Pulseflow: PPG Counterfactual Generation Via Latent Transport

2026-09-27

AI Summary

This study addresses the scarcity of labeled clinical photoplethysmography (PPG) data for atrial fibrillation (AF) and the underutilization of source signals by proposing PulseFlow, a novel generative framework. To our knowledge, this work introduces the first source-conditioned counterfactual generation mechanism, integrating conditional representation learning with invertible latent transport to explicitly model transformations from observed source signals to target states. Unlike conventional approaches that merely align marginal distributions, PulseFlow enables precise cardiac rhythm editing while preserving subject-specific physiological information. Experimental evaluations on two independent clinical cohorts demonstrate that the proposed framework effectively achieves rhythm conversion with strict source correspondence, substantially improving AF classification performance in few-shot scenarios.

Abstract

Photoplethysmography (PPG) has become an important modality for continuous cardiovascular monitoring, including atrial fibrillation (AF) detection. However, labeled AF recordings remain limited in many clinical settings, making model adaptation difficult when only limited target data are available. Generative modeling offers a natural way to alleviate this scarcity by synthesizing additional AF signals. Existing approaches, however, mainly generate samples that match the target condition without explicitly modeling how an observed source recording should be transformed, making it difficult to leverage abundant source recordings from a specific population or cohort for targeted augmentation. We introduce PulseFlow, a source-conditioned counterfactual generation framework that combines conditional representation learning with invertible latent transport to edit cardiac rhythm while retaining information from the source. Experiments across two clinical cohorts demonstrate effective rhythm transformation, measurable source correspondence, and improved AF classification under limited labels.

Problem

• Photoplethysmography
• Atrial Fibrillation
• Counterfactual Generation
• Data Scarcity
• Generative Modeling

Innovation

• Counterfactual Generation
• Invertible Latent Transport
• Conditional Representation Learning
• Photoplethysmography (PPG)
• Atrial Fibrillation Detection