Key result
An inter-patient ECG classification algorithm using CNN, LSTM, and active learning achieved 97.7% sensitivity for ventricular ectopic beats and 89.4% for supraventricular ectopic beats.
An end-to-end deep learning model using CNN, LSTM, and active learning demonstrates high sensitivity for detecting ventricular and supraventricular ectopic beats on ECG.
May aid automated ectopic beat detection on ECG; leaves open prospective clinical validation before adoption.
In this paper, an inter-patient electrocardiogram (ECG) classification algorithm based on residual networks and active learning is proposed. Our model is an end-to-end model. We use Convolutional Neural Networks (CNN) to extract morphological features of each ECG beat and use Long Short-Term Memory (LSTM) to extract temporal features. we apply active learning to select the most informative beats and incorporate them into the training set to improve algorithm performance. When evaluated on the MIT-BIH Arrhythmia Database, the method our proposed gives 97.7 % sensitivity and 61.6% positive predictive for ventricular ectopic beat (VEB). For supraventricular ectopic beat (SVEB), our method gives 89.4% sensitivity and 41.5% positive predictive. Considering the high sensitivity in detecting these two pathological classes, this method has potential clinical application.
No takes yet. Share an insight, caveat, or question.
Zhou et al. (2021) studied Arrhythmia. ECG classification algorithm based on residual networks and active learning was evaluated on Sensitivity and positive predictive value for ventricular ectopic beat (VEB) and supraventricular ectopic beat (SVEB). An inter-patient ECG classification algorithm using CNN, LSTM, and active learning achieved 97.7% sensitivity for ventricular ectopic beats and 89.4% for supraventricular ectopic beats.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: