Key result
Machine learning artefact removal improves PPG heart rate accuracy against Holter to ~7 bpm error.
Why the study?
Validation of heart rate monitors in cardiac populations during daily life compared to gold-standard Holter monitoring remains limited, and improved algorithms are needed to filter unreliable photoplethysmography-based data.
Do wearable heart rate monitors (ECG-based and PPG-based) combined with a novel artefact removal procedure accurately measure heart rate compared to Holter monitoring in patients with cardiac disease?
Observational (n=15)
Do wearable heart rate monitors (ECG-based and PPG-based) combined with a novel artefact removal procedure accurately measure heart rate compared to Holter monitoring in patients with cardiac disease?
Answers are grounded in this paper and cite their sources.
A novel machine learning artefact removal procedure improves the accuracy of PPG-based wearable heart rate monitors in cardiac patients, though ECG-based chest straps remain more accurate.
Introduction: Heart rate (HR) monitors could objectively measure physical activity intensity in patients with cardiac disease. However, thorough validation of HR monitors in cardiac populations during daily life, compared to gold-standard Holter monitoring, remains limited. Photoplethysmography (PPG)-based HR data provides near-continuous data, spanning longer periods, but improved algorithms to filter unreliable data are needed. Methods: This observational, prospective pilot study compared the accuracy of two wearables for HR monitoring (electrocardiogram [ECG]-based Polar H10 chest strap and PPG-based Fitbit Inspire 2 wrist tracker) against Holter monitoring in 15 patients with atrial fibrillation (AF), heart failure (HF) and coronary artery disease referred for cardiac rehabilitation (CR). All devices were worn simultaneously for 24 h. We developed and assessed an artefact removal procedure (ARP) using logistic regression machine learning models to detect unreliable PPG data. After implementing the ARP, PPG-based HR data improved to a correlation of 0.75, with MAE of 7.2 bpm and MAPE of 12.4%. The procedure removed nearly one-third of unreliable data, achieving an 81% accuracy. Conclusions: While ECG-based monitors provide HR data with clinical acceptable accuracy, PPG-based monitors present accuracy challenges. Our machine learning procedure showed potential to filter unreliable PPG-based HR data, which could help measure physical activity intensity in cardiac disease continuously.
No takes yet. Share an insight, caveat, or question.
Vermunicht et al. (2025) conducted an observational in Atrial fibrillation, heart failure, and coronary artery disease (n=15). Wearable heart rate monitors (ECG-based Polar H10 and PPG-based Fitbit Inspire 2) vs. Holter monitoring was evaluated on Accuracy of heart rate monitoring (correlation, mean absolute error, mean absolute percentage error). A machine learning artefact removal procedure improved PPG-based heart rate accuracy against Holter monitoring, achieving a correlation of 0.75, MAE of 7.2 bpm, and MAPE of 12.4%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: