{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T15:15:11Z","timestamp":1788189311012,"version":"build-2803163510"},"reference-count":25,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:00:00Z","timestamp":1785456000000},"content-version":"vor","delay-in-days":2,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"PPP"},{"DOI":"10.13039\/100016036","name":"Health~Holland","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016036","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016036","name":"Top Sector Life Sciences & Health","doi-asserted-by":"publisher","award":["2021TKI2217"],"award-info":[{"award-number":["2021TKI2217"]}],"id":[{"id":"10.13039\/100016036","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Future Heart"},{"name":"Eurostars programme","award":["5846"],"award-info":[{"award-number":["5846"]}]},{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018693","name":"Horizon Europe programme","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100013297","name":"Eurostars","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100013297","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,29]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Aims<\/jats:title>\n                    <jats:p>Accurate electrocardiogram (ECG) waveform delineation, rhythm classification, and median beat generation are interdependent steps whose joint modelling improves consistency for downstream computerized diagnostic tasks. This study aimed to develop a lead-agnostic segmentation model that performs these tasks by segmenting individual leads and aggregating predictions in post-processing.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods and results<\/jats:title>\n                    <jats:p>A DeepLabV3-based neural network was trained to segment ECG leads into 20 waveform and rhythm classes using 1931 annotated ECGs and 33 093 ECGs with physician-verified diagnostic statements. Post-processing combined lead-wise predictions to delineate intervals, classify rhythm, and construct median beats. Performance was evaluated on internal (n = 988) and external (n = 1303) test sets. Median beats were compared with PTB-XL+ reference medians from Marquette 12SL and University of Glasgow (Uni-G) using similarity metrics and downstream classification. An interactive web tool (http:\/\/segmentation.ecgx.ai) was released to support further research. In the external set, delineation for PQ interval, QRS duration, and QT interval had mean errors of \u22120.9 \u00b1 10.4\u2005ms, 0.2 \u00b1 7.4\u2005ms, and 1.8 \u00b1 16.0\u2005ms. Rhythm classification was performed by assigning class labels to segmented waveform components, with weighted F1 scores of 0.94 for P waves and 0.89 for QRS complexes. Qualitative review showed good alignment with reference beats and differences in beat selection, adjacent beat handling, and QRS identification. Downstream classification performance was equivalent to Marquette 12SL medians but statistically superior to Uni-G medians for 7\/10 diagnostic labels.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study demonstrates a robust, clinically applicable, vendor- and lead-agnostic deep learning model for ECG analysis, encompassing waveform delineation, rhythm classification, and median beat construction.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/ehjdh\/ztag122","type":"journal-article","created":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T11:56:18Z","timestamp":1785412578000},"source":"Crossref","is-referenced-by-count":0,"title":["Explainable electrocardiogram interpretation using deep learning\u2013based semantic segmentation"],"prefix":"10.1093","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7494-4542","authenticated-orcid":false,"given":"Bauke K O","family":"Arends","sequence":"first","affiliation":[{"name":"Department of Cardiology, University Medical Center Utrecht , Internal ref E03.511, Heidelberglaan 100, Utrecht 3584 CX ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0291-7940","authenticated-orcid":false,"given":"Bas B S","family":"Schots","sequence":"additional","affiliation":[{"name":"Department of Cardiology, University Medical Center Utrecht , Internal ref E03.511, Heidelberglaan 100, Utrecht 3584 CX ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Parmenion","family":"Koutsogeorgos","sequence":"additional","affiliation":[{"name":"Cordys Analytics B.V. , Utrecht ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2952-4849","authenticated-orcid":false,"given":"Timo","family":"Nijkamp","sequence":"additional","affiliation":[{"name":"Department of Cardiology, University Medical Center Utrecht , Internal ref E03.511, Heidelberglaan 100, Utrecht 3584 CX ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tim M","family":"Paquaij","sequence":"additional","affiliation":[{"name":"Department of Cardiology, University Medical Center Utrecht , Internal ref E03.511, Heidelberglaan 100, Utrecht 3584 CX ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4205-1255","authenticated-orcid":false,"given":"Diantha J M","family":"Schipaanboord","sequence":"additional","affiliation":[{"name":"Department of Cardiology, University Medical Center Utrecht , Internal ref E03.511, Heidelberglaan 100, Utrecht 3584 CX ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0237-7867","authenticated-orcid":false,"given":"Rutger J","family":"Hassink","sequence":"additional","affiliation":[{"name":"Department of Cardiology, University Medical Center Utrecht , Internal ref E03.511, Heidelberglaan 100, Utrecht 3584 CX ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2713-686X","authenticated-orcid":false,"given":"Pim","family":"van der Harst","sequence":"additional","affiliation":[{"name":"Department of Cardiology, University Medical Center Utrecht , Internal ref E03.511, Heidelberglaan 100, Utrecht 3584 CX ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9950-4388","authenticated-orcid":false,"given":"Ren\u00e9","family":"van Es","sequence":"additional","affiliation":[{"name":"Department of Cardiology, University Medical Center Utrecht , Internal ref E03.511, Heidelberglaan 100, Utrecht 3584 CX ,","place":["The Netherlands"]},{"name":"Cordys Analytics B.V. , Utrecht ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4779-5870","authenticated-orcid":false,"given":"Rutger R","family":"van de Leur","sequence":"additional","affiliation":[{"name":"Department of Cardiology, University Medical Center Utrecht , Internal ref E03.511, Heidelberglaan 100, Utrecht 3584 CX ,","place":["The Netherlands"]},{"name":"Cordys Analytics B.V. , Utrecht ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"2026083110263769700_ztag122-B1","doi-asserted-by":"crossref","first-page":"1341786","DOI":"10.3389\/fcvm.2024.1341786","article-title":"Generalising electrocardiogram detection and delineation: training convolutional neural networks with synthetic data augmentation","volume":"11","author":"Jimenez-Perez","year":"2024","journal-title":"Front Cardiovasc Med"},{"key":"2026083110263769700_ztag122-B2","doi-asserted-by":"crossref","first-page":"101924","DOI":"10.1016\/j.cpcardiol.2023.101924","article-title":"ECG interpretation proficiency of healthcare professionals","volume":"48","author":"Kashou","year":"2023","journal-title":"Curr Probl Cardiol"},{"key":"2026083110263769700_ztag122-B3","doi-asserted-by":"crossref","first-page":"1461","DOI":"10.1001\/jamainternmed.2020.3989","article-title":"Accuracy of physicians\u2019 electrocardiogram interpretations: a systematic review and meta-analysis","volume":"180","author":"Cook","year":"2020","journal-title":"JAMA Intern Med"},{"key":"2026083110263769700_ztag122-B4","doi-asserted-by":"crossref","first-page":"1183","DOI":"10.1016\/j.jacc.2017.07.723","article-title":"Computer-interpreted electrocardiograms","volume":"70","author":"Schl\u00e4pfer","year":"2017","journal-title":"J Am Coll Cardiol"},{"key":"2026083110263769700_ztag122-B5","first-page":"246","volume-title":"International Conference on Neuroinformatics","author":"Moskalenko","year":"2020"},{"key":"2026083110263769700_ztag122-B6","first-page":"1","article-title":"A deep learning based ECG segmentation tool for detection of ECG beat parameters","author":"Haleem","year":"2022","journal-title":"2022 IEEE Symp Comput Commun (ISCC)"},{"key":"2026083110263769700_ztag122-B7","first-page":"63","article-title":"Benchmarking ECG delineation using deep neural network-based semantic segmentation models","volume":"287","author":"Park","year":"2025","journal-title":"Proc Mach Learn Res"},{"key":"2026083110263769700_ztag122-B8","first-page":"1","article-title":"Long-term ECG analysis through image conversion and deep learning","volume":"50","author":"Hern\u00e1ndez-Fern\u00e1ndez","year":"2023","journal-title":"Comput Cardiol"},{"key":"2026083110263769700_ztag122-B9","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0303178","article-title":"Deep learning based ECG segmentation for delineation of diverse arrhythmias. Hammad M, ed","volume":"19","author":"Joung","year":"2024","journal-title":"PLoS One"},{"key":"2026083110263769700_ztag122-B10","doi-asserted-by":"crossref","first-page":"104106","DOI":"10.1016\/j.bspc.2022.104106","article-title":"Post-processing refined ECG delineation based on 1D-UNet","volume":"79","author":"Chen","year":"2023","journal-title":"Biomed Signal Process Control"},{"key":"2026083110263769700_ztag122-B11","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1186\/s12911-023-02233-0","article-title":"Improved delineation model of a standard 12-lead electrocardiogram based on a deep learning algorithm","volume":"23","author":"Darmawahyuni","year":"2023","journal-title":"BMC Med Inform Decis Mak"},{"key":"2026083110263769700_ztag122-B12","doi-asserted-by":"crossref","first-page":"11039","DOI":"10.1038\/s41598-023-37773-y","article-title":"Beat-wise segmentation of electrocardiogram using adaptive windowing and deep neural network","volume":"13","author":"Niroshana","year":"2023","journal-title":"Sci Rep"},{"key":"2026083110263769700_ztag122-B13","doi-asserted-by":"crossref","first-page":"13736","DOI":"10.1038\/s41598-023-40965-1","article-title":"Robust electrocardiogram delineation model for automatic morphological abnormality interpretation","volume":"13","author":"Nurmaini","year":"2023","journal-title":"Sci Rep"},{"key":"2026083110263769700_ztag122-B14","first-page":"673","article-title":"A database for evaluation of algorithms for measurement of QT and other waveform intervals in the ECG","volume":"24","author":"Laguna","year":"1997","journal-title":"Comput Cardiol"},{"key":"2026083110263769700_ztag122-B15","doi-asserted-by":"crossref","first-page":"186181","DOI":"10.1109\/ACCESS.2020.3029211","article-title":"LUDB: a new open-access validation tool for electrocardiogram delineation algorithms","volume":"8","author":"Kalyakulina","year":"2020","journal-title":"IEEE Access"},{"key":"2026083110263769700_ztag122-B16","doi-asserted-by":"crossref","first-page":"e015138","DOI":"10.1161\/JAHA.119.015138","article-title":"Automatic triage of 12-lead ECGs using deep convolutional neural networks","volume":"9","author":"Van De Leur","year":"2020","journal-title":"J Am Heart Assoc"},{"key":"2026083110263769700_ztag122-B17","first-page":"833","volume-title":"Lecture Notes in Computer Science","author":"Chen","year":"2018"},{"key":"2026083110263769700_ztag122-B18","article-title":"An improved Deeplabv3 + semantic segmentation algorithm with multiple loss constraints. Zhang Q, ed","volume":"17","author":"Wang","year":"2022","journal-title":"PLoS One"},{"key":"2026083110263769700_ztag122-B19","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1038\/s41597-023-02153-8","article-title":"PTB-XL+, a comprehensive electrocardiographic feature dataset","volume":"10","author":"Strodthoff","year":"2023","journal-title":"Sci Data"},{"key":"2026083110263769700_ztag122-B20","doi-asserted-by":"crossref","first-page":"102632","DOI":"10.1016\/j.artmed.2023.102632","article-title":"Generative adversarial networks in electrocardiogram synthesis: recent developments and challenges","volume":"143","author":"Berger","year":"2023","journal-title":"Artif Intell Med"},{"key":"2026083110263769700_ztag122-B21","doi-asserted-by":"crossref","first-page":"e0184352","DOI":"10.1371\/journal.pone.0184352","article-title":"The development and validation of an easy to use automatic QT-interval algorithm. Baumert M, ed","volume":"12","author":"Hermans","year":"2017","journal-title":"PLoS One"},{"key":"2026083110263769700_ztag122-B22","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1016\/j.jelectrocard.2009.01.003","article-title":"Intra- and interreader variability in QT interval measurement by tangent and threshold methods in a central electrocardiogram laboratory","volume":"42","author":"Panicker","year":"2009","journal-title":"J Electrocardiol"},{"key":"2026083110263769700_ztag122-B23","doi-asserted-by":"crossref","DOI":"10.1111\/anec.12621","article-title":"Reproducibility of measuring QRS duration and implications for optimization of interventricular pacing delay in cardiac resynchronization therapy","volume":"24","author":"Stephansen","year":"2019","journal-title":"Ann Noninvasive Electrocardiol"},{"key":"2026083110263769700_ztag122-B24","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1038\/s41591-018-0268-3","article-title":"Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network","volume":"25","author":"Hannun","year":"2019","journal-title":"Nat Med"},{"key":"2026083110263769700_ztag122-B25","doi-asserted-by":"crossref","first-page":"124003","DOI":"10.1088\/1361-6579\/abc960","article-title":"Classi\ufb01cation of 12-lead ECGs: the PhysioNet\/computing in cardiology challenge 2020","volume":"41","author":"Alday","journal-title":"Physiol Meas"}],"container-title":["European Heart Journal - Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/ehjdh\/advance-article-pdf\/doi\/10.1093\/ehjdh\/ztag122\/70412051\/ztag122.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ehjdh\/article-pdf\/7\/7\/ztag122\/70412051\/ztag122.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ehjdh\/article-pdf\/7\/7\/ztag122\/70412051\/ztag122.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T14:26:49Z","timestamp":1788186409000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ehjdh\/article\/doi\/10.1093\/ehjdh\/ztag122\/8748432"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,29]]},"references-count":25,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7,29]]}},"URL":"https:\/\/doi.org\/10.1093\/ehjdh\/ztag122","relation":{},"ISSN":["2634-3916"],"issn-type":[{"value":"2634-3916","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,8]]},"published":{"date-parts":[[2026,7,29]]},"article-number":"ztag122"}}