# FlowECG: Using Flow Matching to Create a More Efficient ECG Signal Generator

arXiv: https://arxiv.org/abs/2509.10491 · HTML: https://mlsanity.com/paper/2509.10491/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 31 Aug 2025.

## Builds on (most cited first, 10 of 10)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [Adversarial Audio Synthesis](https://mlsanity.com/paper/1802.04208/) (2018)
- [Calibrated Reliable Regression using Maximum Mean Discrepancy](https://mlsanity.com/paper/2006.10255/) (2020)
- [Diffusion-based Conditional ECG Generation with Structured State Space Models](https://mlsanity.com/paper/2301.08227/) (2023)
- [SimGANs: Simulator-Based Generative Adversarial Networks for ECG Synthesis to Improve Deep ECG Classification](https://mlsanity.com/paper/2006.15353/) (2020)
- [PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation](https://mlsanity.com/paper/2408.07547/) (2024)
- [DiffECG: A Versatile Probabilistic Diffusion Model for ECG Signals Synthesis](https://mlsanity.com/paper/2306.01875/) (2023)
- [BioDiffusion: A Versatile Diffusion Model for Biomedical Signal Synthesis](https://mlsanity.com/paper/2401.10282/) (2024)
- [Deep generative models as the probability transformation functions](https://mlsanity.com/paper/2506.17171/) (2025)

## Built on by (most cited first, 4 of 4)

- [Simulator and Experience Enhanced Diffusion Model for Comprehensive ECG Generation](https://mlsanity.com/paper/2511.09895/) (2025)
- [Signal or Noise? Understanding Generative Models for Real-World Sensor Time Series](https://mlsanity.com/paper/2607.04245/) (2026)
- [Cylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal Transformation](https://mlsanity.com/paper/2610.08510/) (2026)
- [ECG-RSI: Recursive Self-Improvement through Targeted Electrocardiogram Waveform Evolution](https://mlsanity.com/paper/2610.17718/) (2026)

## Abstract (arXiv)

Synthetic electrocardiogram generation serves medical AI applications requiring privacy-preserving data sharing and training dataset augmentation. Current diffusion-based methods achieve high generation quality but require hundreds of neural network evaluations during sampling, creating computational bottlenecks for clinical deployment. We propose FlowECG, a flow matching approach that adapts the SSSD-ECG architecture by replacing the iterative diffusion process with continuous flow dynamics. Flow matching learns direct transport paths from noise to data distributions through ordinary differential equation solving. We evaluate our method on the PTB-XL dataset using Dynamic Time Warping, Wasserstein distance, Maximum Mean Discrepancy, and spectral similarity metrics. FlowECG matches SSSD-ECG performance at 200 neural function evaluations, outperforming the baseline on three metrics. The key finding shows that FlowECG maintains generation quality with substantially fewer sampling steps, achieving comparable results with 10-25 evaluations compared to 200 for diffusion methods. This efficiency improvement reduces computational requirements by an order of magnitude while preserving physiologically realistic 12-lead ECG characteristics. The approach enables practical deployment in resource-limited clinical settings where real-time generation or large-scale synthetic data creation is needed.