BeliefPPG: Uncertainty-aware Heart Rate Estimation from PPG signals via Belief Propagation

TL;DR

BeliefPPG introduces a probabilistic, uncertainty-aware approach for heart rate estimation from PPG signals using belief propagation within a hidden Markov model framework, achieving state-of-the-art results across multiple datasets.

Contribution

It presents a novel neural network-based method that models heart rate as a stochastic process and refines estimates using belief propagation to incorporate temporal dynamics.

Findings

State-of-the-art performance on multiple benchmarks

Robustness demonstrated across eight datasets

Provides well-calibrated uncertainty estimates

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.