{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T16:43:29Z","timestamp":1791650609259,"version":"4.3.4"},"reference-count":34,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T00:00:00Z","timestamp":1775520000000},"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>Objective<\/jats:title>\n                    <jats:p>In hemodynamically stable patients with symptomatic abdominal aortic aneurysms (AAA), timely diagnosis of impending rupture remains a critical challenge. To address this, we developed and validated an interpretable multimodal deep learning model to assess rupture risk and support emergency decision-making.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      This retrospective cohort study included 263 symptomatic AAA patients, with the most recent year's cases (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u200933) as an independent temporal test set. In the 230-patient development cohort, 75 impending rupture cases were matched 1:1 with 75 stable controls using propensity score for age, sex, and maximum aortic diameter. We developed a multimodal deep learning model that combines sequential CTA slices with six key clinical biomarkers through a bidirectional cross-attention (BCA) mechanism built on a ResNet-50 image encoder. For interpretability, we used Gradient-weighted Class Activation Mapping (Grad-CAM) and conducted pre-specified sensitivity analyses assessing robustness against endpoint decision-dependence, treatment-related data leakage, and domain shifts.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      In the matched development test set (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u200930), our multimodal model achieved an area under the curve (AUC) of 0.898 with sensitivity and negative predictive value (NPV) both at 93.3%, offering a high safety margin for ruling out rupture. It markedly outperformed two pragmatic clinical baselines (clinical-rule model AUC: 0.751; CTA-sign model 0.778). This strong performance persisted in the independent temporal validation cohort (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u200933), where it attained an AUC of 0.880, sensitivity of 92.9%, and NPV of 87.5%. The proposed BCA fusion outperformed alternative architectures, and Grad-CAM visualizations were anatomically plausible in 78.8% of cases, supporting model interpretability.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>We developed and temporally validated an interpretable multimodal model that integrates CTA and clinical biomarkers to enable rapid AAA rupture risk stratification, offering a clinically relevant improvement in the safety and efficiency of emergency triage over current practice, pending prospective validation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcvm.2026.1771669","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T04:26:06Z","timestamp":1775535966000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A multimodal deep learning model for predicting impending rupture in symptomatic abdominal aortic aneurysms using CTA and clinical data"],"prefix":"10.3389","volume":"13","author":[{"given":"Jiaxin","family":"Cheng","sequence":"first","affiliation":[{"name":"College of Medicine and Biological Information Engineering, Northeastern University","place":["Shenyang, Liaoning, China"]},{"name":"National Key Laboratory of Frigid Zone Cardiovascular Disease, Cardiovascular Research Institute and Department of Cardiology, General Hospital of Northern Theater Command","place":["Shenyang, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sihan","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences","place":["Shenyang, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Frigid Zone Cardiovascular Disease, Cardiovascular Research Institute and Department of Cardiology, General Hospital of Northern Theater Command","place":["Shenyang, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruoxi","family":"Gu","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Frigid Zone Cardiovascular Disease, Cardiovascular Research Institute and Department of Cardiology, General Hospital of Northern Theater Command","place":["Shenyang, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuan","family":"Wu","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Frigid Zone Cardiovascular Disease, Cardiovascular Research Institute and Department of Cardiology, General Hospital of Northern Theater Command","place":["Shenyang, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasong","family":"Wang","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Frigid Zone Cardiovascular Disease, Cardiovascular Research Institute and Department of Cardiology, General Hospital of Northern Theater Command","place":["Shenyang, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Radiology, General Hospital of Northern Theater Command","place":["Shenyang, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Radiology, General Hospital of Northern Theater Command","place":["Shenyang, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaozeng","family":"Wang","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Frigid Zone Cardiovascular Disease, Cardiovascular Research Institute and Department of Cardiology, General Hospital of Northern Theater Command","place":["Shenyang, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haibo","family":"Yu","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Frigid Zone Cardiovascular Disease, Cardiovascular Research Institute and Department of Cardiology, General Hospital of Northern Theater Command","place":["Shenyang, Liaoning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"5955","DOI":"10.21037\/qims-2024-2985","article-title":"Assessing differences in growth and shape between symptomatic and asymptomatic abdominal aortic aneurysms","volume":"15","author":"Braet","year":"2025","journal-title":"Quant Imaging Med Surg"},{"key":"B2","doi-asserted-by":"publisher","first-page":"W57","DOI":"10.2214\/ajr.05.1554","article-title":"Ct findings of rupture, impending rupture, and contained rupture of abdominal aortic aneurysms","volume":"188","author":"Schwartz","year":"2007","journal-title":"Am J Roentgenol"},{"key":"B3","doi-asserted-by":"publisher","first-page":"486","DOI":"10.1111\/acem.14475","article-title":"Accuracy of presenting symptoms, physical examination, and imaging for diagnosis of ruptured abdominal aortic aneurysm: systematic review and meta-analysis","volume":"29","author":"Fernando","year":"2022","journal-title":"Acad Emerg Med"},{"key":"B4","doi-asserted-by":"publisher","first-page":"706","DOI":"10.3390\/diagnostics15060706","article-title":"Atherosclerotic abdominal aortic aneurysms on computed tomography angiography: a narrative review on spectrum of findings, structured reporting, treatment, secondary complications and differential diagnosis","volume":"15","author":"Scicolone","year":"2025","journal-title":"Diagnostics"},{"key":"B5","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1016\/j.ejrad.2014.12.022","article-title":"The blood flow channel index as novel predictor of abdominal aortic aneurysm impending rupture based on the intraluminal thrombus angio-Ct study","volume":"84","author":"Wiernicki","year":"2015","journal-title":"Eur J Radiol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1016\/j.bbe.2023.06.004","article-title":"Attention-guided multiple instance learning for copd identification: to combine the intensity and morphology","volume":"43","author":"Wu","year":"2023","journal-title":"Biocybernetics Biomed Eng"},{"key":"B7","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.diii.2022.11.007","article-title":"Artificial intelligence: a critical review of applications for lung nodule and lung cancer","volume":"104","author":"de Margerie-Mellon","year":"2023","journal-title":"Diagn Interv Imaging"},{"key":"B8","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1097\/cd9.0000000000000108","article-title":"Real-time three-dimensional echocardiography: a feasible and accurate method for measuring right ventricular function in pulmonary hypertension","volume":"3","author":"Ahmad","year":"2023","journal-title":"Cardiol Discov"},{"key":"B9","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1177\/15385744231189024","article-title":"Applying artificial intelligence to predict complications after endovascular aneurysm repair","volume":"58","author":"Long","year":"2024","journal-title":"Vasc Endovascular Surg"},{"key":"B10","doi-asserted-by":"publisher","first-page":"321-","DOI":"10.1016\/j.jvs.2019.12.026","article-title":"Artificial intelligence in abdominal aortic aneurysm","volume":"72","author":"Raffort","year":"2020","journal-title":"J Vasc Surg"},{"key":"B11","doi-asserted-by":"publisher","first-page":"16431","DOI":"10.1038\/s41598-025-00484-7","article-title":"Automatic Cta analysis for blood vessels and aneurysm features extraction in Evar planning","volume":"15","author":"Robbi","year":"2025","journal-title":"Sci Rep"},{"key":"B12","doi-asserted-by":"publisher","first-page":"15266028251314359","DOI":"10.1177\/15266028251314359","article-title":"Multimodal artificial intelligence model for prediction of abdominal aortic aneurysm shrinkage after endovascular repair (the ART in EVAR study)","author":"van Rijswijk","year":"2025","journal-title":"J Endovasc Ther"},{"key":"B13","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/j.avsg.2024.07.111","article-title":"A comprehensive review on computational analysis, research advances, and major findings on abdominal aortic aneurysms for the years 2021 to 2023","volume":"110","author":"Manta","year":"2025","journal-title":"Ann Vasc Surg"},{"key":"B14","doi-asserted-by":"publisher","first-page":"121772","DOI":"10.1016\/j.ins.2024.121772","article-title":"Dcafusion: a novel general image fusion framework based on reference image reconstruction and dual-cross attention mechanism","volume":"698","author":"Fang","year":"2025","journal-title":"Inf Sci (Ny)"},{"key":"B15","doi-asserted-by":"publisher","first-page":"9604","DOI":"10.1038\/s41598-025-94828-y","article-title":"Morphology and biomechanical index predict the rupture location and rupture risk of abdominal aortic aneurysm","volume":"15","author":"Liu","year":"2025","journal-title":"Sci Rep"},{"key":"B16","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/s11306-018-1451-8","article-title":"Ns-Knn: a modified K-nearest neighbors approach for imputing metabolomics data","volume":"14","author":"Lee","year":"2018","journal-title":"Metabolomics"},{"key":"B17","doi-asserted-by":"publisher","first-page":"5849","DOI":"10.1038\/s41467-021-26085-2","article-title":"Dubstepr is a scalable correlation-based feature selection method for accurately clustering single-cell data","volume":"12","author":"Ranjan","year":"2021","journal-title":"Nat Commun"},{"key":"B18","doi-asserted-by":"publisher","first-page":"109913","DOI":"10.1016\/j.patcog.2023.109913","article-title":"Icafusion: iterative cross-attention guided feature fusion for multispectral object detection","volume":"145","author":"Shen","year":"2024","journal-title":"Pattern Recogn"},{"key":"B19","first-page":"1","article-title":"Cat: cross attention in vision transformer","volume-title":"2022 IEEE International Conference on Multimedia and Expo (ICME)","author":"Lin","year":"2022"},{"key":"B20","article-title":"Attention Is All You Need","author":"Vaswani","year":"2023"},{"key":"B21","first-page":"6022","article-title":"Cutmix: regularization strategy to train strong classifiers with localizable features","author":"Yun","year":"2019"},{"key":"B22","doi-asserted-by":"crossref","DOI":"10.1117\/12.2520589","article-title":"Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates","author":"Smith","year":"2019"},{"key":"B23","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1186\/s12880-024-01517-9","article-title":"Deep learning models for differentiating three sinonasal malignancies using multi-sequence Mri","volume":"25","author":"Wang","year":"2025","journal-title":"BMC Med Imaging"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1571","DOI":"10.1007\/s11517-025-03283-4","article-title":"Automatic skeletal maturity grading from pelvis radiographs by deep learning for adolescent idiopathic scoliosis","volume":"63","author":"Zhao","year":"2025","journal-title":"Med Biol Eng Comput"},{"key":"B25","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1038\/s41746-024-01080-1","article-title":"The clinician-Ai interface: intended use and explainability in Fda-cleared Ai devices for medical image interpretation","volume":"7","author":"McNamara","year":"2024","journal-title":"NPJ Digit Med"},{"key":"B26","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1109\/tmi.2022.3206142","article-title":"Deep learning on multiphysical features and hemodynamic modeling for abdominal aortic aneurysm growth prediction","volume":"42","author":"Kim","year":"2023","journal-title":"IEEE Trans Med Imaging"},{"key":"B27","doi-asserted-by":"publisher","first-page":"38413","DOI":"10.1038\/s41598-025-22167-z","article-title":"Deep learning algorithm for predicting rapid progression of abdominal aortic aneurysm by integrating Ct images and clinical features","volume":"15","author":"Oh","year":"2025","journal-title":"Sci Rep"},{"key":"B28","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.ejvs.2022.05.027","article-title":"Association between blood flow pattern and rupture risk of abdominal aortic aneurysm based on computational fluid dynamics","volume":"64","author":"Qiu","year":"2022","journal-title":"Eur J Vasc Endovasc Surg"},{"key":"B29","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1016\/j.ejvs.2004.06.017","article-title":"Does immediate operation for symptomatic non-ruptured abdominal aortic aneurysm compromise outcome?","volume":"28","author":"Tambyraja","year":"2004","journal-title":"Eur J Vasc Endovasc Surg"},{"key":"B30","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1007\/s10753-022-01626-z","article-title":"Aortic wall inflammation in the pathogenesis, diagnosis and treatment of aortic aneurysms","volume":"45","author":"Skotsimara","year":"2022","journal-title":"Inflammation"},{"key":"B31","doi-asserted-by":"publisher","first-page":"5001","DOI":"10.3390\/ijms25095001","article-title":"The role of inflammasome in abdominal aortic aneurysm and its potential drugs","volume":"25","author":"Pi","year":"2024","journal-title":"Int J Mol Sci"},{"key":"B32","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1038\/s42256-021-00338-7","article-title":"Ai for radiographic COVID-19 detection selects shortcuts over signal","volume":"3","author":"DeGrave","year":"2021","journal-title":"Nat Mach Intell"},{"key":"B33","doi-asserted-by":"publisher","first-page":"962","DOI":"10.1016\/j.crad.2013.04.007","article-title":"Common and uncommon Ct findings in rupture and impending rupture of abdominal aortic aneurysms","volume":"68","author":"Ahmed","year":"2013","journal-title":"Clin Radiol"},{"key":"B34","doi-asserted-by":"publisher","first-page":"2184","DOI":"10.1253\/circj.CJ-21-0541","article-title":"Computed tomography attenuation values of the high-attenuating crescent sign can discriminate between rupture, impending rupture, and non-rupture of aortic aneurysms","volume":"85","author":"Ueda","year":"2021","journal-title":"Circ J"}],"container-title":["Frontiers in Cardiovascular Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcvm.2026.1771669\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T04:26:08Z","timestamp":1775535968000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcvm.2026.1771669\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,7]]},"references-count":34,"alternative-id":["10.3389\/fcvm.2026.1771669"],"URL":"https:\/\/doi.org\/10.3389\/fcvm.2026.1771669","relation":{},"ISSN":["2297-055X"],"issn-type":[{"value":"2297-055X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,7]]},"article-number":"1771669"}}