{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T15:24:52Z","timestamp":1788362692438,"version":"build-2803163510"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T00:00:00Z","timestamp":1781654400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Cardiovasc. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Cancer patients carry elevated risk of new-onset coronary heart disease (CHD), but accurate risk stratification remains limited. We aimed to develop a multimodal deep learning model for predicting new-onset CHD in cancer patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Consecutive cancer patients from January 2010 to December 2020 were enrolled. The primary endpoint was new-onset CHD during hospitalization or follow-up. We constructed a hybrid CNN-LSTM model by fusing electronic health records (EHRs) and 12-lead electrocardiogram (ECG). Model performance was compared with seven machine learning methods (LR, DT, KNN, SVM, RF, AdaBoost, GBDT). Clinical utility and calibration were assessed by ROC, decision curve analysis (DCA) and calibration curves. Subgroup analyses were conducted in early-stage (Stage II) and late-stage (Stage III\u2009+\u2009IV) cohorts.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 1262 patients were included in the final analysis, of whom 722 (57.2%) developed new-onset CHD, with 696 (55.2%) classified as early-stage (Stage II). The CNN-LSTM model achieved an AUC of 0.975 (95%CI: 0.962\u20130.988), outperforming seven conventional machine learning models. In subgroup analysis, the model yielded an AUC of 0.924 in early-stage patients and 0.888 in late-stage patients. SHAP analysis identified that PAB, CRP, age, cTnI, PT, and ECG markers including HR, QT and QTc intervals were the strongest predictive features.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The multimodal CNN-LSTM model enables robust and interpretable prediction of new-onset CHD in cancer patients. Coagulation, myocardial injury, inflammatory, metabolic, and electrophysiological markers provide mechanistic insights and may facilitate early cardioprotective strategies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcvm.2026.1834641","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T04:44:46Z","timestamp":1781671486000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Multimodal fusion of EHR and ECG based on deep learning for predicting new-onset coronary heart disease in cancer patients"],"prefix":"10.3389","volume":"13","author":[{"given":"Sheng","family":"Zhang","sequence":"first","affiliation":[{"name":"Key Laboratory of Digital-Intelligent Disease Surveillance and Health Governance, North Sichuan Medical College","place":["Nanchong, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Chongqing University Cancer Hospital","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,17]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1104","DOI":"10.1161\/CIRCULATIONAHA.115.020406","article-title":"Shared risk factors in cardiovascular disease and cancer","volume":"133","author":"Koene","year":"2016","journal-title":"Circulation"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ijcard.2021.03.050","article-title":"Cancer-related vulnerable lesions in patients with stable coronary artery disease","volume":"335","author":"Taruya","year":"2021","journal-title":"Int J Cardiol"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1083","DOI":"10.1002\/ehf2.12386","article-title":"Modern-day cardio-oncology: a report from the \u2018heart failure and world congress on acute heart failure 2018\u2019","volume":"5","author":"Anker","year":"2018","journal-title":"ESC Heart Fail"},{"key":"B4","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1007\/s12265-020-10042-3","article-title":"The role of biomarkers in cardio-oncology","volume":"13","author":"Ananthan","year":"2020","journal-title":"J Cardiovasc Transl Res"},{"key":"B5","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1007\/s00204-020-02952-7","article-title":"Improving cardiotoxicity prediction in cancer treatment: integration of conventional circulating biomarkers and novel exploratory tools","volume":"95","author":"Pang","year":"2021","journal-title":"Arch Toxicol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1007\/s11864-021-00845-0","article-title":"Circulating biomarkers for cardiotoxicity risk prediction","volume":"22","author":"Gong","year":"2021","journal-title":"Curr Treat Options Oncol"},{"key":"B7","doi-asserted-by":"publisher","first-page":"2129","DOI":"10.1093\/eurheartj\/ehw128","article-title":"2016 ESC guidelines for the diagnosis and treatment of acute and chronic heart failure: the task force for the diagnosis and treatment of acute and chronic heart failure of the European Society of Cardiology (ESC). Developed with the special contribution of the Heart Failure Association (HFA) of the ESC","volume":"37","author":"Ponikowski","year":"2016","journal-title":"Eur Heart J"},{"key":"B8","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1016\/j.ijcard.2015.07.103","article-title":"Experimental determination of diagnostic window of cardiac troponins in the development of chronic anthracycline cardiotoxicity and estimation of its predictive value","volume":"201","author":"Adamcova","year":"2015","journal-title":"Int J Cardiol"},{"key":"B9","doi-asserted-by":"publisher","first-page":"3308","DOI":"10.1002\/ehf2.14078","article-title":"Myocardial strain for heart failure with preserved ejection fraction but without diastolic dysfunction","volume":"9","author":"Park","year":"2022","journal-title":"ESC Heart Fail"},{"key":"B10","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1007\/s10549-012-2039-z","article-title":"High-sensitivity C-reactive protein (hs-CRP) as a biomarker for trastuzumab-induced cardiotoxicity in HER2-positive early-stage breast cancer: a pilot study","volume":"134","author":"Onitilo","year":"2012","journal-title":"Breast Cancer Res Treat"},{"key":"B11","doi-asserted-by":"publisher","first-page":"186","DOI":"10.2459\/JCM.0000000000001587","article-title":"Soluble ST2 as a possible biomarker for inflammation in patients with acute heart failure","volume":"25","author":"Lai","year":"2024","journal-title":"J Cardiovasc Med (Hagerstown)"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1242","DOI":"10.1111\/imj.13796","article-title":"Serum albumin level and abnormal corrected QT interval in patients with coronary artery disease and chronic kidney disease","volume":"48","author":"Wu","year":"2018","journal-title":"Intern Med J"},{"key":"B13","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1093\/eurheartj\/ehx564","article-title":"Beta-blockers for heart failure with reduced, mid-range, and preserved ejection fraction: an individual patient-level analysis of double-blind randomized trials","volume":"39","author":"Cleland","year":"2018","journal-title":"Eur Heart J"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1524","DOI":"10.1002\/ejhf.670","article-title":"Resting heart rate is an independent predictor of death in patients with colorectal, pancreatic, and non-small cell lung cancer: results of a prospective cardiovascular long-term study","volume":"18","author":"Anker","year":"2016","journal-title":"Eur J Heart Fail"},{"key":"B15","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1038\/s41746-020-00341-z","article-title":"Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines","volume":"3","author":"Huang","year":"2020","journal-title":"NPJ Digit Med"},{"key":"B16","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1021\/acs.jcim.7b00641","article-title":"In silico pharmacoepidemiologic evaluation of drug-induced cardiovascular complications using combined classifiers","volume":"58","author":"Cai","year":"2018","journal-title":"J Chem Inf Model"},{"key":"B17","doi-asserted-by":"publisher","first-page":"2963","DOI":"10.1038\/s41467-021-23235-4","article-title":"Deep learning predicts cardiovascular disease risks from lung cancer screening low dose computed tomography","volume":"12","author":"Chao","year":"2021","journal-title":"Nat Commun"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1093\/ajhp\/zxad147","article-title":"Risk prediction models for antineoplastic-associated cardiotoxicity in treatment of breast cancer: a systematic review","volume":"80","author":"Rodriguez","year":"2023","journal-title":"Am J Health Syst Pharm"},{"key":"B19","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1038\/s41746-020-0301-z","article-title":"Deep representation learning of electronic health records to unlock patient stratification at scale","volume":"3","author":"Landi","year":"2020","journal-title":"NPJ Digit Med"},{"key":"B20","doi-asserted-by":"publisher","first-page":"110329","DOI":"10.1016\/j.isci.2024.110329","article-title":"Risk prediction of heart diseases in patients with breast cancer: a deep learning approach with longitudinal electronic health records data","volume":"27","author":"Zhou","year":"2024","journal-title":"iScience"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1434","DOI":"10.1109\/JBHI.2017.2771768","article-title":"Real-time multilead convolutional neural network for myocardial infarction detection","volume":"22","author":"Liu","year":"2018","journal-title":"IEEE J Biomed Health Inform"},{"key":"B22","doi-asserted-by":"publisher","first-page":"11123","DOI":"10.1038\/s41598-026-40925-5","article-title":"A joint CNN-bi-LSTM-transformer architecture with SHAP explanations for multi-label arrhythmia detection from 12-lead ECGs","volume":"16","author":"Al-Bairmani","year":"2026","journal-title":"Sci Rep"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1535335","DOI":"10.3389\/fdgth.2025.1535335","article-title":"Integrated portable ECG monitoring system with CNN classification for early arrhythmia detection","volume":"7","author":"Panwar","year":"2025","journal-title":"Front Digit Health"},{"key":"B24","doi-asserted-by":"publisher","first-page":"2536","DOI":"10.1038\/s41467-024-45733-x","article-title":"Artificial intelligence-enabled prediction of chemotherapy-induced cardiotoxicity from baseline electrocardiograms","volume":"15","author":"Yagi","year":"2024","journal-title":"Nat Commun"},{"key":"B25","doi-asserted-by":"publisher","first-page":"e011504","DOI":"10.1161\/CIRCOUTCOMES.124.011504","article-title":"Artificial intelligence-enhanced risk stratification of cancer therapeutics-related cardiac dysfunction using electrocardiographic images","volume":"18","author":"Oikonomou","year":"2025","journal-title":"Circ Cardiovasc Qual Outcomes"},{"key":"B26","doi-asserted-by":"publisher","first-page":"840262","DOI":"10.3389\/fcvm.2022.840262","article-title":"Use of multi-modal data and machine learning to improve cardiovascular disease care","volume":"9","author":"Amal","year":"2022","journal-title":"Front Cardiovasc Med"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"Lee","year":"2020","journal-title":"Bioinformatics"},{"key":"B28","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s13677-020-00218-2","article-title":"Cloud-based intelligent self-diagnosis and department recommendation service using Chinese medical BERT","volume":"10","author":"Wang","year":"2021","journal-title":"J Cloud Comput"},{"key":"B29","doi-asserted-by":"publisher","first-page":"17","DOI":"10.2174\/1874120701711010017","article-title":"Noninvasive fetal electrocardiography part I: Pan-Tompkins\u2019 algorithm adaptation to fetal R-peak identification","volume":"11","author":"Agostinelli","year":"2017","journal-title":"Open Biomed Eng J"},{"key":"B30","doi-asserted-by":"publisher","first-page":"2459","DOI":"10.3390\/cancers15092459","article-title":"Integration of radiomics and tumor biomarkers in interpretable machine learning models","volume":"15","author":"Brocki","year":"2023","journal-title":"Cancers (Basel)"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1235","DOI":"10.1162\/neco_a_01199","article-title":"A review of recurrent neural networks: LSTM cells and network architectures","volume":"31","author":"Yu","year":"2019","journal-title":"Neural Comput"},{"key":"B32","doi-asserted-by":"publisher","first-page":"164","DOI":"10.5853\/jos.2023.03279","article-title":"Cancer-associated stroke: thrombosis mechanism, diagnosis, outcome, and therapeutic strategies","volume":"26","author":"Heo","year":"2024","journal-title":"J Stroke"},{"key":"B33","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1186\/s13019-020-01225-9","article-title":"Two different troponin isoforms for detecting early myocardial injury after curative resection of oesophageal cancer","volume":"15","author":"Gu","year":"2020","journal-title":"J Cardiothorac Surg"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1712","DOI":"10.1182\/blood-2013-04-460121","article-title":"Epidemiology of cancer-associated venous thrombosis","volume":"122","author":"Timp","year":"2013","journal-title":"Blood"},{"key":"B35","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.jaccao.2021.01.002","article-title":"How to diagnose and manage QT prolongation in cancer patients","volume":"3","author":"Kim","year":"2021","journal-title":"JACC CardioOncol"},{"key":"B36","doi-asserted-by":"publisher","first-page":"e21190","DOI":"10.1097\/MD.0000000000021190","article-title":"Effect of thyrotropin suppressive therapy on heart rate variability and QT dispersion in patients with differentiated thyroid cancer","volume":"99","author":"Liu","year":"2020","journal-title":"Medicine (Baltimore)"},{"key":"B37","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1055\/a-2675-6068","article-title":"Introducing the new definition and diagnostic criteria of disseminated intravascular coagulation released by the international society on thrombosis and haemostasis in 2025","volume":"52","author":"Iba","year":"2026","journal-title":"Semin Thromb Hemost"},{"key":"B38","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1093\/jnci\/djaf243","article-title":"Cardiovascular risk in long-term survivors of breast, prostate, colon, and rectal cancer","volume":"118","author":"Westvold","year":"2026","journal-title":"J Natl Cancer Inst"}],"container-title":["Frontiers in Cardiovascular Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcvm.2026.1834641\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T04:44:49Z","timestamp":1781671489000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcvm.2026.1834641\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,17]]},"references-count":38,"alternative-id":["10.3389\/fcvm.2026.1834641"],"URL":"https:\/\/doi.org\/10.3389\/fcvm.2026.1834641","relation":{},"ISSN":["2297-055X"],"issn-type":[{"value":"2297-055X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,17]]},"article-number":"1834641"}}