{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T11:32:26Z","timestamp":1785929546314,"version":"3.56.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100013263","name":"Nasjonalforeningen for Folkehelsen","doi-asserted-by":"publisher","award":["#29038"],"award-info":[{"award-number":["#29038"]}],"id":[{"id":"10.13039\/501100013263","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021697","name":"Vestfold Hospital Trust","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100021697","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cardiovasc Eng Tech"],"published-print":{"date-parts":[[2025,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>Background<\/jats:title>\n            <jats:p>The electrocardiogram (ECG) is an almost universally accessible diagnostic tool for heart disease. An ECG is measured by using an electrocardiograph, and today\u2019s electrocardiographs use built-in software to interpret the ECGs automatically after they are recorded. However, these algorithms exhibit limited performance, and therefore, clinicians usually have to manually interpret the ECG, regardless of whether an algorithm has interpreted it or not. Manual interpretation of the ECG can be time-consuming and requires specific skills. Therefore, better algorithms are clearly needed to make correct ECG interpretations more accessible and time-efficient. Algorithms based on artificial intelligence (AI) have demonstrated promising performance in various fields, including ECG interpretation, over the past few years and may represent an alternative to manual ECG interpretation by doctors.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>We trained and validated a convolutional neural network with an Inception architecture on a dataset with 88253 12-lead ECGs, and classified 30 of the most frequent annotated cardiac conditions in the dataset. We assessed two different loss functions and different ECG sampling rates and the best-performing model used double soft F1-loss and ECGs downsampled to 75Hz. This model achieved an F1-score of <jats:inline-formula>\n                <jats:alternatives>\n                  <jats:tex-math>$$0.420\\pm 0.017$$<\/jats:tex-math>\n                  <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                    <mml:mrow>\n                      <mml:mn>0.420<\/mml:mn>\n                      <mml:mo>\u00b1<\/mml:mo>\n                      <mml:mn>0.017<\/mml:mn>\n                    <\/mml:mrow>\n                  <\/mml:math>\n                <\/jats:alternatives>\n              <\/jats:inline-formula>, accuracy <jats:inline-formula>\n                <jats:alternatives>\n                  <jats:tex-math>$$= 0.954 \\pm 0.002$$<\/jats:tex-math>\n                  <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                    <mml:mrow>\n                      <mml:mo>=<\/mml:mo>\n                      <mml:mn>0.954<\/mml:mn>\n                      <mml:mo>\u00b1<\/mml:mo>\n                      <mml:mn>0.002<\/mml:mn>\n                    <\/mml:mrow>\n                  <\/mml:math>\n                <\/jats:alternatives>\n              <\/jats:inline-formula>, and an AUROC score of <jats:inline-formula>\n                <jats:alternatives>\n                  <jats:tex-math>$$0.832 \\pm 0.019$$<\/jats:tex-math>\n                  <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                    <mml:mrow>\n                      <mml:mn>0.832<\/mml:mn>\n                      <mml:mo>\u00b1<\/mml:mo>\n                      <mml:mn>0.019<\/mml:mn>\n                    <\/mml:mrow>\n                  <\/mml:math>\n                <\/jats:alternatives>\n              <\/jats:inline-formula>. An aggregated saliency map, showing the global importance of all 12 ECG leads for the 30 cardiac conditions, was generated using Local Interpretable Model-Agnostic Explanations (LIME). The global saliency map showed that the Inception model paid the most attention to the limb leads and the augmented leads and less importance to the precordial leads.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusions<\/jats:title>\n            <jats:p>One of the more significant contributions that emerge from this study is the use of aggregated saliency maps to obtain global\u00a0ECG lead importance for different cardiac conditions. In addition, we emphasized the relevance of evaluating different loss functions, and in this specific case, we found double soft F1-loss to be slightly better than binary cross-entropy (BCE). Finally, we found it somewhat surprising that drastic\u00a0downsampling of\u00a0the ECG led to higher performance than higher sampling frequencies, such as\u00a0500Hz. These findings contribute in several ways to our understanding of the artificial intelligence-based interpretation of ECGs, but further studies should be carried out to validate these findings in other datasets from other patient cohorts.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1007\/s13239-025-00797-8","type":"journal-article","created":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T13:23:55Z","timestamp":1758115435000},"page":"599-610","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Assessing the Impact of Downsampled ECGs and Alternative Loss Functions in Multi-Label Classification of 12-Lead ECGs"],"prefix":"10.1007","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4055-4297","authenticated-orcid":false,"given":"Bj\u00f8rn-Jostein","family":"Singstad","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eraraya Morenzo","family":"Muten","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"key":"797_CR1","unstructured":"WHO Cardiovascular Diseases (CVDs). https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/cardiovascular-diseases-(cvds)"},{"issue":"1","key":"797_CR2","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1023\/A:1023667812925","volume":"7","author":"SS Barold","year":"2003","unstructured":"Barold, S. S. Willem Einthoven and the birth of clinical electrocardiography a hundred years ago. Card. Electrophysiol. Rev. 7(1):99\u2013104, 2003. https:\/\/doi.org\/10.1023\/A:1023667812925.","journal-title":"Card. Electrophysiol. Rev."},{"issue":"3","key":"797_CR3","doi-asserted-by":"publisher","first-page":"123","DOI":"10.12968\/bjca.2019.14.3.123","volume":"14","author":"M Bickerton","year":"2019","unstructured":"Bickerton, M., and A. Pooler. Misplaced ECG electrodes and the need for continuing training. Br. J. Cardiac Nursing. 14(3):123\u2013132, 2019. https:\/\/doi.org\/10.12968\/bjca.2019.14.3.123.","journal-title":"Br. J. Cardiac Nursing"},{"issue":"2","key":"797_CR4","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.amjmed.2018.08.025","volume":"132","author":"H Smulyan","year":"2019","unstructured":"Smulyan, H. The computerized ECG: friend and foe. Am. J. Med. 132(2):153\u2013160, 2019. https:\/\/doi.org\/10.1016\/j.amjmed.2018.08.025.","journal-title":"Am. J. Med."},{"issue":"9","key":"797_CR5","doi-asserted-by":"publisher","first-page":"1183","DOI":"10.1016\/j.jacc.2017.07.723","volume":"70","author":"J Schl\u00e4pfer","year":"2017","unstructured":"Schl\u00e4pfer, J., and H. J. Wellens. Computer-interpreted electrocardiograms. J. Am. Coll. Cardiol. 70(9):1183\u20131192, 2017. https:\/\/doi.org\/10.1016\/j.jacc.2017.07.723.","journal-title":"J. Am. Coll. Cardiol."},{"issue":"4","key":"797_CR6","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1007\/s10618-019-00619-1","volume":"33","author":"HI Fawaz","year":"2019","unstructured":"Fawaz, H. I., G. Forestier, J. Weber, et al. Deep learning for time series classification: a review. Data Min. Knowl. Disc. 33(4):917\u2013963, 2019. https:\/\/doi.org\/10.1007\/s10618-019-00619-1.","journal-title":"Data Min. Knowl. Disc."},{"key":"797_CR7","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-15432-4","author":"AH Ribeiro","year":"2020","unstructured":"Ribeiro, A. H., M. H. Ribeiro, G. M. M. Paix\u00e3o, et al. Automatic diagnosis of the 12-lead ECG using a deep neural network. Nature Commun. 2020. https:\/\/doi.org\/10.1038\/s41467-020-15432-4.","journal-title":"Nature Commun."},{"key":"797_CR8","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1016\/j.procs.2020.04.074","volume":"171","author":"JR Annam","year":"2020","unstructured":"Annam, J.R., Kalyanapu, S., Ch., S., et al. Classification of ECG heartbeat arrhythmia: A\u00a0review. Procedia Comput. Sci. 171:679\u2013688, 2020. https:\/\/doi.org\/10.1016\/j.procs.2020.04.074.","journal-title":"Procedia Comput. Sci."},{"key":"797_CR9","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1016\/j.inffus.2019.06.024","volume":"53","author":"Q Yao","year":"2020","unstructured":"Yao, Q., R. Wang, X. Fan, et al. Multi-class arrhythmia detection from 12-lead varied-length ECG using attention-based time-incremental convolutional neural network. Inform. Fusion. 53:174\u2013182, 2020. https:\/\/doi.org\/10.1016\/j.inffus.2019.06.024.","journal-title":"Inform. Fusion"},{"key":"797_CR10","doi-asserted-by":"publisher","DOI":"10.3390\/sym12111827","author":"D Li","year":"2020","unstructured":"Li, D., H. Wu, J. Zhao, et al. Automatic classification system of arrhythmias using 12-lead ECGs with a deep neural network based on an attention mechanism. Symmetry. 2020. https:\/\/doi.org\/10.3390\/sym12111827.","journal-title":"Symmetry"},{"key":"797_CR11","doi-asserted-by":"publisher","unstructured":"Chen, T.-M., C.-H. Huang, E. S. C. Shih, et al. Detection and classification of cardiac arrhythmias by a challenge-best deep learning neural network model. Iscience. 2020. https:\/\/doi.org\/10.1016\/j.isci.2020.100886.","DOI":"10.1016\/j.isci.2020.100886"},{"issue":"46","key":"797_CR12","doi-asserted-by":"publisher","first-page":"4717","DOI":"10.1093\/eurheartj\/ehab649","volume":"42","author":"ZI Attia","year":"2021","unstructured":"Attia, Z. I., D. M. Harmon, E. R. Behr, et al. Application of artificial intelligence to the electrocardiogram. Eur. Heart J. 42(46):4717\u20134730, 2021. https:\/\/doi.org\/10.1093\/eurheartj\/ehab649.","journal-title":"Eur. Heart J."},{"issue":"1","key":"797_CR13","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1038\/s41591-018-0268-3","volume":"25","author":"AY Hannun","year":"2019","unstructured":"Hannun, A. Y., P. Rajpurkar, M. Haghpanahi, et al. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat. Med. 25(1):65\u201369, 2019. https:\/\/doi.org\/10.1038\/s41591-018-0268-3.","journal-title":"Nat. Med."},{"issue":"7623","key":"797_CR14","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1038\/538020a","volume":"538","author":"D Castelvecchi","year":"2016","unstructured":"Castelvecchi, D. Can we open the black box of AI? Nature News. 538(7623):20, 2016. https:\/\/doi.org\/10.1038\/538020a.","journal-title":"Nature News"},{"issue":"1","key":"797_CR15","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/s11747-019-00710-5","volume":"48","author":"A Rai","year":"2020","unstructured":"Rai, A. Explainable AI: from black box to glass box. J. Acad. Mark. Sci. 48(1):137\u2013141, 2020. https:\/\/doi.org\/10.1007\/s11747-019-00710-5.","journal-title":"J. Acad. Mark. Sci."},{"key":"797_CR16","doi-asserted-by":"publisher","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., et al.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 618\u2013626. IEEE, New York City (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.74","DOI":"10.1109\/ICCV.2017.74"},{"key":"797_CR17","doi-asserted-by":"publisher","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: \"Why Should I Trust You?\": Explaining the Predictions of Any Classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery And Data Mining, pp. 1135\u20131144. ACM, San Francisco California USA (2016). https:\/\/doi.org\/10.1145\/2939672.2939778","DOI":"10.1145\/2939672.2939778"},{"key":"797_CR18","doi-asserted-by":"publisher","unstructured":"Lundberg, S.M., Lee, S.-I.: A unified approach to interpreting model predictions. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 4768\u20134777. Curran Associates Inc., Red Hook, NY, USA (2017). https:\/\/doi.org\/10.48550\/arXiv.1705.07874","DOI":"10.48550\/arXiv.1705.07874"},{"key":"797_CR19","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCEP.120.009056","author":"RR Van De Leur","year":"2021","unstructured":"Van De Leur, R. R., Taha, K. and Bos M. N., et al. Discovering and Visualizing Disease-Specific Electrocardiogram Features Using Deep Learning. Circulation: Arrhythmia and Electrophysiology. 2021. https:\/\/doi.org\/10.1161\/CIRCEP.120.009056","journal-title":"Circulation: Arrhythmia and Electrophysiology."},{"key":"797_CR20","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-90285-5","author":"SA Hicks","year":"2021","unstructured":"Hicks, S. A., J. L. Isaksen, V. Thambawita, et al. Explaining deep neural networks for knowledge discovery in electrocardiogram analysis. Sci. Rep. 2021. https:\/\/doi.org\/10.1038\/s41598-021-90285-5.","journal-title":"Sci. Rep."},{"key":"797_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2021.102373","author":"D Zhang","year":"2021","unstructured":"Zhang, D., S. Yang, X. Yuan, et al. Interpretable deep learning for automatic diagnosis of 12-lead electrocardiogram. iScience. 2021. https:\/\/doi.org\/10.1016\/j.isci.2021.102373.","journal-title":"iScience"},{"key":"797_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104393","author":"I Neves","year":"2021","unstructured":"Neves, I., D. Folgado, S. Santos, et al. Interpretable heartbeat classification using local model-agnostic explanations on ECGs. Comput. Biol. Med. 2021. https:\/\/doi.org\/10.1016\/j.compbiomed.2021.104393.","journal-title":"Comput. Biol. Med."},{"key":"797_CR23","doi-asserted-by":"publisher","DOI":"10.1109\/TEM.2021.3104751","author":"M Ganeshkumar","year":"2021","unstructured":"Ganeshkumar, M., R. Vinayakumar, V. Sowmya, et al. Explainable deep learning-based approach for multilabel classification of electrocardiogram. IEEE Trans. Eng. Manage. 2021. https:\/\/doi.org\/10.1109\/TEM.2021.3104751.","journal-title":"IEEE Trans. Eng. Manage."},{"key":"797_CR24","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6579\/ac6f40","author":"A Srivastava","year":"2022","unstructured":"Srivastava, A., S. Pratiher, S. Alam, et al. A deep residual inception network with channel attention modules for multi-label cardiac abnormality detection from reduced-lead ECG. Physiol. Meas. 2022. https:\/\/doi.org\/10.1088\/1361-6579\/ac6f40.","journal-title":"Physiol. Meas."},{"key":"797_CR25","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6579\/abc960","author":"EAP Alday","year":"2020","unstructured":"Alday, E. A. P., A. Gu, A. J. Shah, et al. Classification of 12-lead ECGs: the physionet\/computing in cardiology challenge 2020. Physiol. Meas. 2020. https:\/\/doi.org\/10.1088\/1361-6579\/abc960.","journal-title":"Physiol. Meas."},{"key":"797_CR26","doi-asserted-by":"publisher","unstructured":"Reyna, M.A., Sadr, N., Alday, E.A.P., et al.: Will two do? Varying dimensions in electrocardiography: the physionet\/computing in cardiology challenge 2021. In: 2021 computing in cardiology (CinC), 48:1\u20134 (2021). https:\/\/doi.org\/10.23919\/CinC53138.2021.9662687","DOI":"10.23919\/CinC53138.2021.9662687"},{"key":"797_CR27","doi-asserted-by":"publisher","unstructured":"Singstad, B.-J., Tronstad, C.: Convolutional neural network and rule-based algorithms for classifying 12-lead ECGs, pp. 1\u20134 (2020). https:\/\/doi.org\/10.22489\/CinC.2020.227","DOI":"10.22489\/CinC.2020.227"},{"key":"797_CR28","doi-asserted-by":"publisher","unstructured":"Singstad, B.-J., Muten, E. M., Brekke, P.H.: Multi-label ECG classification using convolutional neural networks in a classifier chain. Comput. Cardiol. (2021). https:\/\/doi.org\/10.23919\/CinC53138.2021.9662750","DOI":"10.23919\/CinC53138.2021.9662750"},{"issue":"7","key":"797_CR29","doi-asserted-by":"publisher","first-page":"1368","DOI":"10.1166\/jmihi.2018.2442","volume":"8","author":"L Feifei","year":"2018","unstructured":"Feifei, L., L. Chengyu, Z. Lina, et al. An open access database for evaluating the algorithms of electrocardiogram rhythm and morphology abnormality detection. J. Med. Imaging Health Inform. 8(7):1368\u20131373, 2018. https:\/\/doi.org\/10.1166\/jmihi.2018.2442.","journal-title":"J. Med. Imaging Health Inform."},{"key":"797_CR30","doi-asserted-by":"publisher","unstructured":"Tihonenko, V., Khaustov, A., Ivanov, S., et al.: St Petersburg INCART 12-lead arrhythmia database. PhysioBank PhysioToolkit PhysioNet, https:\/\/doi.org\/10.13026\/C2V88N (2008)","DOI":"10.13026\/C2V88N"},{"issue":"1","key":"797_CR31","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1038\/s41597-020-0495-6","volume":"7","author":"P Wagner","year":"2020","unstructured":"Wagner, P., N. Strodthoff, R. Bousseljot, et al. PTB-XL, a Large Publicly Available Electrocardiography Dataset. Sci. Data. 7(1):154, 2020. https:\/\/doi.org\/10.1038\/s41597-020-0495-6.","journal-title":"Sci. Data"},{"key":"797_CR32","doi-asserted-by":"publisher","DOI":"10.1515\/bmte.1995.40.s1.317","author":"R Bousseljot","year":"2009","unstructured":"Bousseljot, R., D. Kreiseler, and A. Schnabel. Nutzung der EKG-signaldatenbank cardiodat der PTB \u00fcber das internet. Biomedizinische Technik\/Biomed. Eng. 2009. https:\/\/doi.org\/10.1515\/bmte.1995.40.s1.317.","journal-title":"Biomedizinische Technik\/Biomed. Eng."},{"key":"797_CR33","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-59821-7","author":"J Zheng","year":"2020","unstructured":"Zheng, J., H. Chu, D. Struppa, et al. Optimal multi-stage arrhythmia classification approach. Sci Rep. 2020. https:\/\/doi.org\/10.1038\/s41598-020-59821-7.","journal-title":"Sci Rep"},{"key":"797_CR34","doi-asserted-by":"publisher","unstructured":"Szegedy, C., Wei, L., Yangqing, J., et al.: Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1\u20139. IEEE, Boston, MA, USA (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298594","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"797_CR35","unstructured":"Abadi, M., Agarwal, A., Barham, P., et al.: TensorFlow: large-scale machine learning on heterogeneous distributed systems. Preprint at arXiv:1603.04467 [cs] (2016)"},{"issue":"6088","key":"797_CR36","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart, D. E., G. E. Hinton, and R. J. Williams. Learning representations by back-propagating errors. Nature. 323(6088):533\u2013536, 1986. https:\/\/doi.org\/10.1038\/323533a0.","journal-title":"Nature"},{"key":"797_CR37","unstructured":"van Lohuizen, Q.: Training Deep Neural Networks with Soft Loss for Strong Gravitational Lens Detection. Master\u2019s thesis, University of Groningen"},{"key":"797_CR38","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. Preprint at http:\/\/arxiv.org\/abs\/1412.6980 (2015)"},{"key":"797_CR39","unstructured":"Habib, A., Karmakar, C., Yearwood, J.: Choosing a sampling frequency for ECG QRS detection using convolutional networks. Preprint at https:\/\/arxiv.org\/abs\/2007.02052 (2020)"},{"issue":"1","key":"797_CR40","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten, C., and T. M. Khoshgoftaar. A survey on image data augmentation for deep learning. J. Big Data. 6(1):60, 2019. https:\/\/doi.org\/10.1186\/s40537-019-0197-0.","journal-title":"J. Big Data"},{"issue":"11","key":"797_CR41","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1016\/S2589-7500(21)00208-9","volume":"3","author":"M Ghassemi","year":"2021","unstructured":"Ghassemi, M., L. Oakden-Rayner, and A. L. Beam. The false hope of current approaches to explainable artificial intelligence in health care. Lancet Digital Health. 3(11):745\u2013750, 2021. https:\/\/doi.org\/10.1016\/S2589-7500(21)00208-9.","journal-title":"Lancet Digital Health"}],"container-title":["Cardiovascular Engineering and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13239-025-00797-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13239-025-00797-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13239-025-00797-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T20:14:34Z","timestamp":1760559274000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13239-025-00797-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"references-count":41,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["797"],"URL":"https:\/\/doi.org\/10.1007\/s13239-025-00797-8","relation":{},"ISSN":["1869-408X","1869-4098"],"issn-type":[{"value":"1869-408X","type":"print"},{"value":"1869-4098","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,17]]},"assertion":[{"value":"20 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing or conflicting interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This study utilized ECG data sourced from seven publicly available open-access databases. As such, the analysis was conducted entirely on openly published and de-identified data, and ethical approval was not required. All datasets used were originally collected in accordance with relevant ethical guidelines and standards as reported by their respective curators.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}]}}