{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T15:27:19Z","timestamp":1782574039093,"version":"3.54.5"},"reference-count":40,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/501100003130","name":"Fonds Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["G084023N"],"award-info":[{"award-number":["G084023N"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["DIGITAL HEALTH"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>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 \u201cPPG-compatible\u201d (i.e., HR error &lt;10% during \u226570% of training data). Three quarters trained artefact and activity detection models, one quarter served as the test population. To balance artefact removal and activity preservation, multiple probability thresholds were combined to reject unreliable HR values, remove or interpolate using adjacent reliable values. The Antwerp Activity Index (AAI), an HR-based PA score, was calculated from the resulting PPG and reference data to evaluate threshold combinations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Seventy-eight participants (53.8%) were PPG-compatible, yielding over 5 million datapoints, with 75% (\n                      <jats:italic toggle=\"yes\">n\u2009=\u2009<\/jats:italic>\n                      58; 4,144,654 datapoints) used for training and 25% (\n                      <jats:italic toggle=\"yes\">n\u2009=\u2009<\/jats:italic>\n                      20; 992,180 datapoints) for testing. The artefact model detected artefacts with a sensitivity of 58.5% in daily life and 76.6% during exercise, while limiting incorrect removals (74.9\u201391.3% specificity). Rejecting data for AAI-calculation when artefact probability was &gt;50% and activity probability &lt;70% produced the highest agreement with reference AAI (Pearson\u2019s\n                      <jats:italic toggle=\"yes\">r\u2009=\u2009.<\/jats:italic>\n                      89\u2013.96).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This new machine learning-based procedure, which operates on device-generated HR rather than PPG waveforms, effectively removes artefacts while preserving key activity signals, ensuring clinically relevant PA assessment in daily life.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/20552076261426622","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T12:04:11Z","timestamp":1774958651000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":2,"title":["A novel machine learning procedure to detect and remove artefacts in heart rate data obtained from photoplethysmography wearables: A prospective cohort study"],"prefix":"10.1177","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5922-2095","authenticated-orcid":false,"given":"Paulien","family":"Vermunicht","sequence":"first","affiliation":[{"name":"University of Antwerp"},{"name":"Department of Cardiology, Antwerp University Hospital, Antwerp, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4214-9932","authenticated-orcid":false,"given":"Christophe","family":"Buyck","sequence":"additional","affiliation":[{"name":"University of Antwerp"},{"name":"Department of Cardiology, Antwerp University Hospital, Antwerp, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9395-2271","authenticated-orcid":false,"given":"Sebastiaan","family":"Naessens","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Antwerp University Hospital, Antwerp, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9881-6248","authenticated-orcid":false,"given":"Wendy","family":"Hens","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Antwerp University Hospital, Antwerp, Belgium"},{"name":"University of Antwerp"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emeline","family":"Van Craenenbroeck","sequence":"additional","affiliation":[{"name":"University of Antwerp"},{"name":"Department of Cardiology, Antwerp University Hospital, Antwerp, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan Sebastian","family":"Piedrahita Giraldo","sequence":"additional","affiliation":[{"name":"University of Antwerp"},{"name":"University of Antwerp"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2704-9530","authenticated-orcid":false,"given":"Katsiaryna","family":"Makayed","sequence":"additional","affiliation":[{"name":"University of Antwerp"},{"name":"University of Antwerp"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saartje","family":"Herman","sequence":"additional","affiliation":[{"name":"University of Antwerp"},{"name":"University of Antwerp"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kris","family":"Laukens","sequence":"additional","affiliation":[{"name":"University of Antwerp"},{"name":"University of Antwerp"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johan","family":"Roeykens","sequence":"additional","affiliation":[{"name":"Antwerp University Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Koen","family":"De Deckere","sequence":"additional","affiliation":[{"name":"Sports Medical Center Nottebohm Brecht, Brecht, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8641-4658","authenticated-orcid":false,"given":"Lien","family":"Desteghe","sequence":"additional","affiliation":[{"name":"University of Antwerp"},{"name":"Department of Cardiology, Antwerp University Hospital, Antwerp, Belgium"},{"name":"Hasselt University"},{"name":"University of Antwerp"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hein","family":"Heidbuchel","sequence":"additional","affiliation":[{"name":"University of Antwerp"},{"name":"Department of Cardiology, Antwerp University Hospital, Antwerp, Belgium"},{"name":"Hasselt University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,3,31]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12889-020-08715-4"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehac613"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjmed.2016.09.031"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.21037\/cdt.2019.04.08"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.21037\/cdt.2019.06.05"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1249\/MSS.0000000000001284"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2023.113150"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1249\/MSS.0000000000001388"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1093\/ehjdh\/ztac016"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105596"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.3390\/bios13070718"},{"key":"e_1_3_3_13_2","first-page":"1206","article-title":"Evaluation of different machine learning models for photoplethysmogram signal artifact detection","author":"Athaya T","year":"2020","unstructured":"Athaya T, Choi S. Evaluation of different machine learning models for photoplethysmogram signal artifact detection. I C Inf Comm Tech Co 2020: 1206\u20131208.","journal-title":"I C Inf Comm Tech Co"},{"key":"e_1_3_3_14_2","first-page":"182","volume-title":"Artifact detection of wrist photoplethysmograph signals11th International Conference on Bio-inspired Systems and Signal Processing","author":"Vandecasteele K","year":"2018","unstructured":"Vandecasteele K, L\u00e1zaro J, Cleeren E, et al. Artifact detection of wrist photoplethysmograph signals. In 11th International Conference on Bio-inspired Systems and Signal Processing. Madeira, Portugal: SCITEPRESS, 2018, pp.182\u2013189."},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1093\/europace\/euad122.550"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1093\/ehjdh\/ztaf084"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1177\/20552076251337598"},{"key":"e_1_3_3_18_2","unstructured":"Technology PRa. Polar H10 Heart Rate Sensor System. November 11 2019 2019."},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.3390\/s22176536"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1080\/1091367X.2022.2161820"},{"key":"e_1_3_3_21_2","first-page":"179","article-title":"A probabilistic approach to training machine learning models using noisy data","author":"Alzraiee AH","year":"2024","unstructured":"Alzraiee AH, Niswonger RG. A probabilistic approach to training machine learning models using noisy data. Environ Modell Softw 2024; 179. DOI: ARTN 106133 . 1016\/j.envsoft.2024.106133","journal-title":"Environ Modell Softw"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.2196\/10828"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.2196\/14707"},{"key":"e_1_3_3_24_2","unstructured":"Cardiac Monitors Heart Rate Meters and Alarms."},{"key":"e_1_3_3_25_2","first-page":"45","article-title":"Optimisation of artefact detection in photoplethysmography heart rate data: influence of different classifiers in machine learning models","author":"Vermunicht P","year":"2024","unstructured":"Vermunicht P, Buyck C, Makayed K, et al. Optimisation of artefact detection in photoplethysmography heart rate data: influence of different classifiers in machine learning models. Eur Heart J 2024; 45. DOI: ARTN ehae6663533 .1093\/eurheartj\/ehae666.3533","journal-title":"Eur Heart J"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjmed.2016.09.031"},{"key":"e_1_3_3_27_2","first-page":"45","article-title":"2020 ESC guidelines on sports cardiology and exercise in patients with cardiovascular disease","volume":"74","author":"Pelliccia A","year":"2021","unstructured":"Pelliccia A, Sharma S, Gati S, et al. 2020 ESC guidelines on sports cardiology and exercise in patients with cardiovascular disease. Rev Esp Cardiol (Engl Ed) 2021; 74: 45.","journal-title":"Rev Esp Cardiol (Engl Ed)"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajpc.2022.100425"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1136\/bjsports-2022-105669"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.2583"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.3390\/bios11040126"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jelectrocard.2021.06.009"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3491593"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106443"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1177\/1179546817710028"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1097\/HJR.0b013e328334f42d"},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1177\/0269215509353262"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1207\/s15324796abm3101_9"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1136\/bjsports-2020-102955"},{"key":"e_1_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.3390\/jpm7020003"},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.2196\/10108"}],"container-title":["DIGITAL HEALTH"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261426622","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/20552076261426622","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261426622","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T17:56:10Z","timestamp":1777398970000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/20552076261426622"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":40,"alternative-id":["10.1177\/20552076261426622"],"URL":"https:\/\/doi.org\/10.1177\/20552076261426622","relation":{},"ISSN":["2055-2076","2055-2076"],"issn-type":[{"value":"2055-2076","type":"print"},{"value":"2055-2076","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"article-number":"20552076261426622"}}