Adib Edmond, Afghah Fatemeh, Prevost John J
Electrical and Computer Engineering Department, University of Texas at San Antonio (UTSA), San Antonio, Texas, United States of America.
Department of Electrical and Computer Engineering, Clemson University, Clemson, South Carolina, United States of America.
PLoS One. 2025 Mar 25;20(3):e0271270. doi: 10.1371/journal.pone.0271270. eCollection 2025.
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.
由于异常病例稀缺，心电图（ECG）数据集往往高度不平衡。此外，出于隐私问题，对真实患者心电图的使用有严格规定。因此，始终需要更多的心电图数据，特别是用于训练自动诊断机器学习模型，这些模型在平衡数据集上训练时表现更好。我们研究了生成对抗网络（GAN）家族中5种不同模型的合成心电图生成能力，并比较了它们的性能，重点仅关注正常心动周期。采用动态时间规整（DTW）、弗雷歇（Fréchet）和欧几里得距离函数来定量衡量性能。提出并应用了五种评估生成搏动的不同方法。我们还提出了3个新概念（阈值、可接受搏动和生产率），并将它们与上述方法一起用作模型间比较的系统方法。结果表明，所有测试模型在一定程度上都能成功大量生成形态特征高度相似的可接受心跳，并且它们都有可能用于扩充不平衡数据集。然而，对生成搏动的视觉检查表明，双向长短期记忆深度卷积生成对抗网络（BiLSTM-DC GAN）和 Wasserstein生成对抗网络（WGAN）更受青睐，因为它们生成的可接受搏动在统计上更多。此外，就生产率而言，经典生成对抗网络（Classic GAN）表现更优，生产率为72%。我们还使用最先进的分类器（ECGResNet34）设计了一个简单实验，以实证表明通过合成心电图信号扩充不平衡数据集可以显著提高分类性能。
