# Synthetic ECG Signal Generation Using Generative Neural Networks

arXiv: https://arxiv.org/abs/2112.03268 · HTML: https://mlsanity.com/paper/2112.03268/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 27 references that are in the map.
- First posted on arXiv 5 Dec 2021.

## Builds on (most cited first, 9 of 9)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Generative Adversarial Networks: An Overview](https://mlsanity.com/paper/1710.07035/) (2017)
- [Tutorial on Variational Autoencoders](https://mlsanity.com/paper/1606.05908/) (2016)
- [Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs](https://mlsanity.com/paper/1706.02633/) (2017)
- [NIPS 2016 Tutorial: Generative Adversarial Networks](https://mlsanity.com/paper/1701.00160/) (2016)
- [Synthesis of Realistic ECG using Generative Adversarial Networks](https://mlsanity.com/paper/1909.09150/) (2019)
- [Opportunities and Challenges of Deep Learning Methods for Electrocardiogram Data: A Systematic Review](https://mlsanity.com/paper/2001.01550/) (2019)
- [Synthesis of standard 12-lead electrocardiograms using two dimensional generative adversarial network](https://mlsanity.com/paper/2106.03701/) (2021)
- [Fr'echet Distance for Curves, Revisited](https://mlsanity.com/paper/1504.07685/) (2015)

## Built on by (most cited first, 11 of 11)

- [Synthetic ECG Signal Generation using Probabilistic Diffusion Models](https://mlsanity.com/paper/2303.02475/) (2023)
- [Text-to-ECG: 12-Lead Electrocardiogram Synthesis conditioned on Clinical Text Reports](https://mlsanity.com/paper/2303.09395/) (2023)
- [Arrhythmia Classification using CGAN-augmented ECG Signals](https://mlsanity.com/paper/2202.00569/) (2022)
- [Synthetic Data Generation by Supervised Neural Gas Network for Physiological Emotion Recognition Data](https://mlsanity.com/paper/2501.16353/) (2025)
- [CLEP-GAN: An Innovative Approach to Subject-Independent ECG Reconstruction from PPG Signals](https://mlsanity.com/paper/2502.17536/) (2025)
- [Complementarity-Preserving Generative Theory for Multimodal ECG Synthesis: A Quantum-Inspired Approach](https://mlsanity.com/paper/2603.26695/) (2026)
- [ECG-WM: A Physiology-Informed ECG World Model for Clinical Intervention Simulation](https://mlsanity.com/paper/2605.17580/) (2026)
- [Accurate Detection of Paroxysmal Atrial Fibrillation with Certified-GAN and Neural Architecture Search](https://mlsanity.com/paper/2301.10173/) (2023)
- [Flexible framework for generating synthetic electrocardiograms and photoplethysmograms](https://mlsanity.com/paper/2408.16291/) (2024)
- [Inductive transfer learning from regression to classification in ECG analysis](https://mlsanity.com/paper/2508.11656/) (2025)
- [A Usable GAN-Based Tool for Synthetic ECG Generation in Cardiac Amyloidosis Research](https://mlsanity.com/paper/2601.08260/) (2026)

## Abstract (arXiv)

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), Fr'echet, 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.