{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T05:55:35Z","timestamp":1790056535055,"version":"4.0.1"},"reference-count":20,"publisher":"BMJ","issue":"2","license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"unspecified","delay-in-days":28,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100017018","name":"Wallenberg Centre for Molecular and Translational Medicine","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100017018","id-type":"DOI","asserted-by":"crossref"}]},{"name":"ALF","award":["ALFGBG-998297"],"award-info":[{"award-number":["ALFGBG-998297"]}]},{"name":"Swedish Society for Medicine","award":["SLS-1000926"],"award-info":[{"award-number":["SLS-1000926"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Open Heart"],"accepted":{"date-parts":[[2024,10,11]]},"published-print":{"date-parts":[[2024,10]]},"abstract":"<jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Elevated troponin levels are a sensitive biomarker for cardiac injury. The quick and reliable prediction of troponin elevation for patients with chest pain from readily available ECGs may pose a valuable time-saving diagnostic tool during decision-making concerning this patient population.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods and results<\/jats:title>\n                  <jats:p>The data used included 15\u2009856 ECGs from patients presenting to the emergency rooms with chest pain or dyspnoea at two centres in Sweden from 2015 to June 2023. All patients had high-sensitivity troponin test results within 6 hours after 12-lead ECG. Both troponin I (TnI) and TnT were used, with biomarker-specific cut-offs and sex-specific cut-offs for TnI. On this dataset, a residual convolutional neural network (ResNet) was trained 10 times, each on a unique split of the data. The final model achieved an average area under the curve for the receiver operating characteristic curve of 0.7717 (95% CI\u00b10.0052), calibration curve analysis revealed a mean slope of 1.243 (95% CI\u00b10.075) and intercept of \u22120.073 (95% CI\u00b10.034), indicating a good correlation between prediction and ground truth. Post-classification, tuned for F1 score, accuracy was 71.43% (95% CI\u00b11.28), with an F1 score of 0.5642 (95% CI\u00b10.0052) and a negative predictive value of 0.8660 (95% CI\u00b10.0048), respectively. The ResNet displayed comparable or surpassing metrics to prior presented models.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>The model exhibited clinically meaningful performance, notably its high negative predictive accuracy. Therefore, clinical use of comparable neural networks in first-line, quick-response triage of patients with chest pain or dyspnoea appears as a valuable option in future medical practice.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1136\/openhrt-2024-002937","type":"journal-article","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T11:38:59Z","timestamp":1730288339000},"page":"e002937","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":7,"title":["Predicting troponin biomarker elevation from electrocardiograms using a deep neural network"],"prefix":"10.1136","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9518-3644","authenticated-orcid":false,"given":"Lukas","family":"Hilgendorf","sequence":"first","affiliation":[{"name":"Department of Molecular and Clinical Medicine, University of Gothenburg, Goteborg, Sweden"},{"name":"Wallenberg Laboratory for Cardiovascular and Metabolic Research, Institute of Medicine, University of Gothenburg Sahlgrenska Academy, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Petur","family":"Petursson","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, University of Gothenburg, Goteborg, Sweden"},{"name":"Department of Cardiology, Sahlgrenska University Hospital, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vibha","family":"Gupta","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, University of Gothenburg, Goteborg, Sweden"},{"name":"Wallenberg Laboratory for Cardiovascular and Metabolic Research, Institute of Medicine, University of Gothenburg Sahlgrenska Academy, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Truls","family":"Ramunddal","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, University of Gothenburg, Goteborg, Sweden"},{"name":"Department of Cardiology, Sahlgrenska University Hospital, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erik","family":"Andersson","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, University of Gothenburg, Goteborg, Sweden"},{"name":"Department of Cardiology, Sahlgrenska University Hospital, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Lundgren","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, University of Gothenburg, Goteborg, Sweden"},{"name":"Department of Cardiology, Sahlgrenska University Hospital, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Dworeck","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, University of Gothenburg, Goteborg, Sweden"},{"name":"Department of Cardiology, Sahlgrenska University Hospital, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charlotta","family":"Ljungman","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, University of Gothenburg, Goteborg, Sweden"},{"name":"Department of Cardiology, Sahlgrenska University Hospital, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan","family":"Boren","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Sahlgrenska University Hospital, Goteborg, Sweden"},{"name":"University of Gothenburg, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aidin","family":"Rawshani","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, University of Gothenburg, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3875-8621","authenticated-orcid":false,"given":"Elmir","family":"Omerovic","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, University of Gothenburg, Goteborg, Sweden"},{"name":"Department of Cardiology, Sahlgrenska University Hospital, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gustav","family":"Smith","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Sahlgrenska University Hospital, Goteborg, Sweden"},{"name":"Lund University Faculty of Medicine, Lund, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zacharias","family":"Mandalenakis","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, University of Gothenburg, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9095-1218","authenticated-orcid":false,"given":"Kristofer","family":"Skoglund","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, University of Gothenburg, Goteborg, Sweden"},{"name":"Department of Cardiology, Sahlgrenska University Hospital, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Araz","family":"Rawshani","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, University of Gothenburg, Goteborg, Sweden"},{"name":"Wallenberg Laboratory for Cardiovascular and Metabolic Research, Institute of Medicine, University of Gothenburg Sahlgrenska Academy, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2024,10,30]]},"reference":[{"key":"2025081710463997000_11.2.e002937.1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02457822"},{"key":"2025081710463997000_11.2.e002937.2","doi-asserted-by":"crossref","DOI":"10.1155\/2022\/7617551","article-title":"ResNet-50 for 12-Lead Electrocardiogram Automated Diagnosis","volume":"2022","author":"Sakli","year":"2022","journal-title":"Comput Intell Neurosci"},{"key":"2025081710463997000_11.2.e002937.3","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1016\/j.amjcard.2023.12.015","article-title":"Meta-Analysis of the Performance of AI-Driven ECG Interpretation in the Diagnosis of Valvular Heart Diseases","volume":"213","author":"Singh","year":"2024","journal-title":"Am J Cardiol"},{"key":"2025081710463997000_11.2.e002937.4","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1038\/s41569-020-00503-2","article-title":"Artificial intelligence-enhanced electrocardiography in cardiovascular disease management","volume":"18","author":"Siontis","year":"2021","journal-title":"Nat Rev Cardiol"},{"key":"2025081710463997000_11.2.e002937.5","doi-asserted-by":"crossref","first-page":"20495","DOI":"10.1038\/s41598-020-77599-6","article-title":"Artificial intelligence algorithm for detecting myocardial infarction using six-lead electrocardiography","volume":"10","author":"Cho","year":"2020","journal-title":"Sci Rep"},{"key":"2025081710463997000_11.2.e002937.6","unstructured":"Data Basecamp . What are convolutional neural networks (CNN)? Available: https:\/\/databasecamp.de\/en\/ml\/convolutional-neural-networks [Accessed 22 Jan 2021]."},{"key":"2025081710463997000_11.2.e002937.7","doi-asserted-by":"crossref","DOI":"10.1161\/JAHA.113.000268","article-title":"Physician accuracy in interpreting potential ST-segment elevation myocardial infarction electrocardiograms","volume":"2","author":"McCabe","year":"2013","journal-title":"J Am Heart Assoc"},{"key":"2025081710463997000_11.2.e002937.8","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1016\/S0140-6736(98)03212-7","article-title":"Evolution of the management of acute myocardial infarction: a 20th century saga","volume":"352","author":"Braunwald","year":"1998","journal-title":"The Lancet"},{"key":"2025081710463997000_11.2.e002937.9","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehy462"},{"key":"2025081710463997000_11.2.e002937.10","unstructured":"Cardiac troponin. Available: https:\/\/www.siemens-healthineers.com\/laboratory-diagnostics\/assays-by-diseases-conditions\/cardiac-assays\/cardiac-troponin-assays [Accessed 8 Apr 2024]."},{"key":"2025081710463997000_11.2.e002937.11","doi-asserted-by":"publisher","DOI":"10.1373\/clinchem.2006.084194"},{"key":"2025081710463997000_11.2.e002937.12","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-023-29989-9","article-title":"Deep learning augmented ECG analysis to identify biomarker-defined myocardial injury","volume":"13","author":"Chaudhari","year":"2023","journal-title":"Sci Rep"},{"key":"2025081710463997000_11.2.e002937.13","unstructured":"Salimi A , Kalmady SV , Hindle A , et al . Exploring best practices for ecg signal processing in machine learning. arXiv; 2023. Available: http:\/\/arxiv.org\/abs\/2311.04229 [Accessed 4 Mar 2024]."},{"key":"2025081710463997000_11.2.e002937.14","unstructured":"Ioffe S , Normalization SCB . arXiv; Accelerating Deep Network Training by Reducing Internal Covariate Shift, 2015. Available: http:\/\/arxiv.org\/abs\/1502.03167 [Accessed 11 Apr 2024]."},{"key":"2025081710463997000_11.2.e002937.15","unstructured":"SOP-z-score-standard-score-calculation.pdf. Available: https:\/\/hiv-forschung.de\/wp-content\/uploads\/SOP-Z-score-standard-score-calculation.pdf [Accessed 12 Apr 2024]."},{"key":"2025081710463997000_11.2.e002937.16","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1007\/s11739-021-02920-8","article-title":"Type 2 myocardial infarction: a diagnostic and therapeutic challenge in contemporary cardiology","volume":"17","author":"Merlo","year":"2022","journal-title":"Intern Emerg Med"},{"key":"2025081710463997000_11.2.e002937.17","doi-asserted-by":"crossref","unstructured":"Zhang P , Cheng J , Zhao Y . Classification of ecg signals based on lstm and cnn. In: Sun X , Wang J , Bertino E , eds. Artificial Intelligence and Security. Singapore: Springer, 2020: 278\u201389.","DOI":"10.1007\/978-981-15-8101-4_26"},{"key":"2025081710463997000_11.2.e002937.18","doi-asserted-by":"crossref","unstructured":"Mehari T , Strodthoff N . Self-supervised representation learning from 12-lead ECG data. Comput Biol Med 2022.","DOI":"10.1016\/j.compbiomed.2021.105114"},{"key":"2025081710463997000_11.2.e002937.19","doi-asserted-by":"crossref","unstructured":"Liu Y , Xie H , Cao Q , et al . Multi-label classification of multi-lead ecg based on deep 1d convolutional neural networks with residual and attention mechanism: 2021 computing in cardiology (cinc). Available: https:\/\/ieeexplore.ieee.org\/abstract\/document\/9662873 [Accessed 14 Aug 2024].","DOI":"10.23919\/CinC53138.2021.9662873"},{"key":"2025081710463997000_11.2.e002937.20","doi-asserted-by":"crossref","first-page":"5237","DOI":"10.3390\/s23115237","article-title":"A Systematic Survey of Data Augmentation of ECG Signals for AI Applications","volume":"23","author":"Rahman","year":"2023","journal-title":"Sensors (Basel)"}],"container-title":["Open Heart"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/openhrt-2024-002937","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,17]],"date-time":"2025-08-17T17:46:52Z","timestamp":1755452812000},"score":1,"resource":{"primary":{"URL":"https:\/\/openheart.bmj.com\/lookup\/doi\/10.1136\/openhrt-2024-002937"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":20,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,10,30]]},"published-print":{"date-parts":[[2024,10]]}},"alternative-id":["10.1136\/openhrt-2024-002937"],"URL":"https:\/\/doi.org\/10.1136\/openhrt-2024-002937","relation":{},"ISSN":["2053-3624"],"issn-type":[{"value":"2053-3624","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}