ECGAug: A novel method of generating augmented annotated electrocardiogram QRST complexes and rhythm strips. (July 2021)

• Record Type: Journal Article
• Authors: Stabenau, Hans Friedrich; Bridge, Christopher P.; Waks, Jonathan W.
• Is Part Of: Computers in biology and medicine. Volume 134(2021)
• Publication Date: 2021-07
• Subjects: Data augmentation -- Neural networks -- Time series -- Electrocardiogram -- Annotation; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2021.104408
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Applications of neural networks (NNs) in medicine have increased dramatically in recent years. In order to train a NN that performs ECG segmentation, it can be very time consuming, or even completely prohibitive, to manually annotate fiducial points on enough QRST complexes to reach a high level of performance. Existing methods for time series data augmentation risk creating non-physiological ECG signals that may hamper NN training, and are unable to provide accurate fiducial point locations in the augmented data. We therefore developed ECGAug, a new method which generates an augmented training set of QRST signals (single beats or rhythm strips) with accurate fiducial point annotations. Our algorithm recombines a library of existing, annotated QRS complexes and T waves in physiologic ways, and then performs additional physiological transformations to generate a set of new annotated QRST complexes or rhythm strips to be used for NN training or validation of ECG annotation algorithms. In experiments where we trained NNs to annotate QRST complexes with a limited training dataset, QRST complexes added to the training dataset by ECGAug significantly improved NN performance. We present the ECGAug process, demonstrate its efficacy, and provide links for downloading the open source ECGAug software. Highlights: ECGAug allows generation of augmented QRST signals with accurate fiducial point annotations. Augmented signals can be used for neural network training or validation of ECG annotation algorithms. Individual annotated QRST complexes or longer annotated rhythm strips can be generated. Open source ECGAug software is available at https://github.com/BIVectors/ECGAug .