Paperdoi:10.1016/j.compbiomed.2025.110808
Benchmarking of open-source algorithms for heart rate estimation from motion-corrupted photoplethysmography
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 leaderboardsNo results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.
Tasks & signals
Tasks
Signals
Devices
Keywords
Datasets used
How it works
Cite this paper
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