ChatPPG.
Join free
First page or project page of “Inferring Optical Tissue Properties from Photoplethysmography using Hybrid Amortized Inference” (opens in a new tab)

PaperarXiv:2510.02073

Inferring Optical Tissue Properties from Photoplethysmography using Hybrid Amortized Inference

Preprint2025Added Sep 26, 2026

  • JB
  • MC
  • AW
  • AM
  • AC
  • PA

Authors: Jens Behrmann, Maria R. Cervera, Antoine Wehenkel, Andrew C. Miller, Albert Cerussi, Pranay Jain et al. (11 authors)

arXiv preprint (cs.LG, physics.bio-ph, stat.ML)

PDF (opens in a new tab) arXiv2510.02073 (opens in a new tab) Publisher (opens in a new tab) Cite
First page or project page of “Inferring Optical Tissue Properties from Photoplethysmography using Hybrid Amortized Inference” (opens in a new tab)

Behrmann, Jens et al., "Inferring Optical Tissue Properties from Photoplethysmography using Hybrid Amortized Inference", arXiv:2510.02073, CC BY 4.0

TL;DR

Smart wearables enable continuous tracking of established biomarkers such as heart rate, heart rate variability, and blood oxygen saturation via photoplethysmography (PPG). Beyond these metrics, PPG waveforms contain richer physiological information, as recent deep learning (DL) studies demonstrate. However, DL models often rely on features with unclear physiological meaning, creating a tension between predictive power, clinical interpretability, and sensor design.

  • Form factor: other

Abstract

Smart wearables enable continuous tracking of established biomarkers such as heart rate, heart rate variability, and blood oxygen saturation via photoplethysmography (PPG). Beyond these metrics, PPG waveforms contain richer physiological information, as recent deep learning (DL) studies demonstrate. However, DL models often rely on features with unclear physiological meaning, creating a tension between predictive power, clinical interpretability, and sensor design. We address this gap by introducing PPGen, a biophysical model that relates PPG signals to interpretable physiological and optical parameters. Building on PPGen, we propose hybrid amortized inference (HAI), enabling fast, robust, and scalable estimation of relevant physiological parameters from PPG signals while correcting for model misspecification. In extensive in-silico experiments, we show that HAI can accurately infer physiological parameters under diverse noise and sensor conditions. Our results illustrate a path toward PPG models that retain the fidelity needed for DL-based features while supporting clinical interpretation and informed hardware design.

Verbatim from arXiv (opens in a new tab) · arXiv metadata (abstracts are released under CC0)

Results on ChatPPG leaderboards

All leaderboards

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.

Tasks & signals

Signals

PPG

Keywords

opticstissue-propertiesinferencephysics

How it works

How Method works: Setup → Method → TargetSetup: Signals (PPG); Form factor (other). Method: Method.SetupSignals: PPGSignalsPPGForm factor: otherForm factorotherMethodMethod

Cite this paper

APA

Behrmann, J., Cervera, M. R., Wehenkel, A., Miller, A. C., Cerussi, A., Jain, P., et al. (2025). Inferring Optical Tissue Properties from Photoplethysmography using Hybrid Amortized Inference. arXiv preprint. https://doi.org/10.48550/arXiv.2510.02073

BibTeX

@misc{behrmann2025inferring,
  title         = {{Inferring Optical Tissue Properties from Photoplethysmography using Hybrid Amortized Inference}},
  author        = {Behrmann, Jens and Cervera, Maria R. and Wehenkel, Antoine and Miller, Andrew C. and Cerussi, Albert and Jain, Pranay and others},
  year          = {2025},
  howpublished  = {arXiv preprint},
  doi           = {10.48550/arXiv.2510.02073},
  eprint        = {2510.02073},
  archivePrefix = {arXiv}
}

Built from the hub record. Check it against the publisher before submitting.

Added to the ChatPPG research hub

Same tasks, data and authors