{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T16:01:03Z","timestamp":1792684863865,"version":"4.5.0"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:00:00Z","timestamp":1778284800000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01HL137761"],"award-info":[{"award-number":["R01HL137761"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,18]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Aims<\/jats:title>\n                    <jats:p>AI in electrocardiography (ECG) has diverged into two paths: traditional signal processing with machine learning, and deep learning of raw waveforms. The former preserves physiological interpretability but may miss novel patterns, while the latter overlooks a century of ECG science. No framework yet integrates both. This study introduces a fusion model combining handcrafted feature-based random forest and waveform-based convolutional neural network to improve the diagnosis of acute coronary events.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods and results<\/jats:title>\n                    <jats:p>This prospective, multicentre cohort study included pre-hospital ECGs recorded on emergency medical services from patients with a chief complaint of chest pain. Using this dataset, we developed four fusion frameworks that integrate ECG features with waveform information: (1) decision-level fusion combining predictions from random forest and convolutional neural network (CNN); (2) decision-level fusion with retraining; (3) feature-level fusion by concatenating CNN embeddings with ECG features; and (4) feature-level fusion combining CNN embeddings with tree-level outputs from the random forest. This study comprised of 10 393 ECGs from 7397 patients. On both outcomes, acute coronary syndrome and occlusion myocardial infarction, the proposed decision fusion with retraining (Approach 2) achieved an AUROC of 0.878 (95% CI, 0.837\u20130.915) and 0.961 (95% CI, 0.934\u20130.983) on the test set and an average precision score of 0.749 (95% CI, 0.681\u20130.810) and 0.850 (95% CI, 0.763\u20130.918), respectively, outperforming all other proposed fusion and individual models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study demonstrates the significance of fusion models that integrate complementary ECG representations to improve diagnostic accuracy in acute coronary events, highlighting a promising approach for real-time AI-augmented cardiovascular disease detection across diverse use cases.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/ehjdh\/ztag062","type":"journal-article","created":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T11:38:03Z","timestamp":1778153883000},"source":"Crossref","is-referenced-by-count":1,"title":["Novel machine learning fusion architectures integrating electrocardiogram representations: applications to acute coronary event detection"],"prefix":"10.1093","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6626-9793","authenticated-orcid":false,"given":"Rui Qi","family":"Ji","sequence":"first","affiliation":[{"name":"The Edward S. Rogers Sr, Department of Electrical & Computer Engineering, University of Toronto , Toronto M5S 1A1, Ontario ,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3286-560X","authenticated-orcid":false,"given":"Nathan T","family":"Riek","sequence":"additional","affiliation":[{"name":"School of Nursing, University of Rochester , Rochester, NY 14627 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9436-2058","authenticated-orcid":false,"given":"Tanmay","family":"Gokhale","sequence":"additional","affiliation":[{"name":"University of Pittsburgh Medical Centre , Pittsburgh, PA 15260 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1095-4444","authenticated-orcid":false,"given":"Zeineb","family":"Bouzid","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology , Atlanta, GA 30332 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2362-7749","authenticated-orcid":false,"given":"Karina","family":"Kraevsky","sequence":"additional","affiliation":[{"name":"University of Pittsburgh Medical Centre , Pittsburgh, PA 15260 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5650-0464","authenticated-orcid":false,"given":"Jessica K","family":"Z\u00e8gre-Hemsey","sequence":"additional","affiliation":[{"name":"School of Nursing, University of North Carolina at Chapel Hill , Chapel Hill, NC 27599 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4669-803X","authenticated-orcid":false,"given":"Samir","family":"Saba","sequence":"additional","affiliation":[{"name":"University of Pittsburgh Medical Centre , Pittsburgh, PA 15260 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3522-2100","authenticated-orcid":false,"given":"Christian","family":"Martin-Gill","sequence":"additional","affiliation":[{"name":"University of Pittsburgh Medical Centre , Pittsburgh, PA 15260 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3309-1573","authenticated-orcid":false,"given":"Clifton W","family":"Callaway","sequence":"additional","affiliation":[{"name":"University of Pittsburgh Medical Centre , Pittsburgh, PA 15260 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5094-1931","authenticated-orcid":false,"given":"Murat","family":"Akcakaya","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Pittsburgh , PA 15260 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4987-8298","authenticated-orcid":false,"given":"Ervin","family":"Sejdic\u0301","sequence":"additional","affiliation":[{"name":"The Edward S. Rogers Sr, Department of Electrical & Computer Engineering, University of Toronto , Toronto M5S 1A1, Ontario ,","place":["Canada"]},{"name":"North York General Hospital , Toronto M2K 1E1 ,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salah S","family":"Al-Zaiti","sequence":"additional","affiliation":[{"name":"School of Nursing, University of Rochester , Rochester, NY 14627 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,5,8]]},"reference":[{"key":"2026052009064016500_ztag062-B1","doi-asserted-by":"crossref","first-page":"4717","DOI":"10.1093\/eurheartj\/ehab649","article-title":"Application of artificial intelligence to the electrocardiogram","volume":"42","author":"Attia","year":"2021","journal-title":"Eur Heart J"},{"key":"2026052009064016500_ztag062-B2","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":"2026052009064016500_ztag062-B3","doi-asserted-by":"crossref","first-page":"S61","DOI":"10.1016\/j.jelectrocard.2019.08.008","article-title":"Machine learning in the electrocardiogram","volume":"57","author":"Minchol\u00e9","year":"2019","journal-title":"J Electrocardiol"},{"key":"2026052009064016500_ztag062-B4","doi-asserted-by":"crossref","first-page":"5366","DOI":"10.1007\/s10489-021-02696-6","article-title":"Hybrid CNN-LSTM deep learning model and ensemble technique for automatic detection of myocardial infarction using big ECG data","volume":"52","author":"Rai","year":"2022","journal-title":"Appl Intell"},{"key":"2026052009064016500_ztag062-B5","doi-asserted-by":"crossref","first-page":"19191","DOI":"10.1007\/s11042-024-19740-5","article-title":"eFuseNet: a deep ensemble fusion network for efficient detection of arrhythmia and myocardial infarction using ECG signals","volume":"18","author":"Dwivedi","year":"2024","journal-title":"Multimed Tools Appl"},{"key":"2026052009064016500_ztag062-B6","article-title":"Deep model fusion: a survey","author":"Li","year":"2025","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2026052009064016500_ztag062-B7","doi-asserted-by":"crossref","first-page":"3966","DOI":"10.1038\/s41467-020-17804-2","article-title":"Machine learning-based prediction of acute coronary syndrome using only the pre-hospital 12-lead electrocardiogram","volume":"11","author":"Al-Zaiti","year":"2020","journal-title":"Nat Commun"},{"key":"2026052009064016500_ztag062-B8","doi-asserted-by":"crossref","first-page":"1804","DOI":"10.1038\/s41591-023-02396-3","article-title":"Machine learning for ECG diagnosis and risk stratification of occlusion myocardial infarction","volume":"29","author":"Al-Zaiti","year":"2023","journal-title":"Nat Med"},{"key":"2026052009064016500_ztag062-B9","doi-asserted-by":"crossref","first-page":"3613","DOI":"10.1109\/TBME.2025.3573581","article-title":"ECG-Smart-net: a deep learning architecture for precise ECG diagnosis of occlusion myocardial infarction","volume":"72","author":"Riek","year":"2025","journal-title":"IEEE Trans Biomed Eng"},{"key":"2026052009064016500_ztag062-B10","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"2026052009064016500_ztag062-B11","first-page":"1","volume-title":"2017 Computing in Cardiology (CinC)","author":"Clifford","year":"2017"},{"key":"2026052009064016500_ztag062-B12","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1177\/0885066613503294","article-title":"Acute coronary syndrome","volume":"30","author":"Makki","year":"2015","journal-title":"J Intensive Care Med"},{"key":"2026052009064016500_ztag062-B13","doi-asserted-by":"crossref","first-page":"3481","DOI":"10.1161\/CIRCULATIONAHA.105.537878","article-title":"Pathophysiology of coronary artery disease","volume":"111","author":"Libby","year":"2005","journal-title":"Circulation"},{"key":"2026052009064016500_ztag062-B14","doi-asserted-by":"crossref","first-page":"3757","DOI":"10.1093\/eurheartj\/ehy655","article-title":"What\u2019s new in the fourth universal definition of myocardial infarction?","volume":"39","author":"Thygesen","year":"2018","journal-title":"Eur Heart J"},{"key":"2026052009064016500_ztag062-B15","doi-asserted-by":"crossref","first-page":"e017871","DOI":"10.1161\/JAHA.120.017871","article-title":"In search of an optimal subset of ECG features to augment the diagnosis of acute coronary syndrome at the emergency department","volume":"10","author":"Bouzid","year":"2021","journal-title":"J Am Heart Assoc"},{"key":"2026052009064016500_ztag062-B16","first-page":"100767","article-title":"Accuracy of OMI ECG findings versus STEMI criteria for diagnosis of acute coronary occlusion myocardial infarction","volume":"33","author":"Meyers","year":"2021","journal-title":"Int J Cardiol Heart Vasc"},{"key":"2026052009064016500_ztag062-B17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ijcard.2020.12.082","article-title":"Total coronary occlusion in non ST elevation myocardial infarction: time to change our practice?","volume":"329","author":"Tziakas","year":"2021","journal-title":"Int J Cardiol"},{"key":"2026052009064016500_ztag062-B18","doi-asserted-by":"crossref","first-page":"101314","DOI":"10.1016\/j.jacadv.2024.101314","article-title":"From ST-segment elevation MI to occlusion MI: the new paradigm shift in acute myocardial infarction","volume":"3","author":"McLaren","year":"2024","journal-title":"JACC Adv"},{"key":"2026052009064016500_ztag062-B19","doi-asserted-by":"crossref","first-page":"5201","DOI":"10.3390\/jcm13175201","article-title":"OMI\/NOMI: time for a new classification of acute myocardial infarction","volume":"13","author":"Kola","year":"2024","journal-title":"J Clin Med"},{"key":"2026052009064016500_ztag062-B20","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.resuscitation.2022.01.005","article-title":"Interobserver variability among experienced electrocardiogram readers to diagnose acute thrombotic coronary occlusion in patients with out of hospital cardiac arrest: impact of metabolic milieu and angiographic culprit","volume":"172","author":"Sharma","year":"2022","journal-title":"Resuscitation"},{"key":"2026052009064016500_ztag062-B21","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":"2026052009064016500_ztag062-B22","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/j.jemermed.2020.10.026","article-title":"Comparison of the ST-elevation myocardial infarction (STEMI) vs. NSTEMI and occlusion MI (OMI) vs. NOMI paradigms of acute MI","volume":"60","author":"Meyers","year":"2021","journal-title":"J Emerg Med"},{"key":"2026052009064016500_ztag062-B23","doi-asserted-by":"crossref","first-page":"921","DOI":"10.1016\/j.jelectrocard.2015.08.014","article-title":"Rationale, development, and implementation of the electrocardiographic methods for the prehospital identification of non-ST elevation myocardial infarction events (EMPIRE)","volume":"48","author":"Al-Zaiti","year":"2015","journal-title":"J Electrocardiol"},{"key":"2026052009064016500_ztag062-B24","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.jelectrocard.2021.08.005","article-title":"Prehospital ECG with ST-depression and T-wave inversion are associated with new onset heart failure in individuals transported by ambulance for suspected acute coronary syndrome","volume":"69","author":"Z\u00e8gre-Hemsey","year":"2021","journal-title":"J Electrocardiol"},{"key":"2026052009064016500_ztag062-B25","doi-asserted-by":"crossref","first-page":"1070","DOI":"10.1016\/j.jen.2025.04.016","article-title":"Patient-reported symptoms of acute coronary syndrome in the prehospital period in a prospective study: implications for emergency nurse triage, diagnosis, and clinical outcomes","volume":"51","author":"Z\u00e8gre-Hemsey","year":"2025","journal-title":"J Emerg Nurs"},{"key":"2026052009064016500_ztag062-B26","volume-title":"TIMI Grade Flow","author":"Sarkar","year":"2020"},{"key":"2026052009064016500_ztag062-B27","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.eswa.2018.07.030","article-title":"ECG classification using three-level fusion of different feature descriptors","volume":"114","author":"Golrizkhatami","year":"2018","journal-title":"Expert Syst Appl"},{"key":"2026052009064016500_ztag062-B28","doi-asserted-by":"crossref","first-page":"16477","DOI":"10.1038\/s41598-018-34833-6","article-title":"A deep neural network model using RF to extract feature representation for gene expression data classification","volume":"8","author":"Kong","year":"2018","journal-title":"Sci Rep"},{"key":"2026052009064016500_ztag062-B29","author":"Dai"},{"key":"2026052009064016500_ztag062-B30","first-page":"270","volume-title":"Machine Learning for Healthcare Conference","author":"Vindas","year":"2022"},{"key":"2026052009064016500_ztag062-B31","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.jelectrocard.2022.08.003","article-title":"Emerging ECG methods for acute coronary syndrome detection: recommendations & future opportunities","volume":"74","author":"Al-Zaiti","year":"2022","journal-title":"J Electrocardiol"}],"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\/ztag062\/68257557\/ztag062.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ehjdh\/article-pdf\/7\/5\/ztag062\/68257557\/ztag062.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ehjdh\/article-pdf\/7\/5\/ztag062\/68257557\/ztag062.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T13:06:52Z","timestamp":1779282412000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ehjdh\/article\/doi\/10.1093\/ehjdh\/ztag062\/8674766"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,8]]},"references-count":31,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5,18]]}},"URL":"https:\/\/doi.org\/10.1093\/ehjdh\/ztag062","relation":{},"ISSN":["2634-3916"],"issn-type":[{"value":"2634-3916","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,6]]},"published":{"date-parts":[[2026,5,8]]},"article-number":"ztag062"}}