Hybrid modeling of photoplethysmography for non-invasive monitoring of cardiovascular parameters

Emanuele Palumbo, Sorawit Saengkyongam, Maria R. Cervera, Jens Behrmann, Andrew Miller, Guillermo Sapiro, Christina Heinze-Deml, Antoine Wehenkel

Keywords: PPG, APW, Photoplethysmography, Cardiovascular Modeling, Simulation-based Inference, Generative Modeling, Hybrid Learning

TL;DR: We propose a hybrid model that combines cardiovascular simulations with a learnt map between APW and PPG to predict cardiac biomarkers from PPG.

Track: Findings

Abstract:

Continuous cardiovascular monitoring can play a key role in precision health. However, some fundamental cardiac biomarkers of interest, including stroke volume and cardiac output, require invasive measurements, e.g., arterial pressure waveforms (APW). As a non-invasive alternative, photoplethysmography (PPG) measurements are routinely collected in hospital settings.
Unfortunately, the prediction of key cardiac biomarkers from PPG instead of APW remains an open challenge, further complicated by the scarcity of annotated PPG measurements.
As a solution, we propose a hybrid approach that uses hemodynamic simulations and unlabeled clinical data to estimate cardiovascular biomarkers directly from PPG signals. Our hybrid model combines a conditional variational autoencoder trained on paired PPG-APW data with a conditional density estimator of cardiac biomarkers trained on labeled simulated APW segments. As a key result, our experiments demonstrate that the proposed approach can detect fluctuations of cardiac output and stroke volume and outperform a supervised baseline in monitoring temporal changes in these biomarkers.

General Area: Models and Methods

Specific Subject Areas: Bayesian & Probabilistic Methods, Unsupervised Learning

Data And Code Availability: No

Ethics Board Approval: No

Entered Conflicts: I confirm the above

Anonymity: I confirm the above

Submission Number: 263