High-Fidelity Synthetic ECG Generation via Mel-Spectrogram Informed Diffusion Training Article Swipe

MAKE IMPACT

Zhuoyi Huang , Narayan Sahoo , Anamika Kumari , Girish Kumar , Kai Cai , Shixing Cao , Yue Kang , Tian Xia , S. Chatterjee , Nicholas Hausman , Antoine Jay , Eric S. Rosenthal , Soundar Srinivasan , Alex Fedorov , Sadid A. Hasan , Sulaiman Vesal · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2510.05492

The development of machine learning for cardiac care is severely hampered by privacy restrictions on sharing real patient electrocardiogram (ECG) data. Although generative AI offers a promising solution, the real-world use of existing model-synthesized ECGs is limited by persistent gaps in trustworthiness and clinical utility. In this work, we address two major shortcomings of current generative ECG methods: insufficient morphological fidelity and the inability to generate personalized, patient-specific physiological signals. To address these gaps, we build on a conditional diffusion-based Structured State Space Model (SSSD-ECG) with two principled innovations: (1) MIDT-ECG (Mel-Spectrogram Informed Diffusion Training), a novel training paradigm with time-frequency domain supervision to enforce physiological structural realism, and (2) multi-modal demographic conditioning to enable patient-specific synthesis. We comprehensively evaluate our approach on the PTB-XL dataset, assessing the synthesized ECG signals on fidelity, clinical coherence, privacy preservation, and downstream task utility. MIDT-ECG achieves substantial gains: it improves morphological coherence, preserves strong privacy guarantees with all metrics evaluated exceeding the baseline by 4-8%, and notably reduces the interlead correlation error by an average of 74%, while demographic conditioning enhances signal-to-noise ratio and personalization. In critical low-data regimes, a classifier trained on datasets supplemented with our synthetic ECGs achieves performance comparable to a classifier trained solely on real data. Together, we demonstrate that ECG synthesizers, trained with the proposed time-frequency structural regularization scheme, can serve as personalized, high-fidelity, privacy-preserving surrogates when real data are scarce, advancing the responsible use of generative AI in healthcare.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2510.05492

PDF

https://arxiv.org/pdf/2510.05492

OA Status

green

OpenAlex ID

https://openalex.org/W4414977074

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4414977074

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2510.05492

Digital Object Identifier

Title

High-Fidelity Synthetic ECG Generation via Mel-Spectrogram Informed Diffusion Training

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-10-07

Full publication date if available

Authors

Zhuoyi Huang, Narayan Sahoo, Anamika Kumari, Girish Kumar, Kai Cai, Shixing Cao, Yue Kang, Tian Xia, S. Chatterjee, Nicholas Hausman, Antoine Jay, Eric S. Rosenthal, Soundar Srinivasan, Alex Fedorov, Sadid A. Hasan, Sulaiman Vesal

List of authors in order

Landing page

https://arxiv.org/abs/2510.05492

Publisher landing page

PDF URL

https://arxiv.org/pdf/2510.05492

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2510.05492

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload