dorsal/arxiv
View SchemaA Usable GAN-Based Tool for Synthetic ECG Generation in Cardiac Amyloidosis Research
| Authors | Francesco Speziale, Ugo Lomoio, Fabiola Boccuto, Pierangelo Veltri, Pietro Hiram Guzzi |
|---|---|
| Categories | |
| ArXiv ID | 2601.08260vv1 |
| URL | https://arxiv.org/abs/2601.08260 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
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.
{
"annotation_id": "22cde494-b8a4-4c58-bbfa-6f165fa44095",
"date_created": "2026-02-17T05:53:15.439000Z",
"date_modified": "2026-02-17T05:53:15.439000Z",
"file_hash": "b2f943a76a144e75b3f2d37c86b5343022f1e53336f037fe23561721ae729233",
"private": false,
"record": {
"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.",
"arxiv_id": "2601.08260",
"authors": [
"Francesco Speziale",
"Ugo Lomoio",
"Fabiola Boccuto",
"Pierangelo Veltri",
"Pietro Hiram Guzzi"
],
"categories": [
"cs.LG"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "A Usable GAN-Based Tool for Synthetic ECG Generation in Cardiac Amyloidosis Research",
"url": "https://arxiv.org/abs/2601.08260",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "1dabd7d3-8348-4825-bf3e-2cbbe05e33f3",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}