Generated 12-lead ECG signals from single lead I achieved a higher mean F1-score of 0.81 compared to 0.70 for real 12-lead ECG signals in classifying cardiovascular diseases.
Does a GAN-based 12-lead ECG generation model from single-lead ECG improve classification of cardiac abnormalities compared to real ECG signals?
Generating 12-lead ECG signals from a single lead using a GAN is feasible and may improve the diagnostic capability of single-lead wearable devices for various cardiac abnormalities.
Absolute Event Rate: 0.81% vs 0.7%
Nowadays, Electrocardiogram (ECG) signals can be measured using wearable devices, such as smart watches. Most wearable devices provide only a few details; however, they have the advantage of recording data in real time. In this study, 12-lead ECG signals were generated from lead I and their feasibility was tested to obtain more details. The 12-lead ECG signals were generated using a U-net-based generative adversarial network (GAN) that was trained on ECG data obtained from the Asan Medical Center. Subsequently, unseen PTB-XL PhysioNet data were used to produce real 12-lead ECG signals for classification. The generated and real 12-lead ECG signals were then compared using a ResNet classification model; and the normal, atrial fibrillation (A-fib), left bundle branch block (LBBB), right bundle branch block (RBBB), left ventricular hypertrophy (LVH), and right ventricular hypertrophy (RVH) were classified. The mean precision, recall, and f1-score for the real 12-lead ECG signals are 0.70, 0.72, and 0.70, and that for the generated 12-lead ECG signals are 0.82, 0.80, and 0.81, respectively. In our study, according to the result generated 12-lead ECG signals performed better than real 12-lead ECG.
Yoon et al. (Mon,) conducted a other in Cardiovascular diseases (Arrhythmia, Bundle Branch Blocks, Ventricular Hypertrophy). 12-lead ECG signals generated from lead I using a U-net based GAN vs. Real 12-lead ECG signals was evaluated on Mean F1-score for classification of 6 ECG classes (normal, A-fib, LBBB, RBBB, LVH, RVH). Generated 12-lead ECG signals from single lead I achieved a higher mean F1-score of 0.81 compared to 0.70 for real 12-lead ECG signals in classifying cardiovascular diseases.