Generating Realistic Multi-Beat ECG Signals

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pöhl, Paul, Schlegel, Viktor, Li, Hao, Bharath, Anil
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910966471458816
author Pöhl, Paul
Schlegel, Viktor
Li, Hao
Bharath, Anil
author_facet Pöhl, Paul
Schlegel, Viktor
Li, Hao
Bharath, Anil
contents Generating synthetic ECG data has numerous applications in healthcare, from educational purposes to simulating scenarios and forecasting trends. While recent diffusion models excel at generating short ECG segments, they struggle with longer sequences needed for many clinical applications. This paper proposes a novel three-layer synthesis framework for generating realistic long-form ECG signals. We first generate high-fidelity single beats using a diffusion model, then synthesize inter-beat features preserving critical temporal dependencies, and finally assemble beats into coherent long sequences using feature-guided matching. Our comprehensive evaluation demonstrates that the resulting synthetic ECGs maintain both beat-level morphological fidelity and clinically relevant inter-beat relationships. In arrhythmia classification tasks, our long-form synthetic ECGs significantly outperform end-to-end long-form ECG generation using the diffusion model, highlighting their potential for increasing utility for downstream applications. The approach enables generation of unprecedented multi-minute ECG sequences while preserving essential diagnostic characteristics.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18189
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generating Realistic Multi-Beat ECG Signals
Pöhl, Paul
Schlegel, Viktor
Li, Hao
Bharath, Anil
Signal Processing
Machine Learning
Generating synthetic ECG data has numerous applications in healthcare, from educational purposes to simulating scenarios and forecasting trends. While recent diffusion models excel at generating short ECG segments, they struggle with longer sequences needed for many clinical applications. This paper proposes a novel three-layer synthesis framework for generating realistic long-form ECG signals. We first generate high-fidelity single beats using a diffusion model, then synthesize inter-beat features preserving critical temporal dependencies, and finally assemble beats into coherent long sequences using feature-guided matching. Our comprehensive evaluation demonstrates that the resulting synthetic ECGs maintain both beat-level morphological fidelity and clinically relevant inter-beat relationships. In arrhythmia classification tasks, our long-form synthetic ECGs significantly outperform end-to-end long-form ECG generation using the diffusion model, highlighting their potential for increasing utility for downstream applications. The approach enables generation of unprecedented multi-minute ECG sequences while preserving essential diagnostic characteristics.
title Generating Realistic Multi-Beat ECG Signals
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2505.18189