A novel machine learning procedure to detect and remove artefacts in heart rate data obtained from photoplethysmography wearables: A prospective cohort study

Digital Health 2026 Open access

Read full text
Authors: Paulien Vermunicht, Christophe Buyck, Sebastiaan Naessens, Wendy Hens, Emeline Van Craenenbroeck, Juan Sebastian Piedrahita Giraldo, Katsiaryna Makayed, Saartje Herman, Kris Laukens, Johan Roeykens, Koen De Deckere, Lien Desteghe
+1 more Hein Heidbüchel
DOI: 10.1177/20552076261426622
Cited by: 1
References: 32

Abstract

Introduction: Photoplethysmography (PPG) based heart rate (HR) monitoring supports continuous assessment of physical activity intensity, but device generated HR values remain prone to motion artefacts. This study validated a novel machine learning procedure that detects artefacts directly in PPG derived HR data, rather than in raw waveforms that are unavailable in commercial devices. Methods: In this prospective study, 149 participants (46 following cardiac rehabilitation, 103 healthy) wore a PPG-based wrist device and a reference chest strap for 12 weeks. Prior testing defined participants as "PPG-compatible" (i.e., HR error

Fields of Study & Subjects

Non-Invasive Vital Sign Monitoring Heart Rate Variability and Autonomic Control Optical Imaging and Spectroscopy Techniques

Publication details

Journal / source
Digital Health
Publisher
SAGE Publications
Volume
12
Pages
20552076261426622–20552076261426622
Publication date
1 February 2026
Language
EN