Synthetic ECG signal generation using generative neural networks.
Electrocardiogram (ECG) datasets tend to be highly imbalanced due to the scarcity of abnormal cases. Additionally, the use of real patients' ECGs is highly regulated due to privacy issues. Therefore, there is always a need for more ECG data, especially for the training of automatic diagnosis ma...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0271270 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849769990652166144 |
|---|---|
| author | Edmond Adib Fatemeh Afghah John J Prevost |
| author_facet | Edmond Adib Fatemeh Afghah John J Prevost |
| author_sort | Edmond Adib |
| collection | DOAJ |
| description | Electrocardiogram (ECG) datasets tend to be highly imbalanced due to the scarcity of abnormal cases. Additionally, the use of real patients' ECGs is highly regulated due to privacy issues. Therefore, there is always a need for more ECG data, especially for the training of automatic diagnosis machine learning models, which perform better when trained on a balanced dataset. We studied the synthetic ECG generation capability of 5 different models from the generative adversarial network (GAN) family and compared their performances, the focus being only on Normal cardiac cycles. Dynamic Time Warping (DTW), Fréchet, and Euclidean distance functions were employed to quantitatively measure performance. Five different methods for evaluating generated beats were proposed and applied. We also proposed 3 new concepts (threshold, accepted beat and productivity rate) and employed them along with the aforementioned methods as a systematic way for comparison between models. The results show that all the tested models can, to an extent, successfully mass-generate acceptable heartbeats with high similarity in morphological features, and potentially all of them can be used to augment imbalanced datasets. However, visual inspections of generated beats favors BiLSTM-DC GAN and WGAN, as they produce statistically more acceptable beats. Also, with regards to productivity rate, the Classic GAN is superior with a 72% productivity rate. We also designed a simple experiment with the state-of-the-art classifier (ECGResNet34) to show empirically that the augmentation of the imbalanced dataset by synthetic ECG signals could improve the performance of classification significantly. |
| format | Article |
| id | doaj-art-bec08ac954a14fddb6930ce9edd8a748 |
| institution | DOAJ |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-bec08ac954a14fddb6930ce9edd8a7482025-08-20T03:03:11ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01203e027127010.1371/journal.pone.0271270Synthetic ECG signal generation using generative neural networks.Edmond AdibFatemeh AfghahJohn J PrevostElectrocardiogram (ECG) datasets tend to be highly imbalanced due to the scarcity of abnormal cases. Additionally, the use of real patients' ECGs is highly regulated due to privacy issues. Therefore, there is always a need for more ECG data, especially for the training of automatic diagnosis machine learning models, which perform better when trained on a balanced dataset. We studied the synthetic ECG generation capability of 5 different models from the generative adversarial network (GAN) family and compared their performances, the focus being only on Normal cardiac cycles. Dynamic Time Warping (DTW), Fréchet, and Euclidean distance functions were employed to quantitatively measure performance. Five different methods for evaluating generated beats were proposed and applied. We also proposed 3 new concepts (threshold, accepted beat and productivity rate) and employed them along with the aforementioned methods as a systematic way for comparison between models. The results show that all the tested models can, to an extent, successfully mass-generate acceptable heartbeats with high similarity in morphological features, and potentially all of them can be used to augment imbalanced datasets. However, visual inspections of generated beats favors BiLSTM-DC GAN and WGAN, as they produce statistically more acceptable beats. Also, with regards to productivity rate, the Classic GAN is superior with a 72% productivity rate. We also designed a simple experiment with the state-of-the-art classifier (ECGResNet34) to show empirically that the augmentation of the imbalanced dataset by synthetic ECG signals could improve the performance of classification significantly.https://doi.org/10.1371/journal.pone.0271270 |
| spellingShingle | Edmond Adib Fatemeh Afghah John J Prevost Synthetic ECG signal generation using generative neural networks. PLoS ONE |
| title | Synthetic ECG signal generation using generative neural networks. |
| title_full | Synthetic ECG signal generation using generative neural networks. |
| title_fullStr | Synthetic ECG signal generation using generative neural networks. |
| title_full_unstemmed | Synthetic ECG signal generation using generative neural networks. |
| title_short | Synthetic ECG signal generation using generative neural networks. |
| title_sort | synthetic ecg signal generation using generative neural networks |
| url | https://doi.org/10.1371/journal.pone.0271270 |
| work_keys_str_mv | AT edmondadib syntheticecgsignalgenerationusinggenerativeneuralnetworks AT fatemehafghah syntheticecgsignalgenerationusinggenerativeneuralnetworks AT johnjprevost syntheticecgsignalgenerationusinggenerativeneuralnetworks |