{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T19:47:56Z","timestamp":1777060076309,"version":"3.51.4"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T00:00:00Z","timestamp":1776729600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100020098","name":"Innovative Health Initiative","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100020098","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009708","name":"Novo Nordisk Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009708","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006823","name":"Boston Children's Hospital","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006823","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008276","name":"Shipowner Per Henriksen R and Wife Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008276","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Biomedical Signal Processing and Control"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.bspc.2026.110424","type":"journal-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T16:19:26Z","timestamp":1777047566000},"page":"110424","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Pooling cohorts for deep learning analysis: a potential source of bias for electrocardiogram analysis"],"prefix":"10.1016","volume":"122","author":[{"given":"Marie","family":"M\u00f8rch-Pedersen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1227-5113","authenticated-orcid":false,"given":"Malene","family":"N\u00f8rregaard","sequence":"additional","affiliation":[]},{"given":"Claus","family":"Graff","sequence":"additional","affiliation":[]},{"given":"Oliver B.","family":"Vad","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8284-1844","authenticated-orcid":false,"given":"Pia R.","family":"Lundegaard","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8466-8515","authenticated-orcid":false,"given":"Jesper Hastrup","family":"Svendsen","sequence":"additional","affiliation":[]},{"given":"Torben","family":"Hansen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0994-0184","authenticated-orcid":false,"given":"Allan","family":"Linneberg","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1217-8944","authenticated-orcid":false,"given":"Peter G.","family":"J\u00f8rgensen","sequence":"additional","affiliation":[]},{"given":"Magnus T.","family":"Jensen","sequence":"additional","affiliation":[]},{"given":"Peter","family":"Rossing","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3088-4375","authenticated-orcid":false,"given":"Christina","family":"Ellervik","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4893-0824","authenticated-orcid":false,"given":"Dominik","family":"Linz","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6026-0929","authenticated-orcid":false,"given":"Vajira","family":"Thambawita","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7012-3853","authenticated-orcid":false,"given":"Mary M.","family":"Maleckar","sequence":"additional","affiliation":[]},{"given":"Michael A.","family":"Riegler","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3267-4910","authenticated-orcid":false,"given":"J\u00f8rgen K.","family":"Kanters","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3227-1131","authenticated-orcid":false,"given":"Jonas L.","family":"Isaksen","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.bspc.2026.110424_b0005","doi-asserted-by":"crossref","first-page":"8363","DOI":"10.1038\/s41598-023-35557-y","article-title":"Embracing cohort heterogeneity in clinical machine learning development: a step toward generalizable models","volume":"13","author":"Schinkel","year":"2023","journal-title":"Sci. Rep."},{"key":"10.1016\/j.bspc.2026.110424_b0010","doi-asserted-by":"crossref","unstructured":"A. Torralba, A.A. Efros, Unbiased look at dataset bias, in: CVPR 2011, IEEE, 2011: pp. 1521\u20131528. doi:10.1109\/CVPR.2011.5995347.","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"10.1016\/j.bspc.2026.110424_b0015","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1002683","article-title":"Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study","volume":"15","author":"Zech","year":"2018","journal-title":"PLoS Med."},{"key":"10.1016\/j.bspc.2026.110424_b0020","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1001\/jamacardio.2022.0183","article-title":"Assessment of artificial intelligence in echocardiography diagnostics in differentiating takotsubo syndrome from myocardial infarction","volume":"7","author":"Laumer","year":"2022","journal-title":"JAMA Cardiol."},{"key":"10.1016\/j.bspc.2026.110424_b0025","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1080\/07853890.2022.2160008","article-title":"Feasibility of machine learning-based modeling and prediction using multiple centers data to assess intrahepatic cholangiocarcinoma outcomes","volume":"55","author":"Zhou","year":"2023","journal-title":"Ann. Med."},{"key":"10.1016\/j.bspc.2026.110424_b0030","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1186\/s40001-024-01756-0","article-title":"Predicting sepsis in-hospital mortality with machine learning: a multi-center study using clinical and inflammatory biomarkers","volume":"29","author":"Zhang","year":"2024","journal-title":"Eur. J. Med. Res."},{"key":"10.1016\/j.bspc.2026.110424_b0035","unstructured":"IEC, Medical electrical equipment - part 2-25: particular requirements for the basic safety and essential performance of electrocardiographs. (Cardiovascular), 2011."},{"key":"10.1016\/j.bspc.2026.110424_b0040","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ahj.2018.02.014","article-title":"Comparison of automated interval measurements by widely used algorithms in digital electrocardiographs","volume":"200","author":"Kligfield","year":"2018","journal-title":"Am. Heart J."},{"key":"10.1016\/j.bspc.2026.110424_b0045","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":"10.1016\/j.bspc.2026.110424_b0050","first-page":"A4693","article-title":"Gesus: study design, participation and characteristics of the danish general suburban population study","volume":"60","author":"Bergholdt","year":"2013","journal-title":"Dan. Med. J."},{"key":"10.1016\/j.bspc.2026.110424_b0055","first-page":"377","article-title":"Int99: a randomized non-pharmacological intervention study for prevention of ischaemic heart disease: baseline results Inter99","volume":"10","author":"J\u00f8rgensen","year":"2003","journal-title":"Eur. J. Cardiovasc. Prev. Rehabil. off. J. Eur. Soc. Cardiol. Work. Groups Epidemiol. Prev. Card. Rehabil. Exerc. Physiol."},{"key":"10.1016\/j.bspc.2026.110424_b0060","doi-asserted-by":"crossref","unstructured":"L.J. Palmer, UK Biobank: bank on it, The Lancet 369 (2007) 1980\u20131982. doi:10.1016\/S0140-6736(07)60924-6.","DOI":"10.1016\/S0140-6736(07)60924-6"},{"key":"10.1016\/j.bspc.2026.110424_b0065","unstructured":"UK Biobank, ECG protocol: Resource 510, (n.d.). https:\/\/biobank.ndph.ox.ac.uk\/ukb\/refer.cgi?id=510 (accessed May 25, 2024)."},{"key":"10.1016\/j.bspc.2026.110424_b0070","doi-asserted-by":"crossref","first-page":"672","DOI":"10.1007\/s00125-014-3164-5","article-title":"Prevalence of systolic and diastolic dysfunction in patients with type 1 diabetes without known heart disease: the Thousand & 1 Study","volume":"57","author":"Jensen","year":"2014","journal-title":"Diabetologia"},{"key":"10.1016\/j.bspc.2026.110424_b0075","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1177\/1479164116645583","article-title":"Thousand&2: abnormal echocardiography in patients with type 2 diabetes and relation to symptoms and clinical characteristics","volume":"13","author":"J\u00f8rgensen","year":"2016","journal-title":"Diab. Vasc. Dis. Res."},{"key":"10.1016\/j.bspc.2026.110424_b0080","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1016\/S2221-6189(14)60065-2","article-title":"Time-critical AMI Detection: a novel and fast technique using the 12-lead ECG","volume":"3","author":"Lateef","year":"2014","journal-title":"J. Acute Dis."},{"key":"10.1016\/j.bspc.2026.110424_b0085","doi-asserted-by":"crossref","first-page":"86","DOI":"10.17691\/stm2020.12.1.11","article-title":"High-Frequency ECG for detection of myocardial ischemia associated with right coronary artery stenosis in IHD patients","volume":"12","author":"Kolosova","year":"2020","journal-title":"Sovrem. Tekhnologii V Meditsine"},{"key":"10.1016\/j.bspc.2026.110424_b0090","doi-asserted-by":"crossref","first-page":"1337","DOI":"10.1111\/dme.13689","article-title":"Cardiac repolarization and depolarization in people with Type 1 diabetes with normal ejection fraction and without known heart disease: a case-control study","volume":"35","author":"Isaksen","year":"2018","journal-title":"Diabet Med."},{"key":"10.1016\/j.bspc.2026.110424_b0095","doi-asserted-by":"crossref","unstructured":"J.L. Isaksen, C. Graff, C. Ellervik, J.S. Jensen, H.U. Andersen, P. Rossing, J.K. Kanters, M.T. Jensen, Type 1 diabetes is associated with T-wave morphology changes. The Thousand & 1 Study, J Electrocardiol 51 (2018) S72\u2013S77. doi:10.1016\/j.jelectrocard.2018.05.015.","DOI":"10.1016\/j.jelectrocard.2018.05.015"},{"key":"10.1016\/j.bspc.2026.110424_b0100","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.jelectrocard.2024.04.003","article-title":"Electrocardiographic markers in patients with type 2 diabetes and the role of diabetes duration","volume":"84","author":"Isaksen","year":"2024","journal-title":"J. Electrocardiol."},{"key":"10.1016\/j.bspc.2026.110424_b0105","doi-asserted-by":"crossref","first-page":"10949","DOI":"10.1038\/s41598-021-90285-5","article-title":"Explaining deep neural networks for knowledge discovery in electrocardiogram analysis","volume":"11","author":"Hicks","year":"2021","journal-title":"Sci. Rep."},{"key":"10.1016\/j.bspc.2026.110424_b0110","doi-asserted-by":"crossref","DOI":"10.1161\/CIRCEP.119.007284","article-title":"Age and sex estimation using artificial intelligence from standard 12-Lead ECGs","volume":"12","author":"Attia","year":"2019","journal-title":"Circ Arrhythm Electrophysiol"},{"key":"10.1016\/j.bspc.2026.110424_b0115","series-title":"Choosing the Right Classifiers and Performance Metrics for Brain Decoding with Imbalanced Data, NeuroImage 277","article-title":"Class imbalance should not throw you off balance","author":"Th\u00f6lke","year":"2023"},{"key":"10.1016\/j.bspc.2026.110424_b0120","doi-asserted-by":"crossref","first-page":"5979","DOI":"10.1038\/s41598-022-09954-8","article-title":"On evaluation metrics for medical applications of artificial intelligence","volume":"12","author":"Hicks","year":"2022","journal-title":"Sci. Rep."},{"key":"10.1016\/j.bspc.2026.110424_b0125","doi-asserted-by":"crossref","first-page":"H1798","DOI":"10.1152\/ajpheart.00577.2013","article-title":"QT\/RR curvatures in healthy subjects: sex differences and covariates","volume":"305","author":"Malik","year":"2013","journal-title":"Am. J. Physiol. Heart Circ. Physiol."},{"key":"10.1016\/j.bspc.2026.110424_b0130","doi-asserted-by":"crossref","first-page":"65","DOI":"10.3390\/jpm4010065","article-title":"Predicting \u201cheart age\u201d using electrocardiography","volume":"4","author":"Ball","year":"2014","journal-title":"J. Pers. Med."},{"key":"10.1016\/j.bspc.2026.110424_b0135","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1159\/000006892","article-title":"Influence of body composition on electrocardiographic identification of left ventricular hypertrophy in adolescents","volume":"91","author":"Sugita","year":"1999","journal-title":"Cardiology"},{"key":"10.1016\/j.bspc.2026.110424_b0140","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/s40292-022-00504-x","article-title":"Stage 2 hypertension and electrocardiogram abnormality: evaluating the risk factors of cardiovascular diseases in Nigeria","volume":"29","author":"Chinedu","year":"2022","journal-title":"High Blood Press. Cardiovasc. Prev."},{"key":"10.1016\/j.bspc.2026.110424_b0145","doi-asserted-by":"crossref","DOI":"10.1088\/1361-6579\/ac34ea","article-title":"Two-stage ECG signal denoising based on deep convolutional network","volume":"42","author":"Qiu","year":"2021","journal-title":"Physiol. Meas."},{"key":"10.1016\/j.bspc.2026.110424_b0150","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1016\/0002-8703(68)90138-5","article-title":"Skin-electrode impedance problems in electrocardiography","volume":"76","author":"Berson","year":"1968","journal-title":"Am. Heart J."},{"key":"10.1016\/j.bspc.2026.110424_b0155","doi-asserted-by":"crossref","first-page":"e9","DOI":"10.1016\/j.amjmed.2011.12.024","article-title":"Negative P wave in V1 Is the key to identifying high placement of V1-V2 electrodes in nonpathological subjects","volume":"125","author":"Garc\u00eda-Niebla","year":"2012","journal-title":"Am. J. Med."},{"key":"10.1016\/j.bspc.2026.110424_b0160","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1111\/j.1742-6723.2007.01004.x","article-title":"Accuracy of ECG electrode placement by emergency department clinicians","volume":"19","author":"McCann","year":"2007","journal-title":"Emerg. Med. Australas."},{"key":"10.1016\/j.bspc.2026.110424_b0165","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.amjmed.2011.04.023","article-title":"Importance of recognizing pseudo-septal infarction due to electrocardiographic lead misplacement","volume":"125","author":"Ilg","year":"2012","journal-title":"Am. J. Med."},{"key":"10.1016\/j.bspc.2026.110424_b0170","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.jelectrocard.2019.01.088","article-title":"Common source of miscalculation and misclassification of P-wave negativity and P-wave terminal force in lead V1","volume":"53","author":"Rasmussen","year":"2019","journal-title":"J Electrocardiol"},{"key":"10.1016\/j.bspc.2026.110424_b0175","article-title":"Practical MATLAB deep learning: a projects-based approach","author":"Paluszek","year":"2022","journal-title":"Apress Media LLC"},{"key":"10.1016\/j.bspc.2026.110424_b0180","doi-asserted-by":"crossref","first-page":"1179","DOI":"10.1093\/europace\/euaa377","article-title":"Deep learning and the electrocardiogram: review of the current state-of-the-art","volume":"23","author":"Somani","year":"2021","journal-title":"Europace"},{"key":"10.1016\/j.bspc.2026.110424_b0185","doi-asserted-by":"crossref","unstructured":"N. L, C. C, L. H, Z. S, S. M, A Deep-Learning Approach to ECG Classification Based on Adversarial Domain Adaptation, Healthc. Basel Switz. 8 (2020). doi:10.3390\/healthcare8040437.","DOI":"10.3390\/healthcare8040437"},{"key":"10.1016\/j.bspc.2026.110424_b0190","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.adp6040","article-title":"Domain adaptation in small-scale and heterogeneous biological datasets","volume":"10","author":"Orouji","year":"2024","journal-title":"Sci. Adv."},{"key":"10.1016\/j.bspc.2026.110424_b0195","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1038\/s41746-023-00805-y","article-title":"An adversarial training framework for mitigating algorithmic biases in clinical machine learning","volume":"6","author":"Yang","year":"2023","journal-title":"NPJ Digit. Med."},{"key":"10.1016\/j.bspc.2026.110424_b0200","unstructured":"Z. Pan, E. Andrews, L. Chang, P. Mishra, Privacy-Preserving Debiasing using Data Augmentation and Machine Unlearning, (2024). doi:10.48550\/arXiv.2404.13194."},{"key":"10.1016\/j.bspc.2026.110424_b0205","unstructured":"Center for Devices and Radiological Health, Use of Real-World Evidence to Support Regulatory Decision-Making for Medical Devices. Guidance for Industry and Food and Drug Administration Staff, (2017). https:\/\/www.fda.gov\/regulatory-information\/search-fda-guidance-documents\/use-real-world-evidence-support-regulatory-decision-making-medical-devices (accessed December 5, 2024)."},{"key":"10.1016\/j.bspc.2026.110424_b0210","unstructured":"Center for Devices and Radiological Health, Marketing Submission Recommendations for a Predetermined Change Control Plan for Artificial Intelligence-Enabled Device Software Functions, (2024). https:\/\/www.fda.gov\/regulatory-information\/search-fda-guidance-documents\/marketing-submission-recommendations-predetermined-change-control-plan-artificial-intelligence (accessed December 5, 2024)."},{"key":"10.1016\/j.bspc.2026.110424_b0215","unstructured":"Center for Devices and Radiological Health, Good Machine Learning Practice for Medical Device Development: Guiding Principles, (2023). https:\/\/www.fda.gov\/medical-devices\/software-medical-device-samd\/good-machine-learning-practice-medical-device-development-guiding-principles (accessed December 5, 2024)."},{"key":"10.1016\/j.bspc.2026.110424_b0220","unstructured":"Center for Devices and Radiological Health, Transparency for Machine Learning-Enabled Medical Devices: Guiding Principles, (2024). https:\/\/www.fda.gov\/medical-devices\/software-medical-device-samd\/transparency-machine-learning-enabled-medical-devices-guiding-principles (accessed December 5, 2024)."},{"key":"10.1016\/j.bspc.2026.110424_b0225","article-title":"Evaluating artificial intelligence-enabled medical tests in cardiology: best practice","volume":"60","author":"Isaksen","year":"2025","journal-title":"IJC Heart Vasc."}],"container-title":["Biomedical Signal Processing and Control"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S174680942600978X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S174680942600978X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T19:18:10Z","timestamp":1777058290000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S174680942600978X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":45,"alternative-id":["S174680942600978X"],"URL":"https:\/\/doi.org\/10.1016\/j.bspc.2026.110424","relation":{},"ISSN":["1746-8094"],"issn-type":[{"value":"1746-8094","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Pooling cohorts for deep learning analysis: a potential source of bias for electrocardiogram analysis","name":"articletitle","label":"Article Title"},{"value":"Biomedical Signal Processing and Control","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.bspc.2026.110424","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"110424"}}