Deep Generative Models: The winning key for large and easily accessible ECG datasets?

Giuliana Monachino, Beatrice Zanchi, Luigi Fiorillo, Giulio Conte, Angelo Auricchio, Athina Tzovara, Francesca Dalia Faraci

Abstract: Highlights•High-quality and large ECG datasets are a high priority to foster cardiac research.•Several barriers related to dataset building and sharing have to be overcome.•ECGs generation through DGMs can address data scarcity and class unbalance issues.•DGMs can foster open science by generating anonymized copies of datasets for sharing.•Standardized quality and privacy assessment measures are urgently needed.