Quality assessment of ECG signals acquired with wearable devices is essential to avoid misdiagnosis of some cardiac disorders. For that purpose, novel deep learning algorithms have been recently proposed. However, training of these methods require large amount of data and public databases with annotated ECG samples are limited. Hence, the present work aims at validating the usefulness of a well-known data augmentation approach in this context of ECG quality assessment. Precisely, classification between high- and low-quality ECG excerpts achieved by a common convolutional neural network (CNN) trained on two databases has been compared. On the one hand, 2,000 5 second-length ECG excerpts were initially selected from a freely available database. Half of the segments were extracted from noisy ECG recordings and the other half from high-quality signals. On the other hand, using a data augmentation approach based on time-scale modification, noise addition, and pitch shifting of the original noisy ECG experts, 1,000 additional low-quality intervals were generated. These surrogate noisy signals and the original high-quality ones formed the second dataset. The results for both cases were compared using a McNemar test and no statistically significant differences were noticed, thus suggesting that the synthesized noisy signals could be used for reliable training of CNN-based ECG quality indices.
Paper
Full text
ECG Quality Assessment via Deep Learning and Data Augmentation
Semantic Scholar · Medicine · 2021
Abstract
Quality assessment of ECG signals acquired with wearable devices is essential to avoid misdiagnosis of some cardiac disorders. For that purpose, novel deep learning algorithms have been recently proposed. However, training of these methods require large amount of data and public databases with annotated ECG samples are limited. Hence, the present work aims at validating the usefulness of a well-known data augmentation approach in this context of ECG quality assessment. Precisely, classification between high- and low-quality ECG excerpts achieved by a common convolutional neural network (CNN) trained on two databases has been compared. On the one hand, 2,000 5 second-length ECG excerpts were initially selected from a freely available database. Half of the segments were extracted from noisy ECG recordings and the other half from high-quality signals. On the other hand, using a data augmentation approach based on time-scale modification, noise addition, and pitch shifting of the original noisy ECG experts, 1,000 additional low-quality intervals were generated. These surrogate noisy signals and the original high-quality ones formed the second dataset. The results for both cases were compared using a McNemar test and no statistically significant differences were noticed, thus suggesting that the synthesized noisy signals could be used for reliable training of CNN-based ECG quality indices.