PPG2ECG: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation

arXiv:2605.12541 · eess.SP, cs.AI, cs.LG · Submitted 2026-05-09 · Read on arXiv

Listen

Radio episode about this paper

Transcript

Introduction to the show: ident: Electrical Engineering. The day in electrical engineering: signals, systems and the hardware that carries them.

Rosa: We're looking at the paper: "PPG2ECG: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation".

Dev: Here's the gist of the paper. Electrocardiography (ECG) is the clinical standard for cardiac assessment but requires dedicated hardware that does not scale to daily-life monitoring 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.

Rosa: Pruning redundant reasoning tokens PG-LRF, a physiology-guided latent rectified flow framework, introduces an electro-hemodynamic simulator that co-models ECG and PPG through shared cardiac phase dynamics.

Dev: This framework is guided by this simulator to learn a structured electro-hemodynamic latent space using a Physiology-Aware AutoEncoder.

Rosa: Subsequently, it integrates 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.

Paper summary: Rosa: So, this paper is called "PPG2ECG: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation". It basically tackles the problem of using simple wearable pulse data, or PPG, to generate an electrocardiogram because ECG is the gold standard for clinical cardiac assessment but it needs dedicated hardware that doesn't scale well for daily use <ref:2605.12541#pg1>.

Dev: Right. The core idea here is to bridge that gap by recovering the electrical shape and timing from just a peripheral pulse signal, PPG, and they argue that current methods mostly rely on just statistical alignment and data-driven generation which doesn't explicitly structure the latent space around how the physiology actually works <ref:2605.12541#pg1>.

Rosa: Exactly. They point out two main challenges: first, there's a lack of physiology-aware latent abstraction, meaning PPG and ECG are coupled but they show different things; ECG shows electrical activation, while PPG captures the delayed pulse <ref:2605.12541#pg2>.

Dev: And the second challenge is missing simulator guidance. They say existing methods often hallucinate physically impossible delays by ignoring the actual cardiac cycle dynamics and that forward flow from ECG to PPG thirty-one twenty-four <ref:2605.12541#pg2>.

Rosa: So they propose PG-LRF as a framework for this, using an electro-hemodynamic simulator that co-models both ECG and PPG through shared cardiac phase dynamics <ref:2605.12541#pg3>. They use this simulator to guide a Physiology Aware AutoEncoder, or PAE, which learns a structured latent space by enforcing consistency between the two modalities and using latency consistency derived from the simulator <ref:2605.12541#pg3>.

Dev: And then they use this guidance in a PPG conditioned latent rectified flow to generate ECG latents from noise, where the simulator residuals steer that transport toward matching ECG morphology and ensuring forward hemodynamic consistency between ECG and PPG during training <ref:2605.12541#pg3>. It’s using the simulator as soft, phase-aware guidance instead of a hard constraint which they think avoids severe model mismatch <ref:2605.12541#pg2>.

Rosa: That means they are trying to keep the flexibility of data-driven latent generation while anchoring those generated distributions to dynamics that are electro-hemodynamically plausible <ref:2605.12541#pg3>. It’s a way to get signal fidelity while respecting the underlying physics of how the heart works <ref:2605.12541#pg3>.

Dev: From an engineering standpoint, I'm interested in how they handle that coupling between upstream electrical activation and the delayed peripheral pulse <ref:2605.12541#pg2>. How do you make sure the latent space respects that directional relationship?

Paper summary: Rosa: Well, they use a shared cardiac phase oscillator within their simulator to co-model those dynamics <ref:2605.12541#pg3>. This helps regularize the latent space using the pulse arrival delay, or delta PAT, which acts as a regularization term for the PAE latent space <ref:2605.12541#pg3>.

Dev: That makes sense for structuring the manifold. But when you're training that flow, how do you actually enforce that ECG-to-PPG forward hemodynamic consistency during the transport process? Is it just adding a loss term?

Rosa: They use two things there. First, simulator derived residuals are used to penalize deviations from the desired ECG vector field by the Euler residual <ref:2605.12541#pg3>. Second, they use PPG simulator losses to regularize generated ECGs through their induced PPG response <ref:2605.12541#pg3>.

Dev: So those simulator constraints act as soft physiological priors, narrowing down the possibilities in that underdetermined problem of going from PPG back to ECG <ref:2605.12541#pg3>. That sounds like a clever way to manage the uncertainty without over-constraining the whole thing <ref:2605.12541#pg3>.

Rosa: And they combine that statistical transport with physiological regularization to produce ECGs that are signal-faithful and preserve critical clinical intervals <ref:2605.12541#pg3>. It’s aiming for better cardiovascular disease classification on the large scale MC-MED dataset <ref:2605.12541#pg3>.

Dev: So, looking at the overall paper, "PPG2ECG: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation", it really proposes integrating mechanistic physiological priors with data-driven latent generation <ref:2605.12541#pg2>.

Rosa: It’s about using that simulator knowledge as soft, phase aware guidance while keeping the flexibility of the data driven latent generation <ref:2605.12541#pg3>. The authors are showing how this works by introducing three components: the simulator, the PAE learning a shared latent space, and then the rectified flow guided by those residuals <ref:2605.12541#pg3>.

Dev: I think what matters is that they show improvements over previous work when you look at their metrics. They reduced Mean Absolute Error from zero point eight seven to zero point seven one and Root Mean Square Error from one point three two to one point zero seven <ref:2605.12541#pg3>. That’s a measurable improvement in waveform fidelity and accuracy compared to strong baselines <ref:2605.12541#pg3>.

Rosa: And they also saw gains in clinical error measures, like QRS error dropping from forty-eight point one to thirty-eight point six milliseconds and QTcF error from thirty-five point nine to thirty-two point two milliseconds <ref:2605.12541#pg3>. That means the generated ECGs are not just looking visually right, but they are capturing the important clinical timing intervals better than before <ref:2605.12541#pg3>.

Paper summary: Dev: The paper concludes that PPG-to-ECG generation is improved by this framework because it handles complex cross modal variations better <ref:2605.12541#pg3>. It moves beyond just data driven similarity to explicitly encode the directional physiological coupling <ref:2605.12541#pg2>.

Rosa: Exactly. So, the main implication is that this framework can help bridge the gap between ubiquitous wearable sensing and verifiable clinical cardiac assessment <ref:2605.12541#pg3>. It shows that integrating simulator knowledge as soft guidance can make data driven models much more robust for tasks like long term monitoring or when ECG isn't available <ref:2605.12541#pg3>.

Dev: It does have limitations, though they mentioned needing evaluation on additional datasets to fully assess generalization <ref:2605.12541#pg3>. So while the results are strong on MC-MED, we need to see how robust this performs outside of that specific data distribution <ref:2605.12541#pg3>.

Rosa: That’s a fair point. So, in short, "PPG2ECG: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation" introduces a simulator to guide latent space learning and flow matching, leading to ECGs that are not only signal faithful but also preserve critical clinical intervals <ref:2605.12541#pg3>.

Dev: It's about using mechanistic knowledge to improve the performance of purely data driven generation problems by structuring the latent space around electro-hemodynamic factors <ref:2605.12541#pg2>.

Rosa: So, to wrap up this talk on "PPG2ECG: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation", the authors are presenting a method where they use an electro-hemodynamic simulator to co model ECG and PPG through shared cardiac phase dynamics <ref:2605.12541#pg3>.

Dev: They use this simulator to guide a Physiology Aware AutoEncoder which learns a shared latent space regularized by cross modal alignment and latency consistency from the simulator <ref:2605.12541#pg3>. And then they use that guidance in a PPG conditioned latent rectified flow to generate ECG latents while using simulator residuals to enforce ECG side morphology consistency and forward hemodynamic consistency during training <ref:2605.12541#pg3>.

Rosa: The result is a framework that combines statistical transport with physiological regularization to produce ECGs that are signal faithful, preserve critical clinical intervals, and improve cardiovascular disease classification on the large scale MC-MED dataset <ref:2605.12541#pg3>.

Dev: It’s about using simulator knowledge as soft, phase aware guidance while retaining the flexibility of data driven latent generation to bridge the gap between wearable sensing and clinical assessment <ref:2605.12541#pg3>.

Conclusion: Rosa: So, this paper is called "PPG2ECG: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation". It basically tackles how to use simple wearable pulse data, or PPG, to make an electrocardiogram because ECG is the standard for clinical cardiac assessment but it needs specialized hardware that doesn't work well for daily monitoring.

Dev: Right. They show how you can recover the electrical shape and timing from just that peripheral pulse signal, PPG, and they argue that current methods mostly rely on statistical alignment which doesn't actually structure the latent space around how physiology works <ref:2605.12541#pg1>.

Rosa: They address the problem of missing physiological awareness in the latent space abstraction. They show how you can build a simulator that models both ECG and PPG through shared cardiac phase dynamics <ref:2605.12541#pg3>.

Dev: And then they use this simulator to guide an encoder, a Physiology Aware AutoEncoder, which learns a structured latent space by enforcing consistency between the two modalities and using latency consistency derived from the simulator <ref:2605.12541#pg3>.

Rosa: Then they use that guidance in a flow matching method to generate ECG latents while using simulator residuals to enforce ECG side morphology consistency and forward hemodynamic consistency during training <ref:2605.12541#pg3>.

Dev: So, the final objective combines statistical transport with these physiological constraints to produce ECGs that are signal faithful and keep critical clinical intervals correct <ref:2605.12541#pg3>.

Rosa: It’s about using simulator knowledge as soft guidance while keeping the flexibility of data driven latent generation to bridge the gap between wearable sensing and clinical assessment <ref:2605.12541#pg3>.

Dev: The authors are showing how integrating simulator knowledge as soft, phase aware guidance can make data driven models much more robust for tasks like long term monitoring or when ECG isn't available <ref:2605.12541#pg3>.

Rosa: They also point out a limitation, though they mention they need to evaluate this on more datasets to see how it generalizes beyond the specific data they used <ref:2605.12541#pg3>.

Dev: That's fair. So, in short, this work proposes a framework that uses an electro-hemodynamic simulator to guide latent space learning and flow matching, leading to ECGs that are not only signal faithful but also preserve critical clinical intervals <ref:2605.12541#pg3>.

Rosa: It’s about using simulator knowledge as soft guidance while retaining the flexibility of data driven latent generation to bridge the gap between wearable sensing and clinical assessment <ref:2605.12541#pg3>.

Dev: Next up, we'll look at how their specific results stack up against those previous attempts at this problem.

Xiaoda Wang, Minxiao Wang, Kaiqiao Han, Defu Cao, Ching Chang, Yidan Shi, Runze Yan, Xiao Luo, Yan Liu, Xiao Hu

Department of Computer Science, Emory University Department of Computer Science, University of California, Los Angeles Department of Computer Science, University of Southern California Department of Statistics, University of Wisconsin–Madison

eess.SP, cs.AI, cs.LG

Submitted: 2026-05-09

Updated: 2026-11-08

Comments: Accepted to NeurIPS 2026

License: http://creativecommons.org/licenses/by-sa/4.0/

Importance score: 84/100

The gist: Electrocardiography (ECG) is the clinical standard for cardiac assessment but requires dedicated hardware that does not scale to daily-life monitoring PPG is ubiquitous in wearables but lacks…

Key concepts

Electro-hemodynamic Simulator
This is a tool that mimics the physical relationship between blood flow (hemodynamics) and electrical signals (ECG). It models how changes in heart function affect both the pulse wave seen in PPG and the resulting electrical signal recorded by an ECG, allowing the model to learn consistent dynamics across both modalities.
Physiology-Aware AutoEncoder
This component learns a structured latent space by using simulator guidance. It takes raw PPG and ECG data as input and maps them into a shared latent space that respects known physiological constraints, such as expected timing delays between the two signals, ensuring the learned representations are physically meaningful.
Latent Rectified Flow
This is a generative modeling technique used to transform random noise into structured data. In this paper, it is conditioned on PPG input and guided by simulator residuals. This ensures that the generated ECGs not only look like real signals but also follow the correct physiological timing and morphology dictated by the learned latent space.

Terminology

Summary

Electrocardiography (ECG) is the clinical standard for cardiac assessment but requires dedicated hardware that does not scale to daily-life monitoring 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. p. 0

Where the paper says it

PG-LRF: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation Xiaoda Wang1,3 , Minxiao Wang2 , Kaiqiao Han3 , Defu Cao4 , Ching Chang3 , Yidan Shi3 , Runze Yan2 , Xiao Luo5 , Yan Liu4 , Xiao Hu2 , Yizhou Sun3 , Wei Wang3 , Carl Yang1 1Department of Computer Science, Emory University 2Nell Hodgson Woodruff School of Nursing, Emory University 3Department of Computer Science, University of California, Los Angeles 4Department of Computer Science, University of Southern California 5Department of Statistics, University of Wisconsin–Madison 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.

Pruning redundant reasoning tokens

PG-LRF, a physiology-guided latent rectified flow framework, introduces an electro-hemodynamic simulator that co-models ECG and PPG through shared cardiac phase dynamics. This framework is guided by this simulator to learn a structured electro-hemodynamic latent space using a Physiology-Aware AutoEncoder. p. 1

Where the paper says it

We introduce a novel electro-hemodynamic simulator that explicitly co-models ECG and PPG by linking an upstream electrical readout with a delayed peripheral pulse via shared cardiac phase dynamics. Using this simulator as a physiological anchor, PG-LRF employs a Physiology-Aware AutoEncoder (PAE) to abstract modality-specific observations into a structured cardiovascular latent space regularized by cross-modal alignment and latency-aware consistency.

Subsequently, it integrates 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. p. 0
Where the paper says it

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.

The main contributions include the Physiology-Guided Generative Formulation, which introduces an electro-hemodynamic physiological simulator to co-model ECG and PPG through shared cardiac phase dynamics, the Physiology-Aware Representation Learning, which designs a Physiology-Aware AutoEncoder that abstracts modality-specific observations into a structured electro-hemodynamic latent space constrained by simulator-derived latency-aware consistency and cross-modal latent alignment, and Simulator-Guided Flow Matching, which integrates the electro-hemodynamic simulator into PPGconditioned latent rectified flow to ensure ECGs are waveform-faithful and physiologically plausible under the ECG-to-PPG hemodynamic pathway. p. 1
Where the paper says it

We design a Physiology-Aware AutoEncoder that abstracts modality-specific observations into a structured electro-hemodynamic latent space, rigorously constrained by simulator-derived latency-aware consistency, and cross-modal latent alignment. ❸ Simulator-Guided Flow Matching.

How the training signal is built

The training process involves two main phases. First, the Physiology-Aware AutoEncoder (PAE) is trained with the objective LPAE to obtain aligned PPG and ECG latent representations. p. 6

Where the paper says it

4 Training and Inference PG-LRF is optimized in two phases. We first train the Physiology-Aware AutoEncoder with the objective LPAE to obtain aligned PPG and ECG latent representations.

The PAE objective (LPAE) comprises three groups of objectives: simulator-informed phase delay consistency (LPAT), autoencoding regularization (Lrec), and cross-modal latent alignment (LGPA). p. 4
Where the paper says it

PAE Training Objective. PAE is optimized with three groups of objectives: native-rate autoencoding, cross-modal latent alignment, and simulator-informed delay consistency.

Specifically, the phase delay consistency loss penalizes deviations from the class-specific simulator delay δPAT, while the autoencoding regularization preserves modality-specific waveform information through Lrec and LKL terms. p. 4
Where the paper says it

(13) (ii) Autoencoding regularization. The reconstruction loss preserves modality-specific waveform information: Lrec = ∥D p θ (zp) − xp∥ 2 2 + ∥De θ (ze) − xe∥ 2 2 .

Where the gains come from

The core of the generation is the Simulator-Guided Latent Rectified Flow, where a conditional vector field transports a Gaussian latent variable toward the ECG latent distribution conditioned on zp. This transport is regularized by simulator-derived residuals to ensure both ECG-side morphological fidelity and ECG-to-PPG forward hemodynamic consistency during training. p. 1

Where the paper says it

On top of this latent space, PG-LRF introduces a simulator-guided latent rectified flow. During training, the generative transport is explicitly regularized by the simulator to ensure both ECG-side morphological fidelity and forward ECG-to-PPG hemodynamic consistency.

The simulator uses a shared cardiac phase oscillator to co-model the dynamics, where the pulse-arrival delay δPAT regularizes the PAE latent space, and vector fields fe and fp define finite-difference residuals for simulator-guided latent flow training. p. 2
Where the paper says it

Instead, it provides a soft training-time interface: the pulse-arrival delay δPAT regularizes the PAE latent space, while the vector fields fe and fp define finite-difference residuals for simulator-guided latent flow training. The shared cardiac phase follows 3

Furthermore, ECG-to-PPG Forward Mapper Gρ is used during training to ensure the generated ECG induces a plausible delayed hemodynamic response. p. 5
Where the paper says it

The generated ECG should not only exhibit plausible electrical morphology, but also induce a plausible delayed hemodynamic response. We therefore use a lightweight ECG-to-PPG forward mapper Gρ as a differentiable bridge from the decoded ECG domain to the PPG signal domain: x˜p = Gρ(˜xe).

The model is optimized in two stages. In the first stage, the PAE is trained to map native-rate PPG and ECG segments into a shared electro-hemodynamic latent space. p. 2

Where the paper says it

(a) The Electro-Hemodynamic Physiological Simulator: co-models ECG and PPG through shared cardiac phase dynamics. (b) Physiology-Aware AutoEncoder: learns an aligned electro-hemodynamic latent space from native-rate PPG and ECG.

The input PPG segment has length 400 at 40 Hz, and the input ECG segment has length 1200 at 120 Hz. p. 6
Where the paper says it

To preserve acquisition-specific temporal structures, we maintain both modalities at their native sampling rates: 40 Hz for PPG (yielding xp ∈ R 400×1 ) and 120 Hz for ECG (yielding xe ∈ R 1200×1 ). Prior to modeling, we apply z-score normalization to each segment.

In the second stage, the PPG encoder, ECG encoder, and ECG decoder are frozen. p. 4
Where the paper says it

(18) The full PAE objective is LPAE = λPATLPAT + Lrec + βLKL + λGPALGPA + λLIDLLID + λCSDLCSD. (19) After PAE training, the PPG encoder, ECG encoder, and ECG decoder are frozen for the subsequent PPG-conditioned latent rectified flow.

The latent rectified flow then learns a conditional vector field that transports Gaussian noise toward the ECG latent distribution conditioned on zp. p. 2
Where the paper says it

The Physiology-Aware AutoEncoder maps both modalities into aligned latent representations zp, ze ∈ R Cz×Tz , where Cz and Tz denote the latent channel dimension and temporal length. The Electro-Hemodynamic Simulator Guided Latent Rectified Flow then learns a conditional vector field vψ(zt, t, zp) that transports a Gaussian latent variable toward the ECG latent distribution conditioned on zp.

The simulator-guided residual losses are used during training to penalize deviations from the ECG vector field by the Euler residual and PPG simulator losses to regularize generated ECGs through their induced PPG response. These simulator constraints function as soft physiological priors, narrowing the set of plausible solutions in the underdetermined PPG-to-ECG inverse problem. p. 1

Where the paper says it

We integrate the electro-hemodynamic simulator into PPGconditioned latent rectified flow. Simulator-derived constraints guide the model to generate ECGs that are waveform-faithful and physiologically plausible under the ECG-to-PPG hemodynamic pathway.

The final objective combines statistical transport with physiological regularization to produce ECGs that are not only signal-faithful but also preserve critical clinical intervals and improve downstream cardiovascular disease classification on the large-scale MC-MED dataset. p. 8
Where the paper says it

Extensive evaluations on the large-scale MC-MED dataset demonstrate that PG-LRF consistently outperforms existing baselines, generating ECGs that are not only signal-faithful but also preserve critical clinical intervals and improve downstream cardiovascular disease classification. Ultimately, PG-LRF effectively bridges the gap between ubiquitous wearable sensing and verifiable clinical cardiac assessment, demonstrating the profound value of integrating mechanistic physiological priors with modern latent generative modeling.

p. 8
Where the paper says it

Extensive evaluations on the large-scale MC-MED dataset demonstrate that PG-LRF consistently outperforms existing baselines, generating ECGs that are not only signal-faithful but also preserve critical clinical intervals and improve downstream cardiovascular disease classification. Ultimately, PG-LRF effectively bridges the gap between ubiquitous wearable sensing and verifiable clinical cardiac assessment, demonstrating the profound value of integrating mechanistic physiological priors with modern latent generative modeling.

p. 8
Where the paper says it

Extensive evaluations on the large-scale MC-MED dataset demonstrate that PG-LRF consistently outperforms existing baselines, generating ECGs that are not only signal-faithful but also preserve critical clinical intervals and improve downstream cardiovascular disease classification. Ultimately, PG-LRF effectively bridges the gap between ubiquitous wearable sensing and verifiable clinical cardiac assessment, demonstrating the profound value of integrating mechanistic physiological priors with modern latent generative modeling.

p. 8
Where the paper says it

Extensive evaluations on the large-scale MC-MED dataset demonstrate that PG-LRF consistently outperforms existing baselines, generating ECGs that are not only signal-faithful but also preserve critical clinical intervals and improve downstream cardiovascular disease classification. Ultimately, PG-LRF effectively bridges the gap between ubiquitous wearable sensing and verifiable clinical cardiac assessment, demonstrating the profound value of integrating mechanistic physiological priors with modern latent generative modeling.

p. 8
Where the paper says it

Extensive evaluations on the large-scale MC-MED dataset demonstrate that PG-LRF consistently outperforms existing baselines, generating ECGs that are not only signal-faithful but also preserve critical clinical intervals and improve downstream cardiovascular disease classification. Ultimately, PG-LRF effectively bridges the gap between ubiquitous wearable sensing and verifiable clinical cardiac assessment, demonstrating the profound value of integrating mechanistic physiological priors with modern latent generative modeling.

p. 8
Where the paper says it

Extensive evaluations on the large-scale MC-MED dataset demonstrate that PG-LRF consistently outperforms existing baselines, generating ECGs that are not only signal-faithful but also preserve critical clinical intervals and improve downstream cardiovascular disease classification. Ultimately, PG-LRF effectively bridges the gap between ubiquitous wearable sensing and verifiable clinical cardiac assessment, demonstrating the profound value of integrating mechanistic physiological priors with modern latent generative modeling.

p. 8
Where the paper says it

Extensive evaluations on the large-scale MC-MED dataset demonstrate that PG-LRF consistently outperforms existing baselines, generating ECGs that are not only signal-faithful but also preserve critical clinical intervals and improve downstream cardiovascular disease classification. Ultimately, PG-LRF effectively bridges the gap between ubiquitous wearable sensing and verifiable clinical cardiac assessment, demonstrating the profound value of integrating mechanistic physiological priors with modern latent generative modeling.

p. 8
Where the paper says it

Extensive evaluations on the large-scale MC-MED dataset demonstrate that PG-LRF consistently outperforms existing baselines, generating ECGs that are not only signal-faithful but also preserve critical clinical intervals and improve downstream cardiovascular disease classification. Ultimately, PG-LRF effectively bridges the gap between ubiquitous wearable sensing and verifiable clinical cardiac assessment, demonstrating the profound value of integrating mechanistic physiological priors with modern latent generative modeling.

PG-LRF consistently improves PPGto-ECG generation across waveform fidelity, clinical interval consistency, and cardiovascular disease detection on the large-scale MC-MED dataset. Compared with the strongest baseline PPGFlowECG, PG-LRF reduces MAE from 0. p. 6

Where the paper says it

As shown in Table 1, PG-LRF achieves the best performance across all metrics. Compared with the strongest baseline PPGFlowECG, PG-LRF reduces MAE from 0.

87 to 0.71, RMSE from 1. p. 6
Where the paper says it

Waveform-level fidelity. We evaluate waveform fidelity using point-wise metrics (MAE and RMSE), distribution-level metrics (FD and FID), and heart-rate consistency (HR MAE).

32 to 1.07, FID from 44. p. 6
Where the paper says it

Waveform-level fidelity. We evaluate waveform fidelity using point-wise metrics (MAE and RMSE), distribution-level metrics (FD and FID), and heart-rate consistency (HR MAE).

17 to 37.79, and HR MAE from 7. p. 6
Where the paper says it

Waveform-level fidelity. We evaluate waveform fidelity using point-wise metrics (MAE and RMSE), distribution-level metrics (FD and FID), and heart-rate consistency (HR MAE).

08 to 3.94. PG-LRF also improves PR error from 68. p. 7
Where the paper says it

3 ms, and QTcF error from 35. p. 7

Where the paper says it

6 ms, QT error from 32. p. 7

Where the paper says it

As shown in Table 2, PG-LRF achieves the best performance across all metrics. Compared with PPGFlowECG, PG-LRF reduces PR error from 68.

3 ms, and QTcF error from 35.

It also improves ST-J60 deviation and both P- and T-wave duration errors, indicating that the generated ECGs better preserve conduction, depolarization, and ST-segment morphology.

9 to 59.9 ms, QRS error from 48. p. 7
Where the paper says it

Compared with PPGFlowECG, PG-LRF reduces PR error from 68. 9 ms, QRS error from 48.

1 to 38.6 ms, QT error from 32.5 to 29.3 ms, and QTcF error from 35.9 to 32.2 ms. ECGs generated by PG-LRF achieve higher AUROC than the PPG-based PaPaGei baseline across all disease categories, improving Macro-AUROC from 0. p. 7
Where the paper says it

04 PG-LRF 0. 01 As shown in Table 3, ECGs generated by PG-LRF achieve higher AUROC than the PPG-based PaPaGei baseline across all disease categories, improving Macro-AUROC from 0.

545 to 0.633.

The paper concludes that PG-LRF effectively bridges the gap between ubiquitous wearable sensing and verifiable clinical cardiac assessment by integrating mechanistic physiological priors with modern latent generative modeling. This framework demonstrates the profound value of integrating simulator knowledge as soft, phase-aware guidance while retaining the flexibility of data-driven latent generation. p. 1

Where the paper says it

A robust approach must instead integrate simulator knowledge as soft, phase-aware guidance while retaining the flexibility of data-driven latent generation. To address these challenges, we propose PG-LRF, a physiology-guided latent rectified flow framework for electro-hemodynamic PPG-to-ECG generation.

The proposed framework may have positive impacts for scalable cardiovascular monitoring by supporting research on long-term cardiac monitoring, data augmentation, and retrospective analysis when ECG is unavailable or difficult to collect continuously. p. 8
Where the paper says it

5 Broader impacts PG-LRF may have positive impacts for scalable cardiovascular monitoring. Since PPG is widely available in wearable devices and bedside monitors, generating ECG-like signals from PPG could support research on long-term cardiac monitoring, data augmentation, and retrospective analysis when ECG is unavailable or difficult to collect continuously.

The work has several limitations, including the need for evaluation on additional datasets to further assess generalization. p. 7
Where the paper says it

2 Cardiovascular Disease Detection To assess whether the generated ECGs preserve clinically useful information, we evaluate downstream multi-label cardiovascular disease detection. Following prior PPG-to-ECG benchmarks, we use visitlevel ICD-based cardiovascular labels, including I48, I71, I70, I44, I25, and I50, covering rhythm, conduction, vascular, ischemic, and heart-failure-related conditions.

The paper presents PG-LRF, a physiology-guided latent rectified flow framework designed to overcome the limitations of purely data-driven PPG-to-ECG generation. p. 8

Where the paper says it

The proposed physiology-guided framework may also encourage more clinically grounded generative modeling for physiological time series. 6 Conclusion In this paper, we presented PG-LRF, a physiology-guided latent rectified flow framework designed to overcome the limitations of purely data-driven PPG-to-ECG generation.

p. 8
Where the paper says it

The proposed physiology-guided framework may also encourage more clinically grounded generative modeling for physiological time series. 6 Conclusion In this paper, we presented PG-LRF, a physiology-guided latent rectified flow framework designed to overcome the limitations of purely data-driven PPG-to-ECG generation.

p. 8
Where the paper says it

The proposed physiology-guided framework may also encourage more clinically grounded generative modeling for physiological time series. 6 Conclusion In this paper, we presented PG-LRF, a physiology-guided latent rectified flow framework designed to overcome the limitations of purely data-driven PPG-to-ECG generation.

p. 8
Where the paper says it

The proposed physiology-guided framework may also encourage more clinically grounded generative modeling for physiological time series. 6 Conclusion In this paper, we presented PG-LRF, a physiology-guided latent rectified flow framework designed to overcome the limitations of purely data-driven PPG-to-ECG generation.

p. 8
Where the paper says it

The proposed physiology-guided framework may also encourage more clinically grounded generative modeling for physiological time series. 6 Conclusion In this paper, we presented PG-LRF, a physiology-guided latent rectified flow framework designed to overcome the limitations of purely data-driven PPG-to-ECG generation.

It introduces an electro-hemodynamic simulator that co-models ECG and PPG via shared cardiac phase dynamics. p. 0
Where the paper says it

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.

p. 0
Where the paper says it

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.

p. 0
Where the paper says it

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.

p. 0
Where the paper says it

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.

p. 0
Where the paper says it

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.

p. 0
Where the paper says it

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.

p. 0
Where the paper says it

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.

This simulator provides soft, phase-aware guidance to a native-rate Physiology-Aware AutoEncoder to structure the latent space, and explicitly regularizes the latent rectified flow to enforce both ECG-side morphological fidelity and forward ECG-to-PPG hemodynamic consistency. p. 8
Where the paper says it

We introduced a novel electro-hemodynamic simulator that comodels ECG and PPG via shared cardiac phase dynamics. This simulator provides soft, phase-aware guidance to a native-rate Physiology-Aware AutoEncoder to structure the latent space, and explicitly regularizes the latent rectified flow to enforce both ECG-side morphological fidelity and forward ECG-to-PPG hemodynamic consistency.

The framework operates as a regularized conditional transport framework where the PAE constructs a dense, physiology-aware manifold, the rectified flow learns an optimal deterministic transport upon it, and the simulator guidance anchors the generated distributions to electro-hemodynamically plausible dynamics. p. 2
Where the paper says it

Second, a Physiology-Aware AutoEncoder (PAE) learns a modality-aware shared latent space regularized by cross-modal alignment and simulator-derived latency consistency. Third, a PPG-conditioned latent rectified flow generates ECG latents from Gaussian noise, while simulator-derived residuals guide the transport toward ECG-side morphology consistency and ECG-to-PPG forward hemodynamic consistency.

p. 2
Where the paper says it

Second, a Physiology-Aware AutoEncoder (PAE) learns a modality-aware shared latent space regularized by cross-modal alignment and simulator-derived latency consistency. Third, a PPG-conditioned latent rectified flow generates ECG latents from Gaussian noise, while simulator-derived residuals guide the transport toward ECG-side morphology consistency and ECG-to-PPG forward hemodynamic consistency.

p. 2
Where the paper says it

Second, a Physiology-Aware AutoEncoder (PAE) learns a modality-aware shared latent space regularized by cross-modal alignment and simulator-derived latency consistency. Third, a PPG-conditioned latent rectified flow generates ECG latents from Gaussian noise, while simulator-derived residuals guide the transport toward ECG-side morphology consistency and ECG-to-PPG forward hemodynamic consistency.

p. 2
Where the paper says it

Second, a Physiology-Aware AutoEncoder (PAE) learns a modality-aware shared latent space regularized by cross-modal alignment and simulator-derived latency consistency. Third, a PPG-conditioned latent rectified flow generates ECG latents from Gaussian noise, while simulator-derived residuals guide the transport toward ECG-side morphology consistency and ECG-to-PPG forward hemodynamic consistency.

p. 2
Where the paper says it

Second, a Physiology-Aware AutoEncoder (PAE) learns a modality-aware shared latent space regularized by cross-modal alignment and simulator-derived latency consistency. Third, a PPG-conditioned latent rectified flow generates ECG latents from Gaussian noise, while simulator-derived residuals guide the transport toward ECG-side morphology consistency and ECG-to-PPG forward hemodynamic consistency.

p. 2
Where the paper says it

Second, a Physiology-Aware AutoEncoder (PAE) learns a modality-aware shared latent space regularized by cross-modal alignment and simulator-derived latency consistency. Third, a PPG-conditioned latent rectified flow generates ECG latents from Gaussian noise, while simulator-derived residuals guide the transport toward ECG-side morphology consistency and ECG-to-PPG forward hemodynamic consistency.

p. 2
Where the paper says it

Second, a Physiology-Aware AutoEncoder (PAE) learns a modality-aware shared latent space regularized by cross-modal alignment and simulator-derived latency consistency. Third, a PPG-conditioned latent rectified flow generates ECG latents from Gaussian noise, while simulator-derived residuals guide the transport toward ECG-side morphology consistency and ECG-to-PPG forward hemodynamic consistency.

The final objective combines statistical transport with physiological regularization to produce ECGs that are not only signal-faithful but also preserve critical clinical intervals and improve downstream cardiovascular disease classification on the large-scale MC-MED dataset. The paper presents PG-LRF, a physiology-guided latent rectified flow framework designed to overcome the limitations of purely data-driven PPG-to-ECG generation. It introduces an electro-hemodynamic simulator that co-models ECG and PPG via shared cardiac phase dynamics. This simulator provides soft, phase-aware guidance to a native-rate Physiology-Aware AutoEncoder to structure the latent space, and explicitly regularizes the latent rectified flow to enforce both ECG-side morphology consistency and ECG-to-PPG forward hemodynamic consistency during generative transport. p. 8
Where the paper says it

We introduced a novel electro-hemodynamic simulator that comodels ECG and PPG via shared cardiac phase dynamics. This simulator provides soft, phase-aware guidance to a native-rate Physiology-Aware AutoEncoder to structure the latent space, and explicitly regularizes the latent rectified flow to enforce both ECG-side morphological fidelity and forward ECG-to-PPG hemodynamic consistency.

p. 8
Where the paper says it

We introduced a novel electro-hemodynamic simulator that comodels ECG and PPG via shared cardiac phase dynamics. This simulator provides soft, phase-aware guidance to a native-rate Physiology-Aware AutoEncoder to structure the latent space, and explicitly regularizes the latent rectified flow to enforce both ECG-side morphological fidelity and forward ECG-to-PPG hemodynamic consistency.

p. 8
Where the paper says it

We introduced a novel electro-hemodynamic simulator that comodels ECG and PPG via shared cardiac phase dynamics. This simulator provides soft, phase-aware guidance to a native-rate Physiology-Aware AutoEncoder to structure the latent space, and explicitly regularizes the latent rectified flow to enforce both ECG-side morphological fidelity and forward ECG-to-PPG hemodynamic consistency.

p. 8
Where the paper says it

We introduced a novel electro-hemodynamic simulator that comodels ECG and PPG via shared cardiac phase dynamics. This simulator provides soft, phase-aware guidance to a native-rate Physiology-Aware AutoEncoder to structure the latent space, and explicitly regularizes the latent rectified flow to enforce both ECG-side morphological fidelity and forward ECG-to-PPG hemodynamic consistency.

p. 8
Where the paper says it

We introduced a novel electro-hemodynamic simulator that comodels ECG and PPG via shared cardiac phase dynamics. This simulator provides soft, phase-aware guidance to a native-rate Physiology-Aware AutoEncoder to structure the latent space, and explicitly regularizes the latent rectified flow to enforce both ECG-side morphological fidelity and forward ECG-to-PPG hemodynamic consistency.

p. 8
Where the paper says it

We introduced a novel electro-hemodynamic simulator that comodels ECG and PPG via shared cardiac phase dynamics. This simulator provides soft, phase-aware guidance to a native-rate Physiology-Aware AutoEncoder to structure the latent space, and explicitly regularizes the latent rectified flow to enforce both ECG-side morphological fidelity and forward ECG-to-PPG hemodynamic consistency.

The framework operates as a regularized conditional transport framework where the PAE constructs a dense, physiology-aware manifold, the rectified flow learns an optimal deterministic transport upon it, and the simulator guidance anchors the generated distributions to electro-hemodynamically plausible dynamics. The final objective combines statistical transport with physiological regularization to produce ECGs that are not only signal-faithful but also preserve critical clinical intervals and improve downstream cardiovascular disease classification on the large-scale MC-MED dataset. The paper presents PG-LRF, a physiology-guided latent rectified flow framework designed to overcome the limitations of purely data-driven PPG-to-ECG generation. It introduces an electro-hemodynamic simulator that co-models ECG and PPG via shared cardiac phase dynamics. This simulator provides soft, phase-aware guidance to a native-rate Physiology-Aware AutoEncoder to structure the latent space, and explicitly regularizes the latent rectified flow to enforce both ECG-side morphology consistency and ECG-to-PPG forward hemodynamic consistency during generative transport. The framework operates as a regularized conditional transport framework where the PAE constructs a dense, physiology-aware manifold, the rectified flow learns an optimal deterministic transport upon it, and the simulator guidance anchors the generated distributions to electro-hemodynamically plausible dynamics. The final objective combines statistical transport with physiological regularization to produce ECGs that are not only signal-faithful but also preserve critical clinical intervals and improve downstream cardiovascular disease classification on the large-scale MC-MED dataset. The paper presents PG-LRF, a physiology-guided latent rectified flow framework designed to overcome the limitations of purely data-driven PPG-to-ECG generation. It introduces an electro-hemodynamic simulator that co-models ECG and PPG via shared cardiac phase dynamics. This simulator provides soft, phase-aware guidance to a native-rate Physiology-Aware AutoEncoder to structure the latent space, and explicitly regularizes the latent rectified flow to enforce both ECG-side morphology consistency and ECG-to-PPG forward hemodynamic consistency during generative transport. The framework operates as a regularized conditional transport framework where the PAE constructs a dense, physiology-aware manifold, the rectified flow learns an optimal deterministic transport upon it, and the simulator guidance anchors the generated distributions to electro-hemodynamically plausible dynamics. The final objective combines statistical transport with physiological regularization to produce ECGs that are not only signal-faithful but also preserve critical clinical intervals and improve downstream cardiovascular disease classification on the large-scale MC-MED dataset. The paper presents PG-LRF, a physiology-guided latent rectified flow framework designed to overcome the limitations of purely data-driven PPG-to-ECG generation. It introduces an electro-hemodynamic simulator that co-models ECG and PPG via shared cardiac phase dynamics. This simulator provides soft, phase-aware guidance to a native-rate Physiology-Aware AutoEncoder to structure the latent space, and explicitly regularizes the latent rectified flow to enforce both ECG-side morphology consistency and ECG-to-PPG forward hemodynamic consistency during generative transport. The framework operates as a regularized conditional transport framework where the PAE constructs a dense, physiology-aware manifold, the rectified flow learns an optimal deterministic transport upon it, and the simulator guidance anchors the generated distributions to electro-hemodynamically plausible dynamics. The final objective combines statistical transport with physiological regularization to produce ECGs that are not only signal-faithful but also preserve critical clinical intervals and improve downstream cardiovascular disease classification on the large-scale MC-MED dataset.

The paper presents PG-LRF, a physiology-guided latent rectified flow framework designed to overcome the limitations of purely data-driven PPG-to-ECG generation. It introduces an electro-hemodynamic simulator that co-models ECG and PPG via shared cardiac phase dynamics. This simulator provides soft, phase-aware guidance to a native-rate Physiology-Aware AutoEncoder to structure the latent space, and explicitly regularizes the latent rectified flow to enforce both ECG-side morphology consistency and ECG-to-PPG forward hemodynamic consistency during generative transport. The framework operates as a regularized conditional transport framework where the PAE constructs a dense, physiology-aware manifold, the rectified flow learns an optimal deterministic transport upon it, and the simulator guidance anchors the generated distributions to electro-hemodynamically plausible dynamics. The final objective combines statistical transport with physiological regularization to produce ECGs that are not only signal-faithful but also preserve critical clinical intervals and improve downstream cardiovascular disease classification on the large-scale MC-MED dataset. The paper presents PG-LRF, a physiology-guided latent rectified flow framework designed to overcome the limitations of purely data-driven PPG-to-ECG generation. It introduces an electro-hemodynamic simulator that co-models ECG and PPG via shared cardiac phase dynamics. This simulator provides soft, phase-aware guidance to a native-rate Physiology-Aware AutoEncoder to structure the latent space, and explicitly regularizes the latent rectified flow to enforce both ECG-side morphology consistency and ECG-to-PPG forward hemodynamic consistency during generative transport. The framework operates as a regularized conditional transport framework where the PAE constructs a dense, physiology-aware manifold, the rectified flow learns an optimal deterministic transport upon it, and the simulator guidance anchors the generated distributions to electro-hemodynamically plausible dynamics. The final objective combines statistical transport with physiological regularization to produce ECGs that are not only signal-faithful but also preserve critical clinical intervals and improve downstream cardiovascular disease classification on the large-scale MC-MED dataset.

Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.

Improvements for AI systems

  1. Physiology-Guided Latent Rectified Flow (PG-LRF) can generate ECGs that are both signal-faithful and physiologically plausible under a forward ECG-to-PPG hemodynamic pathway, improving waveform fidelity by reducing MAE and RMSE compared to CardioFlow.

  2. The improved system can preserve clinically meaningful fiducial measurements such as PR interval, QRS duration, QT interval, QTcF, ST-J60 deviation, P-wave duration, and T-wave duration with better accuracy than previous methods like PPGFlowECG.

  3. The model's ability to detect cardiovascular diseases is enhanced by achieving higher Area Under the Receiver Operating Characteristic (AUROC) scores for multiple disease categories compared to PPG-based baselines, suggesting better recovery of clinically relevant electrical patterns.

  4. The system can be used for long-term cardiac monitoring and retrospective analysis when ECG is unavailable or difficult to collect continuously by generating ECG-like signals from ubiquitous wearable PPG data.

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 PPG2ECG, a physiology-guided latent rectified flow framework. PPG2ECG 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 PPG2ECG 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

Sources

Related papers