Key result
A deep convolutional neural network using 2D time-frequency maps of 3-second ECG segments detected shockable rhythms with 98.82% accuracy, 95.05% sensitivity, and 99.43% specificity.
Why the study?
To assess the feasibility of feeding 2D time-frequency maps of ECG segments into deep convolutional neural networks to automatically detect shockable rhythms while optimizing the model and shortening segment length.
Does a deep learning-based algorithm using 2D time-frequency maps of 3-second ECG segments accurately detect shockable ventricular arrhythmias?
Does a deep learning-based algorithm using 2D time-frequency maps of 3-second ECG segments accurately detect shockable ventricular arrhythmias?
A deep learning-based algorithm using 2D time-frequency maps of 3-second ECG segments can accurately and efficiently detect shockable ventricular arrhythmias, potentially improving public access defibrillation.
Supports DL-based shockable rhythm detection in AEDs; leaves open prospective clinical validation.
Ventricular fibrillation (VF) and rapid ventricular tachycardia (VT) of a heart rate over 180 beats min -1 , commonly known as shockable rhythms (ShR), are life-threatening ventricular arrhythmias. This study was to assess the feasibility of feeding two-dimensional (2D) time-frequency maps of electrocardiogram (ECG) segment into deep convolutional neural network (CNN) to automatically detect ShR with emphases on optimizing the CNN model and shortening the analysis segment. A total of 115 single-lead surface ECG records collected from four publicly accessible ECG databases were divided into non-overlapping 3-second segments as well as 5-, 8-, and 10-second segments for comparisons. For each one-dimension (1D) ECG segment, its 2D time-frequency maps was obtained by employing a continuous wavelet transform (CWT). Moreover, the performance of automated algorithms with eight different CNN models was evaluated for ShR detection against annotations labeled in the databases. A total of 5,795 3-second maps of ShR and 48,648 maps of non-shockable rhythms (NSR) were analyzed successfully, and a promising performance of the automated algorithm with a twelve-layer CNN model was achieved on this segment length in terms of accuracy (98.82%), sensitivity (95.05%), and specificity (99.43%). Compared with current approaches imposing priority either only on highly real-time or high performance, the presented solution suggested that the deep learning based algorithm together with ECG time-frequency maps may offer the possibility of providing an intelligent and efficient detection of ShR and NSR in short segments especially for public access defibrillation.
No takes yet. Share an insight, caveat, or question.
Lai et al. (2020) studied Ventricular fibrillation and rapid ventricular tachycardia (n=115). Deep convolutional neural network (CNN) using 2D time-frequency maps of 3-second ECG segments vs. Database annotations was evaluated on Detection of shockable rhythms. A deep convolutional neural network using 2D time-frequency maps of 3-second ECG segments detected shockable rhythms with 98.82% accuracy, 95.05% sensitivity, and 99.43% specificity.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: