.…”

“…Almost all of the above-noted methods require one or more reference signals (such as chest pressure, chest displacement, chest acceleration, compression depth, or thoracic impedance). As most of the current AEDs do not have the hardware availability to capture the reference signal, the dependency on the reference signal is a deficiency of the available methods [17]. Unfortunately, only a few algorithms have been developed without reference signals.…”

LDIAED: A lightweight deep learning algorithm implementable on automated external defibrillators

“…The study in [18] was to assess the feasibility of feeding two-dimensional (2D) time-frequency maps of electrocardiogram (ECG) segment into deep convolutional neural network to automatically detect shockable signals with emphasis on optimizing the convolutional neural network model and shortening the analysis segment. The objective of [19] was to apply a deep-learning algorithm using convolutional layers, residual networks, and bidirectional long short-term memory to classify shockable versus non-shockable signals in the presence and absence of CPR artifact components associated with the mechanical activity of compressions and ventilation of the heart.…”