A Usable GAN-Based Tool for Synthetic ECG Generation in Cardiac Amyloidosis Research

TL;DR

This paper introduces a user-friendly GAN-based tool that generates realistic synthetic ECG data to aid early diagnosis and research in cardiac amyloidosis, addressing data scarcity and class imbalance issues.

Contribution

It presents a novel GAN model with a graphical interface for generating labeled ECG beats, tailored for clinical research in cardiac amyloidosis.

Findings

Generated ECG beats preserve class distribution

Tool enables large-scale synthetic data production

Supports early diagnosis and patient stratification

Abstract

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.