BeliefPPG: Uncertainty-aware heart rate estimation from PPG signals via belief propagation

Valentin Bieri, Paul Streli, Berken Utku Demirel, Christian Holz
Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence, PMLR 216:173-183, 2023.

Abstract

We present a novel learning-based method that achieves state-of-the-art performance on several heart rate estimation benchmarks extracted from photoplethysmography signals (PPG). We consider the evolution of the heart rate in the context of a discrete-time stochastic process that we represent as a hidden Markov model. We derive a distribution over possible heart rate values for a given PPG signal window through a trained neural network. Using belief propagation, we incorporate the statistical distribution of heart rate changes to refine these estimates in a temporal context. From this, we obtain a quantized probability distribution over the range of possible heart rate values that captures a meaningful and well-calibrated estimate of the inherent predictive uncertainty. We show the robustness of our method on eight public datasets with three different cross-validation experiments.

Cite this Paper

BibTeX
@InProceedings{pmlr-v216-bieri23a, title = {{BeliefPPG}: Uncertainty-aware heart rate estimation from {PPG} signals via belief propagation}, author = {Bieri, Valentin and Streli, Paul and Demirel, Berken Utku and Holz, Christian}, booktitle = {Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence}, pages = {173--183}, year = {2023}, editor = {Evans, Robin J. and Shpitser, Ilya}, volume = {216}, series = {Proceedings of Machine Learning Research}, month = {31 Jul--04 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v216/bieri23a/bieri23a.pdf}, url = {https://proceedings.mlr.press/v216/bieri23a.html}, abstract = {We present a novel learning-based method that achieves state-of-the-art performance on several heart rate estimation benchmarks extracted from photoplethysmography signals (PPG). We consider the evolution of the heart rate in the context of a discrete-time stochastic process that we represent as a hidden Markov model. We derive a distribution over possible heart rate values for a given PPG signal window through a trained neural network. Using belief propagation, we incorporate the statistical distribution of heart rate changes to refine these estimates in a temporal context. From this, we obtain a quantized probability distribution over the range of possible heart rate values that captures a meaningful and well-calibrated estimate of the inherent predictive uncertainty. We show the robustness of our method on eight public datasets with three different cross-validation experiments.} }
Endnote
%0 Conference Paper %T BeliefPPG: Uncertainty-aware heart rate estimation from PPG signals via belief propagation %A Valentin Bieri %A Paul Streli %A Berken Utku Demirel %A Christian Holz %B Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2023 %E Robin J. Evans %E Ilya Shpitser %F pmlr-v216-bieri23a %I PMLR %P 173--183 %U https://proceedings.mlr.press/v216/bieri23a.html %V 216 %X We present a novel learning-based method that achieves state-of-the-art performance on several heart rate estimation benchmarks extracted from photoplethysmography signals (PPG). We consider the evolution of the heart rate in the context of a discrete-time stochastic process that we represent as a hidden Markov model. We derive a distribution over possible heart rate values for a given PPG signal window through a trained neural network. Using belief propagation, we incorporate the statistical distribution of heart rate changes to refine these estimates in a temporal context. From this, we obtain a quantized probability distribution over the range of possible heart rate values that captures a meaningful and well-calibrated estimate of the inherent predictive uncertainty. We show the robustness of our method on eight public datasets with three different cross-validation experiments.
APA
Bieri, V., Streli, P., Demirel, B.U. & Holz, C.. (2023). BeliefPPG: Uncertainty-aware heart rate estimation from PPG signals via belief propagation. Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 216:173-183 Available from https://proceedings.mlr.press/v216/bieri23a.html.

Related Material