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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Zhuoyi, Sahoo, Nutan, Kumari, Anamika, Kumar, Girish, Cai, Kexuan, Cao, Shixing, Kang, Yue, Xia, Tian, Chatterjee, Somya, Hausman, Nicholas, Jay, Aidan, Rosenthal, Eric S., Srinivasan, Soundar, Hasan, Sadid, Fedorov, Alex, Vesal, Sulaiman
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916997757927424
author Huang, Zhuoyi
Sahoo, Nutan
Kumari, Anamika
Kumar, Girish
Cai, Kexuan
Cao, Shixing
Kang, Yue
Xia, Tian
Chatterjee, Somya
Hausman, Nicholas
Jay, Aidan
Rosenthal, Eric S.
Srinivasan, Soundar
Hasan, Sadid
Fedorov, Alex
Vesal, Sulaiman
author_facet Huang, Zhuoyi
Sahoo, Nutan
Kumari, Anamika
Kumar, Girish
Cai, Kexuan
Cao, Shixing
Kang, Yue
Xia, Tian
Chatterjee, Somya
Hausman, Nicholas
Jay, Aidan
Rosenthal, Eric S.
Srinivasan, Soundar
Hasan, Sadid
Fedorov, Alex
Vesal, Sulaiman
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_05492
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle High-Fidelity Synthetic ECG Generation via Mel-Spectrogram Informed Diffusion Training
Huang, Zhuoyi
Sahoo, Nutan
Kumari, Anamika
Kumar, Girish
Cai, Kexuan
Cao, Shixing
Kang, Yue
Xia, Tian
Chatterjee, Somya
Hausman, Nicholas
Jay, Aidan
Rosenthal, Eric S.
Srinivasan, Soundar
Hasan, Sadid
Fedorov, Alex
Vesal, Sulaiman
Machine Learning
Artificial Intelligence
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.
title High-Fidelity Synthetic ECG Generation via Mel-Spectrogram Informed Diffusion Training
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2510.05492