{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T22:08:08Z","timestamp":1790633288366,"version":"4.1.0"},"reference-count":29,"publisher":"BMJ","issue":"2","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/3.0\/igo\/"}],"funder":[{"name":"MGH Primary Care Innovation Fund"},{"name":"Wellman Center for Photomedicine"},{"name":"University Research Scholarship Program of the Ministry of Culture and Innovation from the National Research, Development, and Innovation Fund of Hungary","award":["Excellence 151118"],"award-info":[{"award-number":["Excellence 151118"]}]},{"name":"University Research Scholarship Program of the Ministry of Culture and Innovation from the National Research, Development, and Innovation Fund of Hungary","award":["PD 147269"],"award-info":[{"award-number":["PD 147269"]}]},{"DOI":"10.13039\/100000009","name":"Foundation for the National Institutes of Health","doi-asserted-by":"publisher","award":["T32HL007208"],"award-info":[{"award-number":["T32HL007208"]}],"id":[{"id":"10.13039\/100000009","id-type":"DOI","asserted-by":"publisher"}]},{"name":"J\u00e1nos Bolyai Research Scholarship of the Hungarian Academy of Sciences"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Open Heart"],"accepted":{"date-parts":[[2025,8,4]]},"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Despite standardised approaches, subjective assessment and inconsistent diagnostic testing for chest pain in the emergency department (ED) drive costs, disparities and adverse outcomes. Artificial intelligence offers potential to automate and improve risk stratification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods and results<\/jats:title>\n                    <jats:p>Using a retrospective cohort of 15\u2009048 patients presenting to the ED of a tertiary care hospital, we trained a neural network classifier (\u2018Chest Pain-AI\u2019 or \u2018CP-AI\u2019) to predict a 7-day composite endpoint of major cardiovascular diagnoses including myocardial infarction, pulmonary embolism, aortic dissection and all-cause mortality. Inputs to CP-AI included age, sex, cardiac biomarkers (D-dimer or troponin I or T positivity) and numerical representations of presenting 12-lead ECGs. ECG representations were derived using a publicly available deep learning model known as patient contrastive learning of representations. In an external validation set of 14\u2009476 patients, we evaluated CP-AI against comparator models, including a \u2018Biomarker Model\u2019 incorporating clinical data (age, sex, biomarker positivity), based on both the area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC). CP-AI outperformed the Biomarker Model in prediction of the 7-day composite endpoint with an AUROC of 0.82 (95% CI 0.81 to 0.83) vs 0.79 (95% CI 0.78 to 0.81) and an AUPRC of 0.46 (95% CI 0.44 to 0.49) vs 0.35 (95% CI 0.33 to 0.37) (p&lt;0.05 for both comparisons).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>CP-AI, a fully automated neural network classifier, demonstrated superior performance in the prediction of 7-day major cardiovascular diagnoses for patients presenting with acute chest pain compared with conventional models trained on demographics and cardiac biomarkers. CP-AI may standardise and expedite risk stratification of patients presenting to the ED with chest pain.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/openhrt-2025-003343","type":"journal-article","created":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T16:15:18Z","timestamp":1756743318000},"page":"e003343","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":5,"title":["Risk stratification of chest pain in the emergency department using artificial intelligence applied to electrocardiograms"],"prefix":"10.1136","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4346-6241","authenticated-orcid":false,"given":"Julian S.","family":"Haimovich","sequence":"first","affiliation":[{"name":"Cardiology Division, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA"},{"name":"Heart and Vascular Institute, Cardiovascular Research Center, Mass General Brigham, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M\u00e1rton","family":"Kolossv\u00e1ry","sequence":"additional","affiliation":[{"name":"Cardiovascular Imaging Research Center, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA"},{"name":"Gottsegen National Cardiovascular Center, Budapest, Hungary"},{"name":"Physiological Controls Research Center, University Research and Innovation Center, \u00d3buda University, Budapest, Hungary"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ridwan","family":"Alam","sequence":"additional","affiliation":[{"name":"Cardiology Division, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA"},{"name":"Research Laboratory of Electronics, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raimon","family":"Padr\u00f3s-Valls","sequence":"additional","affiliation":[{"name":"Cardiology Division, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA"},{"name":"Bioinformatics and Systems Biology, University of California San Diego, La Jolla, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael T.","family":"Lu","sequence":"additional","affiliation":[{"name":"Cardiovascular Imaging Research Center, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5509-1646","authenticated-orcid":false,"given":"Aaron D","family":"Aguirre","sequence":"additional","affiliation":[{"name":"Cardiology Division, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA"},{"name":"Heart and Vascular Institute, Cardiovascular Research Center, Mass General Brigham, Boston, Massachusetts, USA"},{"name":"Center for Systems Biology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA"},{"name":"Wellman Center for Photomedicine, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,9,1]]},"reference":[{"key":"2026010701110521000_12.2.e003343.1","doi-asserted-by":"publisher","DOI":"10.1161\/CIR.0000000000001029"},{"key":"2026010701110521000_12.2.e003343.2","doi-asserted-by":"publisher","DOI":"10.1161\/CIR.0b013e3181ec61df"},{"key":"2026010701110521000_12.2.e003343.3","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1208200"},{"key":"2026010701110521000_12.2.e003343.4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2022.08.004"},{"key":"2026010701110521000_12.2.e003343.5","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1093\/qje\/qjab046","article-title":"Diagnosing physician error: a machine learning approach to low-value health care","volume":"137","author":"Mullainathan","year":"2022","journal-title":"Q J Econ"},{"key":"2026010701110521000_12.2.e003343.6","doi-asserted-by":"publisher","DOI":"10.1136\/hrt.2003.027599"},{"key":"2026010701110521000_12.2.e003343.7","doi-asserted-by":"publisher","DOI":"10.1136\/heartjnl-2019-315667"},{"key":"2026010701110521000_12.2.e003343.8","doi-asserted-by":"crossref","first-page":"1020","DOI":"10.1111\/acem.14762","article-title":"Race differences in cardiac testing rates for patients with chest pain in a multisite cohort","volume":"30","author":"Popp","year":"2023","journal-title":"Acad Emerg Med"},{"key":"2026010701110521000_12.2.e003343.9","doi-asserted-by":"crossref","unstructured":"Gustafsson S , Gedon D , Lampa E , et al . Development and validation of deep learning ECG-based prediction of myocardial infarction in emergency department patients. Sci Rep 2022;12. doi:10.1038\/s41598-022-24254-x","DOI":"10.1038\/s41598-022-24254-x"},{"key":"2026010701110521000_12.2.e003343.10","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01335-4"},{"key":"2026010701110521000_12.2.e003343.11","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1093\/ehjdh\/ztab101","article-title":"Development of a machine learning model using electrocardiogram signals to improve acute pulmonary embolism screening","volume":"3","author":"Somani","year":"2022","journal-title":"Eur Heart J Digit Health"},{"key":"2026010701110521000_12.2.e003343.12","doi-asserted-by":"crossref","unstructured":"Kolossv\u00e1ry M , Raghu VK , Nagurney JT , et al . Deep learning analysis of chest radiographs to triage patients with acute chest pain syndrome. Radiology 2023;306. doi:10.1148\/radiol.221926","DOI":"10.1148\/radiol.221926"},{"key":"2026010701110521000_12.2.e003343.13","unstructured":"Identify subjects \/ request data. Available: https:\/\/rc.partners.org\/research-apps-services\/identify-subjects-request-data [Accessed 30 Dec 2024]."},{"key":"2026010701110521000_12.2.e003343.14","doi-asserted-by":"crossref","unstructured":"Diamant N , Reinertsen E , Song S , et al . Patient contrastive learning: a performant, expressive, and practical approach to electrocardiogram modeling. PLoS Comput Biol 2022;18. doi:10.1371\/journal.pcbi.1009862","DOI":"10.1371\/journal.pcbi.1009862"},{"key":"2026010701110521000_12.2.e003343.15","unstructured":"Model_zoo\/pclr at master \u00b7 broadinstitute\/ml4h. Github. n.d. Available: https:\/\/github.com\/broadinstitute\/ml4h\/tree\/master\/model_zoo\/PCLR"},{"key":"2026010701110521000_12.2.e003343.16","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.cvdhj.2023.03.001","article-title":"Artificial intelligence-enabled classification of hypertrophic heart diseases using electrocardiograms","volume":"4","author":"Haimovich","year":"2023","journal-title":"Cardiovasc Digit Health J"},{"key":"2026010701110521000_12.2.e003343.17","unstructured":"Pedregosa F , Varoquaux G , Gramfort A , et al . Scikit-learn: machine learning in python, Available: http:\/\/arxiv.org\/abs\/1201.0490"},{"key":"2026010701110521000_12.2.e003343.18","doi-asserted-by":"crossref","unstructured":"Davis J , Goadrich M . The relationship between Precision-Recall and ROC curves. Proceedings of the 23rd international conference on Machine learning - ICML '06. New York, New York, USA: ACM Press, 2006 doi:10.1145\/1143844.1143874","DOI":"10.1145\/1143844.1143874"},{"key":"2026010701110521000_12.2.e003343.19","doi-asserted-by":"crossref","unstructured":"Efron B , Tibshirani RJ . An Introduction to the Bootstrap. Chapman and Hall\/CRC, 1994.","DOI":"10.1201\/9780429246593"},{"key":"2026010701110521000_12.2.e003343.20","doi-asserted-by":"publisher","DOI":"10.1016\/j.annemergmed.2018.12.010"},{"key":"2026010701110521000_12.2.e003343.21","doi-asserted-by":"crossref","unstructured":"Sun W , Kalmady SV , Sepehrvand N , et al . Towards artificial intelligence-based learning health system for population-level mortality prediction using electrocardiograms. NPJ Digit Med 2023;6. doi:10.1038\/s41746-023-00765-3","DOI":"10.1038\/s41746-023-00765-3"},{"key":"2026010701110521000_12.2.e003343.22","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1016\/j.ajem.2016.09.058","article-title":"Documentation of HEART score discordance between emergency physician and cardiologist evaluations of ED patients with chest pain","volume":"35","author":"Wu","year":"2017","journal-title":"Am J Emerg Med"},{"key":"2026010701110521000_12.2.e003343.23","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjcard.2021.02.015"},{"key":"2026010701110521000_12.2.e003343.24","doi-asserted-by":"crossref","unstructured":"Banco D , Chang J , Talmor N , et al . Sex and race differences in the evaluation and treatment of young adults presenting to the emergency department with chest pain. J Am Heart Assoc 2022;11. doi:10.1161\/JAHA.121.024199","DOI":"10.1161\/JAHA.121.024199"},{"key":"2026010701110521000_12.2.e003343.25","doi-asserted-by":"publisher","DOI":"10.1007\/s11883-024-01190-x"},{"key":"2026010701110521000_12.2.e003343.26","doi-asserted-by":"publisher","DOI":"10.1161\/cir.0000000000001201"},{"key":"2026010701110521000_12.2.e003343.27","doi-asserted-by":"crossref","first-page":"1128","DOI":"10.1001\/jamainternmed.2013.850","article-title":"Yield of routine provocative cardiac testing among patients in an emergency department-based chest pain unit","volume":"173","author":"Hermann","year":"2013","journal-title":"JAMA Intern Med"},{"key":"2026010701110521000_12.2.e003343.28","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjcard.2015.03.058"},{"key":"2026010701110521000_12.2.e003343.29","doi-asserted-by":"publisher","DOI":"10.1257\/aer.20140260"}],"container-title":["Open Heart"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/openhrt-2025-003343","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T09:11:26Z","timestamp":1767777086000},"score":1,"resource":{"primary":{"URL":"https:\/\/openheart.bmj.com\/lookup\/doi\/10.1136\/openhrt-2025-003343"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":29,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,9,1]]},"published-print":{"date-parts":[[2025,9]]}},"alternative-id":["10.1136\/openhrt-2025-003343"],"URL":"https:\/\/doi.org\/10.1136\/openhrt-2025-003343","relation":{},"ISSN":["2053-3624"],"issn-type":[{"value":"2053-3624","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}