A Usable GAN-Based Tool for Synthetic ECG Generation in Cardiac Amyloidosis Research
By: Francesco Speziale , Ugo Lomoio , Fabiola Boccuto and more
Cardiac amyloidosis (CA) is a rare and underdiagnosed infiltrative cardiomyopathy, and available datasets for machine-learning models are typically small, imbalanced and heterogeneous. This paper presents a Generative Adversarial Network (GAN) and a graphical command-line interface for generating realistic synthetic electrocardiogram (ECG) beats to support early diagnosis and patient stratification in CA. The tool is designed for usability, allowing clinical researchers to train class-specific generators once and then interactively produce large volumes of labelled synthetic beats that preserve the distribution of minority classes.
Similar Papers
Synthetic Electrogram Generation with Variational Autoencoders for ECGI
Machine Learning (CS)
Creates fake heart signals to train AI.
High-Fidelity Synthetic ECG Generation via Mel-Spectrogram Informed Diffusion Training
Machine Learning (CS)
Makes fake heart signals for training doctors.
Conditional Electrocardiogram Generation Using Hierarchical Variational Autoencoders
Signal Processing
Creates fake heart signals to train doctors better.