Key result
Novel adversarial autoencoder framework generates continuous, realistic ECG and PPG sequences of ~6 s.
Why the study?
Synthesising complex biomedical signals is difficult due to intricate morphologies and subject-specific constraints, and existing generative adversarial network methods have largely been limited to short-duration outputs or single-pulse events.
Does a generative framework combining autoencoders and adversarial learning-based disentanglement enable multi-step, subject-specific ECG and PPG signal generation?
Does a generative framework combining autoencoders and adversarial learning-based disentanglement enable multi-step, subject-specific ECG and PPG signal generation?
This computational study demonstrates a proof-of-concept generative framework combining autoencoders and adversarial disentanglement to synthesize continuous, subject-specific ECG and PPG signals up to 6-8 seconds.
Artificial data synthesis is a valuable tool for overcoming the challenges of collecting large datasets, particularly in the medical domain where privacy concerns are significant. However, synthesising complex biomedical signals remains difficult due to their intricate morphologies and subject-specific constraints. While GANs have shown promise, existing methods have largely been limited to short-duration outputs or morphology-centered single-pulse events. In this study, we propose a generative framework combining autoencoders and adversarial learning-based disentanglement to enable multi-step, subject-specific biosignal generation with transferable properties, evaluated under a within-recording, segment-level protocol. We evaluate our model on two modalities: Electrocardiogram (ECG; 17 subjects) and Photoplethysmogram (PPG; 7 subjects). The model generates continuous ECG sequences of approximately 6 s (two forward recurrent steps beyond the seed segment), with a subset of subjects retaining recognisable waveform structure up to approximately 8 s. It shows similar performance for PPG, suggesting adaptability across periodic biosignal modalities. With recurrent subject-conditional generation demonstrated across both ECG and PPG, and exploratory style-transfer capabilities demonstrated for selected ECG subjects, the proposed framework serves as a proof of concept for multi-step sequential biosignal generation.
No takes yet. Share an insight, caveat, or question.
Dissanayake et al. (2026) studied Periodic biosignal synthesis (ECG and PPG) (n=24). Generative framework combining autoencoders and adversarial learning-based disentanglement was evaluated on Continuous multi-step ECG and PPG sequence generation duration with recognisable waveform structure. The autoencoder and adversarial disentanglement framework generated continuous ECG and PPG sequences of ~6 s (up to ~8 s in a subset) across 17 ECG and 7 PPG subjects.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: