Mixed convolutional and long short-term memory network for the detection of lethal ventricular arrhythmia

Abstract

Early defibrillation by an automated external defibrillator (AED) is key for the survival of out-of-hospital cardiac arrest (OHCA) patients. ECG feature extraction and machine learning have been successfully used to detect ventricular fibrillation (VF) in AED shock decision algorithms. Recently, deep learning architectures based on 1D Convolutional Neural Networks (CNN) have been proposed for this task. This study introduces a deep learning architecture based on 1D-CNN layers and a Long Short-Term Memory (LSTM) network for the detection of VF. Two datasets were used, one from public repositories of Holter recordings captured at the onset of the arrhythmia, and a second from OHCA patients obtained minutes after the onset of the arrest. Data was partitioned patient-wise into training (80%) to design the classifiers, and test (20%) to report the results. The proposed architecture was compared to 1D-CNN only deep learners, and to a classical approach based on VF-detection features and a support vector machine (SVM) classifier. The algorithms were evaluated in terms of balanced accuracy (BAC), the unweighted mean of the sensitivity (Se) and specificity (Sp). The BAC, Se, and Sp of the architecture for 4-s ECG segments was 99.3%, 99.7%, and 98.9% for the public data, and 98.0%, 99.2%, and 96.7% for OHCA data. The proposed architecture outperformed all other classifiers by at least 0.3-points in BAC in the public data, and by 2.2-points in the OHCA data. The architecture met the 95% Sp and 90% Se requirements of the American Heart Association in both datasets for segment lengths as short as 3-s. This is, to the best of our knowledge, the most accurate VF detection algorithm to date, especially on OHCA data, and it would enable an accurate shock no shock diagnosis in a very short time.

Rhythm Analysis during Cardiopulmonary Resuscitation Using Convolutional Neural Networks

“…For these experiments the 10 features at the output of the first fully connected layer were used as the features learned by the algorithm, these features will be named . To evaluate feature extraction two experiments were conducted [ 36 ], and the results were compared to those obtained using the multiresolution features based on the SWT in the baseline model [ 25 ]. First, a dimensionality reduction experiment was conducted by projecting the feature space into a 2-D space using the t-distributed stochastic neighbor embedding (t-SNE) algorithm [ 49 ].…”

“…Deep learning algorithms using convolutional neural networks (CNN) are end-to-end solutions in which the algorithm learns efficient internal representations of the data (features) and combines them to solve the classification task [ 34 , 35 ]. Deep learning algorithms have already been shown to outperform classical machine learning algorithms in some OHCA applications, such as detection of VF in artifact free ECG [ 30 , 36 ], or the detection of pulse [ 37 ]. However, deep learning has not been applied to design algorithms that give accurate shock/no-shock decisions during CPR.…”

Heartbeat Classification Based on Multifeature Combination and Stacking-DWKNN Algorithm

“…Some researchers [ 5 – 8 ] employed convolutional neural networks (CNNs), which automatically extract the ECG features and significantly improve the final prediction. Some works [ 9 , 10 ] proposed a deep learning architecture based on a convolutional recurrent neural network (GRNN) to detect arrhythmias. Li et al [ 11 ] designed the architecture of the deep neural network, CraftNet, for accurately recognizing the features, and assembled multiple child classifiers to classify heartbeats.…”

Detection and Categorisation of Multilevel High-sensitivity Cardiovascular Biomarkers from Lateral Flow Immunoassay Images via Recurrent Neural Networks

“…Recurrent Neural Networks (RNN) are a class of artificial neural networks that are capable of exhibiting dynamic behaviour along a temporal sequence. Long Short-Term Memory (LSTM) networks [Hochreiter and Schmidhuber, 1997] are a special kind of RNN that are able to learn long-term dependencies in time series data that have been successfully applied to speech recognition [Fernández et al, 2007], language modelling [Jozefowicz et al, 2016] and ECG arrhythmia detection [Picon et al, 2019] [ Xiong et al, 2018]. In this study, we explore the potential of applying LSTM to detect multilevel hs-CRP by considering the LFA image data as time series signals.…”