Show simple item record

dc.contributor.authorThambawita, Vajira
dc.contributor.authorIsaksen, Jonas L.
dc.contributor.authorHicks, Steven A.
dc.contributor.authorGhouse, Jonas
dc.contributor.authorAhlberg, Gustav
dc.contributor.authorLinneberg, Allan
dc.contributor.authorGrarup, Niels
dc.contributor.authorEllervik, Christina
dc.contributor.authorOlesen, Morten Salling
dc.contributor.authorHansen, Torben
dc.contributor.authorGraff, Claus
dc.contributor.authorHolstein-Rathlou, Niels-Henrik
dc.contributor.authorStrümke, Inga
dc.contributor.authorHammer, Hugo L.
dc.contributor.authorMaleckar, Mary M.
dc.contributor.authorHalvorsen, Pål
dc.contributor.authorRiegler, Michael A.
dc.contributor.authorKanters, Jørgen K.
dc.date.accessioned2022-02-15T13:29:07Z
dc.date.available2022-02-15T13:29:07Z
dc.date.issued2021-11-09
dc.description.abstractRecent 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.citationThambawita, 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.cristinIDFRIDAID 1964150
dc.identifier.doi10.1038/s41598-021-01295-2
dc.identifier.issn2045-2322
dc.identifier.urihttps://hdl.handle.net/10037/24057
dc.language.isoengen_US
dc.publisherNatureen_US
dc.relation.journalScientific Reports
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2021 The Author(s)en_US
dc.titleDeepFake electrocardiograms using generative adversarial networks are the beginning of the end for privacy issues in medicineen_US
dc.type.versionpublishedVersionen_US
dc.typeJournal articleen_US
dc.typeTidsskriftartikkelen_US
dc.typePeer revieweden_US


File(s) in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record