dc.contributor.author | Thambawita, Vajira | |
dc.contributor.author | Isaksen, Jonas L. | |
dc.contributor.author | Hicks, Steven A. | |
dc.contributor.author | Ghouse, Jonas | |
dc.contributor.author | Ahlberg, Gustav | |
dc.contributor.author | Linneberg, Allan | |
dc.contributor.author | Grarup, Niels | |
dc.contributor.author | Ellervik, Christina | |
dc.contributor.author | Olesen, Morten Salling | |
dc.contributor.author | Hansen, Torben | |
dc.contributor.author | Graff, Claus | |
dc.contributor.author | Holstein-Rathlou, Niels-Henrik | |
dc.contributor.author | Strümke, Inga | |
dc.contributor.author | Hammer, Hugo L. | |
dc.contributor.author | Maleckar, Mary M. | |
dc.contributor.author | Halvorsen, Pål | |
dc.contributor.author | Riegler, Michael A. | |
dc.contributor.author | Kanters, Jørgen K. | |
dc.date.accessioned | 2022-02-15T13:29:07Z | |
dc.date.available | 2022-02-15T13:29:07Z | |
dc.date.issued | 2021-11-09 | |
dc.description.abstract | 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. | en_US |
dc.identifier.citation | Thambawita, Isaksen, Hicks, Ghouse, Ahlberg, Linneberg, Grarup, Ellervik, Olesen, Hansen, Graff, Holstein-Rathlou, Strümke, Hammer, Maleckar, Halvorsen, Riegler, Kanters. DeepFake electrocardiograms using generative adversarial networks are the beginning of the end for privacy issues in medicine. Scientific Reports. 2021;11(1) | en_US |
dc.identifier.cristinID | FRIDAID 1964150 | |
dc.identifier.doi | 10.1038/s41598-021-01295-2 | |
dc.identifier.issn | 2045-2322 | |
dc.identifier.uri | https://hdl.handle.net/10037/24057 | |
dc.language.iso | eng | en_US |
dc.publisher | Nature | en_US |
dc.relation.journal | Scientific Reports | |
dc.rights.accessRights | openAccess | en_US |
dc.rights.holder | Copyright 2021 The Author(s) | en_US |
dc.title | DeepFake electrocardiograms using generative adversarial networks are the beginning of the end for privacy issues in medicine | en_US |
dc.type.version | publishedVersion | en_US |
dc.type | Journal article | en_US |
dc.type | Tidsskriftartikkel | en_US |
dc.type | Peer reviewed | en_US |