TY - JOUR

T1 - DeepFake electrocardiograms using generative adversarial networks are the beginning of the end for privacy issues in medicine

AU - Thambawita, Vajira

AU - Isaksen, Jonas L

AU - Hicks, Steven A

AU - Ghouse, Jonas

AU - Ahlberg, Gustav

AU - Linneberg, Allan

AU - Grarup, Niels

AU - Ellervik, Christina

AU - Olesen, Morten Salling

AU - Hansen, Torben

AU - Graff, Claus

AU - Holstein-Rathlou, Niels-Henrik

AU - Strümke, Inga

AU - Hammer, Hugo L.

AU - Maleckar, Mary M.

AU - Halvorsen, Pål

AU - Riegler, Michael A

AU - Kanters, Jørgen K

N1 - © 2021. The Author(s).

PY - 2021

Y1 - 2021

N2 - Recent global developments underscore the prominent role big data have in modern medical science. But privacy issues constitute a prevalent problem for collecting and sharing data between researchers. However, synthetic data generated to represent real data carrying similar information and distribution may alleviate the privacy issue. In this study, we present generative adversarial networks (GANs) capable of generating realistic synthetic DeepFake 10-s 12-lead electrocardiograms (ECGs). We have developed and compared two methods, named WaveGAN* and Pulse2Pulse. We trained the GANs with 7,233 real normal ECGs 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. Although these synthetic ECGs mimic the dataset used for creation, the ECGs are not linked to any individuals and may thus 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 generative adversarial neural networks on normal ECGs from two population studies, thereby addressing the relevant privacy issues in medical datasets.

AB - Recent global developments underscore the prominent role big data have in modern medical science. But privacy issues constitute a prevalent problem for collecting and sharing data between researchers. However, synthetic data generated to represent real data carrying similar information and distribution may alleviate the privacy issue. In this study, we present generative adversarial networks (GANs) capable of generating realistic synthetic DeepFake 10-s 12-lead electrocardiograms (ECGs). We have developed and compared two methods, named WaveGAN* and Pulse2Pulse. We trained the GANs with 7,233 real normal ECGs 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. Although these synthetic ECGs mimic the dataset used for creation, the ECGs are not linked to any individuals and may thus 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 generative adversarial neural networks on normal ECGs from two population studies, thereby addressing the relevant privacy issues in medical datasets.

U2 - 10.1038/s41598-021-01295-2

DO - 10.1038/s41598-021-01295-2

M3 - Journal article

C2 - 34753975

VL - 11

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 21896

ER -