---
license: cc-by-4.0
language:
- en
tags:
- generation
- ECG generation
pretty_name: DeepFake-ECG
size_categories:
- 10B<n<100B
---
## DeepFake electrocardiograms: the beginning of the end for privacy issues in medicine
[Paper](https://www.nature.com/articles/s41598-021-01295-2)
[GitHub](https://github.com/vlbthambawita/deepfake-ecg)
[Original-data-source](https://osf.io/6hved/)
[PyPI](https://pypi.org/project/deepfake-ecg/)
## How to download
### Option 1
``` python
from datasets import load_dataset
dataset = load_dataset("deepsynthbody/deepfake_ecg")
```
### Option 2
```bash
git lfs install
git clone https://huggingface.co/datasets/deepsynthbody/deepfake_ecg
# if you want to clone without large files – just their pointers
# prepend your git clone with the following env var:
GIT_LFS_SKIP_SMUDGE=1
```
## Demo of using the generator used to generate this dataset
https://huggingface.co/spaces/deepsynthbody/deepfake-ecg-generator
### Content
Big data is needed to implement personalized medicine, but privacy issues are a prevalent problem for collecting data and sharing them between researchers. A solution is synthetic data generated to represent real dataset carrying similar information. Here, we present generative adversarial networks (GANs) capable of generating realistic synthetic DeepFake 12-lead 10-sec electrocardiograms (ECGs). We have developed and compare two methods, namely WaveGAN* and Pulse2Pulse GAN. We trained the GANs with 7,233 real normal ECG to produce 121,977 DeepFake normal ECGs. By verifying the ECGs using a commercial ECG interpretation program (MUSE 12SL, GE Healthcare), we demonstrate that the Pulse2Pulse GAN was superior to the WaveGAN to produce realistic ECGs. ECG intervals and amplitudes were similar between the DeepFake and real ECGs. These synthetic ECGs are fully anonymous and cannot be referred to any individual, hence they may be used freely. The synthetic dataset will be available as open access for researchers at OSF.io and the DeepFake generator available at the Python Package Index (PyPI) for generating synthetic ECGs. In conclusion, we were able to generate realistic synthetic ECGs using adversarial neural networks on normal ECGs from two population studies, i.e., there by solving the relevant privacy issues in medical datasets.
### Citation (cite this paper to use this dataset in your research)
```latex
@article{thambawita2021deepfake,
title={DeepFake electrocardiograms using generative adversarial networks are the beginning of the end for privacy issues in medicine},
author={Thambawita, Vajira and Isaksen, Jonas L and Hicks, Steven A and Ghouse, Jonas and Ahlberg, Gustav and Linneberg, Allan and Grarup, Niels and Ellervik, Christina and Olesen, Morten Salling and Hansen, Torben and others},
journal={Scientific reports},
volume={11},
number={1},
pages={1--8},
year={2021},
publisher={Nature Publishing Group}
}
```
license: CC BY 4.0
language:
- 英语(en)
tags:
- 生成
- 心电图生成(ECG generation)
pretty_name: DeepFake-ECG
size_categories:
- 100亿 < n < 1000亿
## 深度伪造心电图:破解医学隐私困境的开端
[论文](https://www.nature.com/articles/s41598-021-01295-2)
[GitHub仓库](https://github.com/vlbthambawita/deepfake-ecg)
[原始数据源](https://osf.io/6hved/)
[PyPI(Python Package Index)](https://pypi.org/project/deepfake-ecg/)
## 下载方法
### 选项1
python
from datasets import load_dataset
dataset = load_dataset("deepsynthbody/deepfake_ecg")
### 选项2
bash
git lfs install
git clone https://huggingface.co/datasets/deepsynthbody/deepfake_ecg
# 若仅需克隆文件指针而非完整大文件
# 请在git clone命令前添加如下环境变量:
GIT_LFS_SKIP_SMUDGE=1
## 本数据集生成器的在线演示
https://huggingface.co/spaces/deepsynthbody/deepfake-ecg-generator
### 研究内容
个性化医疗的落地离不开大数据支撑,但在研究人员之间收集与共享数据时,隐私问题始终是普遍存在的难题。解决方案之一便是生成能够承载真实数据集相似信息的合成数据。本研究提出了可生成逼真合成深度伪造12导联10秒心电图(Electrocardiogram,以下简称ECG)的生成对抗网络(Generative Adversarial Networks,以下简称GAN)。我们开发并对比了两种方法,分别为WaveGAN*与Pulse2Pulse GAN。我们使用7233份真实正常心电图训练上述GAN,生成了121977份深度伪造正常心电图。通过商用心电图解读程序(MUSE 12SL,通用电气医疗集团(GE Healthcare))对生成的心电图进行验证,结果显示Pulse2Pulse GAN生成的心电图真实性优于WaveGAN。深度伪造心电图与真实心电图的间期与振幅均无显著差异。此类合成心电图完全匿名,无法关联至任何个体,因此可自由使用。本合成数据集将通过OSF.io向研究人员开放获取,而深度伪造心电图生成工具则可在Python软件包索引(PyPI)获取以用于合成心电图生成。综上,我们基于两项人群研究的正常心电图,通过对抗神经网络成功生成了具备真实性的合成心电图,由此解决了医学数据集面临的相关隐私困境。
### 引用规范(若在研究中使用本数据集,请引用以下论文)
latex
@article{thambawita2021deepfake,
title={DeepFake electrocardiograms using generative adversarial networks are the beginning of the end for privacy issues in medicine},
author={Thambawita, Vajira and Isaksen, Jonas L and Hicks, Steven A and Ghouse, Jonas and Ahlberg, Gustav and Linneberg, Allan and Grarup, Niels and Ellervik, Christina and Olesen, Morten Salling and Hansen, Torben and others},
journal={Scientific reports},
volume={11},
number={1},
pages={1--8},
year={2021},
publisher={Nature Publishing Group}
}