Inclusion of a Dynamic Time Warping penalisation coefficient in the loss function enabled the multivariate GAN to outperform other generative models by 4.9% in generating representative ECG data.
Does a multivariate GAN with novel loss functions improve the generation of high-quality, privacy-preserving synthetic multichannel ECGs compared to other generative models?
A multivariate GAN utilizing a Dynamic Time Warping penalisation coefficient can generate high-quality, privacy-preserving synthetic multichannel ECG data, outperforming alternative models.
Access to medical data is highly regulated due to its sensitive nature, which can constrain communities’ ability to utilise these data for research or clinical purposes. Common de-identification techniques to enable the sharing of data may not provide adequate privacy in every circumstance. We investigate the ability of Generative Adversarial Networks (GANs) to generate synthetic, and more significantly, multichannel electrocardiogram signals that are representative of waveforms observed in patients to address these privacy concerns. Successful generation of high-quality synthetic time series data has the potential to act as an effective substitute for actual patient data. For the first time, we demonstrate a range of novel loss functions using our multivariate GAN architecture and analyse their effect on data quality and privacy. We also present the application of multivariate dynamic time warping as a means of evaluating generated time series. Quantitative evidence demonstrates that the inclusion of a penalisation coefficient (Dynamic Time Warping) in the loss function enables our GAN to outperform the other generative models and loss functions explored by 4.9% according to our metrics. This allows for the generation of data that is more representative of the training set and diverse across generated samples, all whilst ensuring sufficient privacy.
Brophy et al. (Fri,) conducted a other in Electrocardiogram signals. Multivariate Generative Adversarial Networks (GANs) vs. Other generative models was evaluated on Data quality and privacy evaluated by multivariate dynamic time warping. Inclusion of a Dynamic Time Warping penalisation coefficient in the loss function enabled the multivariate GAN to outperform other generative models by 4.9% in generating representative ECG data.