Paperdoi:10.1016/j.compbiomed.2025.110808

Benchmarking of open-source algorithms for heart rate estimation from motion-corrupted photoplethysmography

Venue listedDated Sep 2025Added Nov 17, 2026

  • S
  • P
  • M
  • F
  • S
  • CB

Authors: Sicbaldi, Palmerini, Moscato, di Florio, Silvani, Chiari (University of Bologna)

Computers in Biology and Medicine 196(Pt B) (2025)

TL;DR

Systematic review of 126 published PPG+accelerometer HR algorithms and a uniform benchmark of the 11 with open-source code on PPG-DaLiA. Deep-learning methods beat classical motion-artifact pipelines, especially during walking, stairs and table soccer; BeliefPPG was best on every metric (bias 0.7 ± 0.8 bpm, variability 4.4 ± 2.0 bpm, Spearman 0.73 ± 0.14).

  • Form factor: wrist

Abstract

Photoplethysmography holds promise for continuous, non-intrusive heart rate monitoring through wearable devices. However, motion artifacts can impact the reliability of heart rate estimates. The integration of accelerometer data has been proven helpful in mitigating these artifacts. Although several algorithms that combine photoplethysmography and accelerometer data for heart rate estimation have been proposed, it remains unclear which performs best. We performed a systematic and comprehensive search and evaluation of all relevant published algorithms (N = 126) and benchmarked all available open-source methods (N = 11) using the same real-world dataset. A robust methodological framework was employed for assessing these algorithms, featuring a comprehensive set of performance metrics. Out of 126 retrieved articles, 11 provided open-source implementations and were included in the benchmarking. We found that deep learning algorithms consistently outperformed model-based algorithms and algorithms that did not correct for accelerometer data, particularly in dynamic conditions with substantial motion artifacts. The BeliefPPG algorithm performed best across all metrics, with an estimation bias of 0.7 ± 0.8 bpm, an estimation variability of 4.4 ± 2.0 bpm, and a Spearman's correlation of 0.73 ± 0.14 bpm with the heart rate ground truth. These findings underscore the potential of deep learning techniques to enhance the reliability of photoplethysmography-based heart rate monitoring through integration with accelerometer data in real-world conditions. This work provides valuable insights into the performance of these algorithms and highlights the importance of developing broader, more diverse datasets to enhance generalizability in future research.

Verbatim from Europe PMC (opens in a new tab) · Abstract via Europe PMC; © the authors/publisher

Results on ChatPPG leaderboards

All leaderboards

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

Tasks & signals

Tasks

Heart rateSignal denoising

Signals

Keywords

Heart RateMotion ArtifactBenchmarkSystematic ReviewOpen SourceBeliefPPGWFPVSPECMAR

Datasets used

How it works

How Method works: Setup → Method → TargetSetup: Signals (ppg, acc, ecg); Form factor (wrist). Method: Method. Target: Heart rate; Signal denoising.SetupSignals: ppg, acc, ecgSignalsppg, acc, ecgForm factor: wristForm factorwristMethodMethodTargetHeart rateHeart rateSignal denoisingSignal denoising

Cite this paper

Cite this paper with the fields recorded here. Check it against the publisher before submitting.

Benchmarking of open-source algorithms for heart rate estimation from motion-corrupted photoplethysmography. (2025). Computers in Biology and Medicine 196. https://doi.org/10.1016/j.compbiomed.2025.110808
@article{sicbaldiopensour2025benchmarking,
  title         = {{Benchmarking of open-source algorithms for heart rate estimation from motion-corrupted photoplethysmography}},
  year          = {2025},
  journal       = {Computers in Biology and Medicine 196},
  doi           = {10.1016/j.compbiomed.2025.110808}
}

Added to the ChatPPG research hub