Disentangled conditional generation of ECG signals with interpretable latent factors
Rong Xiao1, Zhijun Xiao2, Jianqing Li1
1The State Key Laboratory of Digital Medical Engineering, School of Instrument Science and Engineering, Southeast University, Nanjing, 210096, China.
Background And Objective:
Electrocardiogram modeling supports signal synthesis, analysis, and data augmentation. Existing generative approaches primarily focus on waveform fidelity and diversity, with limited interpretability of the underlying generation mechanisms, whereas disentangled representation learning improves interpretability through semantically structured latent factors but has been less explored from a generative perspective.
Methods:
We propose an electrocardiogram modeling framework that integrates disentangled representation learning with conditional generative modeling to support interpretable and controllable ECG synthesis. Disentangled latent representations are learned using a β-Total Correlation Variational Autoencoder, and a self-attention mechanism is incorporated to promote semantic alignment between latent dimensions and signal morphological characteristics. A conditional flow module is further introduced in the latent space to enable condition-aware prior reshaping, mitigating distributional collapse while preserving the learned disentangled structure.
Results:
Experimental results demonstrate that the proposed framework mitigates the generation collapse induced by strong disentanglement learning. While preserving a morphology-oriented latent structure, as indicated by a proxy-based mutual information gap score of 0.53, the conditional flow module improves generative performance. In an out-of-domain evaluation where only the flow is fine-tuned on the target dataset, the framework achieves a fidelity of 0.66 and diversity of 0.80, compared with 0.33 and 0.32 under standard prior sampling without flow adaptation.
Conclusions:
In summary, the proposed framework supports interpretable and controllable electrocardiogram generation through disentangled latent representations and condition-aware distribution alignment. The results demonstrate partial semantic consistency under out-of-domain evaluation and show that latent-space flow adaptation can mitigate generation collapse to some extent under strong disentanglement constraints.
Related Concept Videos
01:28Electrocardiogram Fundamentals
An electrocardiogram (ECG) is a diagnostic tool for identifying cardiac conditions such as arrhythmias, conduction abnormalities, and myocardial ischemia.
Definition
An electrocardiogram (ECG) visualizes the heart's electrical activity by tracing the electrical movement associated with each heartbeat on a graph or monitor. As the heart beats, an electrical wave passes through it, correlating with the cardiac cycle events.
Parts of an ECG
An ECG utilizes electrodes on the skin to...
01:29Electrocardiogram
Three major waveforms are present in a typical ECG recording: the P wave, the QRS complex, and the T...
01:25Correlation between ECG and Cardiac Cycle
A cardiac action potential originates in the SA node and spreads throughout the atria and the AV node in approximately 0.03 seconds. This results in the P wave in an ECG and triggers atrial contraction. The action potential is then briefly slowed at the AV node, allowing the atria to contract and fill the ventricles with blood before...