PG-LRF: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation

2026-05-09

AI Summary

Existing PPG-to-ECG generation methods struggle to simultaneously achieve high signal fidelity and physiological plausibility due to the absence of explicit modeling of electro-hemodynamic mechanisms. This work proposes PG-LRF, a novel framework that, for the first time, integrates an electro-hemodynamic simulator into a latent rectified flow generation process. Specifically, a physiology-aware autoencoder constructs a shared latent representation aligned with the cardiac cycle, and bidirectional physiological constraints—encompassing both forward activation and pulse transmission phases—are incorporated into the PPG-conditioned generative flow. Evaluated on the large-scale MC-MED dataset, PG-LRF significantly improves ECG generation quality while enhancing downstream cardiovascular disease classification performance, ensuring that synthesized signals are morphologically and temporally consistent with real physiological dynamics.

Abstract

Electrocardiography (ECG) is the clinical standard for cardiac assessment but requires dedicated hardware that does not scale to daily-life monitoring. Photoplethysmography (PPG) is ubiquitous in wearables but lacks ECG-specific diagnostic morphology and is corrupted by motion and sensor noise. PPG-to-ECG generation aims to bridge this gap by recovering electrical morphology and timing from peripheral pulse signals. However, existing methods largely rely on statistical alignment and data-driven generation. They fail to explicitly structure the latent space around physiology-aware electro-hemodynamic factors and lack constraints from forward physiological dynamics. To address these challenges, we propose PG-LRF, a physiology-guided latent rectified flow framework. PG-LRF introduces an electro-hemodynamic simulator that co-models ECG and PPG through shared cardiac phase dynamics. Guided by this simulator, a Physiology-Aware AutoEncoder learns a structured electro-hemodynamic latent space. Then we integrate this simulator guidance into a PPG-conditioned latent rectified flow, enforcing ECG-side morphology consistency and ECG-to-PPG forward hemodynamic consistency during generative transport. Experiments on the large-scale MC-MED dataset demonstrate that PG-LRF significantly improves PPG-to-ECG generation and downstream cardiovascular disease classification, proving its ability to generate ECGs that are both signal-faithful and physiologically plausible under the ECG-to-PPG hemodynamic pathway

Problem

• PPG-to-ECG generation
• electro-hemodynamic
• physiology-aware
• latent space
• signal morphology

Innovation

• physiology-guided generation
• latent rectified flow
• electro-hemodynamic modeling
• PPG-to-ECG synthesis
• structured latent space