{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T06:45:49Z","timestamp":1782456349378,"version":"3.54.5"},"reference-count":72,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T00:00:00Z","timestamp":1782432000000},"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. Artif. Intell."],"abstract":"<jats:p>The biggest health threat to the global population is cardiovascular disease (CVD), which afflicts almost one-third of the global population and causes considerable monetary and social losses. Risk analysis should be performed in a timely and appropriate manner to enhance clinical practice and preventive interventions. The emergence of advanced data modalities, such as wearable sensors, medical imaging, electronic health records (EHRs), and genomic platforms, has led to a paradigm shift in the holistic assessment of CVD risk through multimodal data integration. This systematic review is a methodological analysis of recent multimodal input deep-learning algorithms that enhance the early detection of CVD and risk-specific evaluation, following PRISMA 2020 guidelines across 69 studies published 20,122,025 based on 2,847 initial database records. We characterized the wide range of available data streams: longitudinal physiological measurements (ECG, HRV, and BP), echocardiogram data, cardiac MRI and CT, lab\/demographic data, behavioral\/environmental data, and genomic\/proteomic data. Mid-level, early, late, and attention-based fusion methods are described in the context of deep neural networks, such as CNNs, RNNs, BiGRU with attention, and hybrid CNN-LSTM networks. Comparative studies showed dramatic improvements in predictive accuracy (often over 98%), strength to missing or noisy modalities, and access to real-time, individualized recommendations. The best-performing DEEP-CARDIO BiGRU-Attention model had 99.9 percent accuracy on Framingham and Statlog benchmarks. A systematic review of 28 studies by Grad-CAM and SHAP confirmed the dominance of each in imaging and structured-data tasks, respectively (Rahman et al., 2024). The federated explainable FL-LSTM model achieved 99% AUC across three ECG databanks with complete privacy protection. We end with a systematic reproducibility, federated learning, equitable AI, and regulatory translation roadmap.<\/jats:p>","DOI":"10.3389\/frai.2026.1840804","type":"journal-article","created":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T05:46:31Z","timestamp":1782452791000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning for cardiovascular disease: a comprehensive review of detection and risk forecasting"],"prefix":"10.3389","volume":"9","author":[{"given":"N.","family":"Ganeshan","sequence":"first","affiliation":[{"name":"School of Computer Science Engineering and Information Systems, Vellore Institute of Technology","place":["Vellore, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G.","family":"Magesh","sequence":"additional","affiliation":[{"name":"School of Computer Science Engineering and Information Systems, Vellore Institute of Technology","place":["Vellore, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,26]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"29","DOI":"10.46439\/biomedres.5.041","article-title":"Recent developments in the diagnosis, treatment, and management of cardiovascular diseases through artificial intelligence and other innovative approaches","volume":"5","author":"Addissouky","year":"2024","journal-title":"PRO"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"13","DOI":"10.32604\/cmc.2021.019013","article-title":"Data and machine learning fusion architecture for cardiovascular disease prediction","volume":"69","author":"Ahmad","year":"2021","journal-title":"Comput. Mater. Contin."},{"key":"ref3","first-page":"87","author":"Ahuja","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1563185","DOI":"10.3389\/fphys.2025.1563185","article-title":"Federated learning-based multimodal approach for early cardiac disease detection","volume":"16","author":"Alasmari","year":"2025","journal-title":"Front. Cardiovasc. Med."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"215","DOI":"10.3390\/diagnostics12123215","article-title":"Ensemble learning based on hybrid deep learning model for heart disease early prediction","volume":"12","author":"Almulihi","year":"2022","journal-title":"Diagnostics"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e2806","DOI":"10.7717\/peerj-cs.2806","article-title":"Demystifying diagnosis: An efficient deep learning technique with explainable AI to improve breast Cancer detection","volume":"11","author":"Alzahrani","year":"2025","journal-title":"PeerJ Comput. Sci."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1412404","DOI":"10.3389\/fradi.2024.1412404","article-title":"Artificial intelligence and multimodal medical imaging data fusion for improving cardiovascular disease care","volume":"4","author":"Amal","year":"2024","journal-title":"Front. Radiol."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1093","DOI":"10.1109\/TCBB.2019.2935059","article-title":"High-risk prediction of cardiovascular diseases via attention-based deep neural networks","volume":"18","author":"An","year":"2019","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"101435","DOI":"10.1016\/j.jacadv.2024.101435","article-title":"Multimodal fusion artificial intelligence model to predict myocarditis and adverse cardiovascular events in cancer patients starting ICI therapy","volume":"4","author":"Ayoub","year":"2025","journal-title":"JACC Advances"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"28669","DOI":"10.1038\/s41598-025-11574-x","article-title":"Pyramidal attention-based T network for brain tumor classification: a comprehensive analysis of transfer learning approaches for clinically reliable and reliable AI hybrid approaches","volume":"15","author":"Banerjee","year":"2025","journal-title":"Sci. Rep."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"931","DOI":"10.1093\/ije\/dyab258","article-title":"Predicting cardiovascular risk from national administrative databases using a combined survival analysis and deep learning approach","volume":"51","author":"Barbieri","year":"2020","journal-title":"Int. J. Epidemiol."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"557","DOI":"10.21037\/cdt-22-438","article-title":"Cardiovascular disease\/stroke risk stratification in deep learning framework: a review","volume":"12","author":"Bhagawati","year":"2023","journal-title":"Cardiovasc. Diagn. Therapy"},{"key":"ref13","article-title":"Hybrid explainable deep learning for heart disease prognosis","volume":"141","author":"Bojarczuk","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"ref14","article-title":"Transformer-based attention models for cardiovascular risk","volume":"14","author":"Browne","year":"2024","journal-title":"Sci. Rep."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"663","DOI":"10.3390\/electronics12071663","article-title":"Classical, evolutionary, and deep learning approaches of automated heart disease prediction: a case study","volume":"12","author":"Cocianu","year":"2023","journal-title":"Electronics"},{"key":"ref16","first-page":"110","article-title":"Explainable AI in cardiovascular health: multimodal analysis and prediction","volume":"18","author":"Dehghani","year":"2025","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"200428","DOI":"10.1016\/j.iswa.2024.200428","article-title":"Integrating explainable machine learning and user-centric design for cardiovascular disease prediction","volume":"23","author":"Dharmarathne","year":"2024","journal-title":"Patterns"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1688872","DOI":"10.3389\/fmed.2025.1688872","article-title":"CASNet: curvature-aware cardiac MRI segmentation with multi-scale and attention-driven encoding for enhanced risk-oriented structural analysis","volume":"12","author":"Du","year":"2026","journal-title":"Front. Med."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"23277","DOI":"10.1038\/s41598-024-74656-2","article-title":"A proposed technique for predicting heart disease using feature selection","volume":"14","author":"El-Sofany","year":"2024","journal-title":"Sci. Rep."},{"key":"ref20","article-title":"A multi-modal integrated deep neural network for the prediction of cardiovascular disease","author":"Evangelin Sonia","year":"2023","journal-title":"Autom. Remote. Control."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1357","DOI":"10.1080\/10255842.2024.2319706","article-title":"A comprehensive review on heart disease prognostication using different artificial intelligence algorithms","volume":"27","author":"Fathima","year":"2024","journal-title":"Comput. Methods Biomech. Biomed. Engin."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1162\/neco_a_01273","article-title":"A survey on deep learning for multimodal data fusion","volume":"32","author":"Gao","year":"2020","journal-title":"Neural Comput."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1111\/exsy.13254","article-title":"EDL-NSGA-II: ensemble deep learning framework with NSGA-II feature selection for heart disease prediction","volume":"40","author":"Gupta","year":"2023","journal-title":"Expert. Syst."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"109899","DOI":"10.1016\/j.bspc.2026.109899","article-title":"Deep learning advancements for cardiovascular diseases (CVDs) diagnosis: imaging modalities, challenges, and future perspectives","volume":"119","author":"Haq","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"911","DOI":"10.21037\/cdt.2020.03.09","article-title":"Artificial intelligence in personalized cardiovascular medicine and cardiovascular imaging","volume":"11","author":"Haq","year":"2020","journal-title":"Cardiovasc. Diagn. Ther."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"104983","DOI":"10.1016\/j.compbiomed.2021.104983","article-title":"Deep neural survival networks for CVD risk prediction: MESA","volume":"139","author":"Hathaway","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1093\/eurjpc\/zwad314","article-title":"Development and validation of cardiovascular risk prediction equations in 76,000 people with known cardiovascular disease","volume":"31","author":"Holt","year":"2023","journal-title":"Eur. J. Prev. Cardiol."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"101535","DOI":"10.1016\/j.imu.2024.101535","article-title":"A one-dimensional convolutional neural network-based method for cardiovascular disease prediction","volume":"49","author":"Honi","year":"2024","journal-title":"Inform. Med. Unlocked"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1804","DOI":"10.1016\/j.cjca.2024.07.014","article-title":"Use of artificial intelligence including multimodal systems in cardiovascular disease management","volume":"40","author":"Jaltotage","year":"2024","journal-title":"Canad. J. Cardiol. Open"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.jacc.2024.05.003","article-title":"Transforming cardiovascular care with artificial intelligence: from discovery to practice","volume":"84","author":"Khera","year":"2024","journal-title":"J. Am. Coll. Cardiol."},{"key":"ref31","article-title":"Ensemble deep learning for multimodal heart disease detection","author":"Krishna","year":"2023","journal-title":"IEEE Access"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"5467","DOI":"10.11591\/ijece.v11i6.pp5467-5476","article-title":"Hybrid deep learning model using recurrent neural network and gated recurrent unit for heart disease prediction","volume":"11","author":"Krishnan","year":"2021","journal-title":"Int. J. Electr. Comput. Eng."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"2058","DOI":"10.1093\/eurheartj\/ehz056","article-title":"Deep learning for cardiovascular medicine: a practical primer","volume":"40","author":"Krittanawong","year":"2019","journal-title":"Eur. Heart J."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"108635","DOI":"10.1016\/j.compbiomed.2024.108635","article-title":"A review of deep learning-based information fusion for medical multimodal classification tasks","volume":"177","author":"Li","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref35","article-title":"Heart failure prognosis risk assessment model based on multimodal data fusion","volume":"26","author":"Li","year":"2025","journal-title":"Egypt. Inform. J."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"157","DOI":"10.3390\/biomedicines10092157","article-title":"Interplay between artificial intelligence and biomechanics modeling in the cardiovascular disease prediction","volume":"10","author":"Li","year":"2022","journal-title":"Biomedicine"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1907","DOI":"10.1093\/eurheartj\/ehaf125","article-title":"Artificial intelligence to improve cardiovascular population health: state-of-the-art and future directions","volume":"46","author":"Meder","year":"2025","journal-title":"Front. Cardiovasc. Med."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1177\/0976500X241281490","article-title":"ML-powered internet of medical things structure for heart disease prediction","volume":"16","author":"Mulani","year":"2025","journal-title":"J. Pharmacol. Pharmacother."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"3707","DOI":"10.1007\/s11831-025-10411-8","article-title":"A comparative evaluation of deep learning architectures for prostate cancer segmentation: introducing TrionixNet with N-Core multi-attention mechanism","volume":"33","author":"Narayan","year":"2026","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"144","DOI":"10.3390\/diagnostics14020144","article-title":"Machine learning-based predictive models for detection of heart disease","volume":"14","author":"Ogunpola","year":"2024","journal-title":"Diagnostics"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"12023","DOI":"10.1200\/JCO.2024.42.16_suppl.12023","article-title":"Development and validation of a deep learning\u2013based cardiovascular disease risk prediction model for long-term breast cancer survivors","volume":"42","author":"Oh","year":"2024","journal-title":"J. Clin. Oncol."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1371\/journal.pone.0271723","article-title":"An evolutionary machine learning algorithm for cardiovascular disease risk prediction","volume":"17","author":"Ordikhani","year":"2022","journal-title":"PLoS One"},{"key":"ref43","article-title":"Federated deep learning for smart healthcare IoT: a privacy-preserving CVD screening model","author":"Otoum","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref44","article-title":"Multimodal data fusion for precision cardiology: current trends and future prospects","author":"Rahman","year":"2024","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"ref45","doi-asserted-by":"publisher","first-page":"121574","DOI":"10.1109\/access.2023.3328909","article-title":"A robust heart disease prediction system using hybrid deep neural networks","volume":"11","author":"Reshan","year":"2023","journal-title":"IEEE Access"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1186\/s40001-024-02044-7","article-title":"Cardiovascular disease diagnosis: a holistic approach using deep learning and machine learning","volume":"29","author":"Sadr","year":"2024","journal-title":"Front. Cardiovasc. Med."},{"key":"ref47","article-title":"A comprehensive survey on explainable multimodal data fusion for CVD risk stratification","author":"Saha","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"ref48","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1109\/JSEN.2011.2129506","article-title":"Fused hierarchical neural networks for cardiovascular disease diagnosis","volume":"12","author":"Sekar","year":"2012","journal-title":"IEEE Sensors J."},{"key":"ref49","doi-asserted-by":"publisher","first-page":"215","DOI":"10.5755\/j01.itc.52.1.32008","article-title":"Deep learning based cardiovascular disease risk factor prediction among type 2 diabetes mellitus patients","volume":"52","author":"Selvarathi","year":"2023","journal-title":"Inf. Technol. Control"},{"key":"ref50","doi-asserted-by":"publisher","first-page":"102040","DOI":"10.1016\/j.inffus.2023.102040","article-title":"A survey of multimodal information fusion for smart healthcare","volume":"102","author":"Shaik","year":"2024","journal-title":"Inf. Fusion"},{"key":"ref51","doi-asserted-by":"publisher","first-page":"3635","DOI":"10.1007\/s11831-025-10414-5","article-title":"A comprehensive study of enhanced computational approaches for breast cancer classification: comparative analysis with existing state of the art methods","volume":"33","author":"Singh","year":"","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref52","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1007\/s11831-025-10315-7","article-title":"A comprehensive study on deep learning models for the detection of diabetic retinopathy using pathological images","volume":"33","author":"Singh","year":"","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref53","article-title":"Artificial intelligence for cardiovascular disease risk prediction: review and future directions","author":"Singh","year":"2024","journal-title":"J. Cardiovasc. Comput. Tomogr."},{"key":"ref54","doi-asserted-by":"publisher","first-page":"3542","DOI":"10.1080\/07391102.2023.2298736","article-title":"Energy-aware heart disease prediction using ESMO and optimal deep learning model for healthcare monitoring in IoT","volume":"43","author":"Sornalakshmi","year":"2024","journal-title":"J. Biomol. Struct. Dynamics"},{"key":"ref55","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1093\/bib\/bbab569","article-title":"Multimodal deep learning for biomedical data fusion: a review","volume":"23","author":"Stahlschmidt","year":"2022","journal-title":"Brief. Bioinform."},{"key":"ref56","doi-asserted-by":"publisher","first-page":"126258","DOI":"10.1109\/access.2024.3447096","article-title":"Deep learning applications in ECG analysis and disease detection: an investigation study of recent advances","volume":"12","author":"Sumalatha","year":"2024","journal-title":"IEEE Access"},{"key":"ref57","doi-asserted-by":"publisher","first-page":"4808","DOI":"10.1093\/eurheartj\/ehae619","article-title":"Cardiovascular care with digital twin technology in the era of generative artificial intelligence","volume":"45","author":"Thangaraj","year":"2024","journal-title":"Eur. Heart J."},{"key":"ref58","doi-asserted-by":"publisher","first-page":"e25574","DOI":"10.1016\/j.heliyon.2024.e25574","article-title":"An automatic diagnostic model for detection and prognosis of cardiovascular disease using multimodal health record data","volume":"10","author":"Venkatesh","year":"2024","journal-title":"Heliyon"},{"key":"ref59","article-title":"IoT-cloud-based smart healthcare monitoring system for heart disease prediction via deep learning","author":"Vincent","year":"2022","journal-title":"Electronics"},{"key":"ref60","doi-asserted-by":"publisher","first-page":"1172","DOI":"10.1109\/TMI.2017.2655486","article-title":"Detecting cardiovascular disease from mammograms with deep learning","volume":"36","author":"Wang","year":"2017","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref61","doi-asserted-by":"publisher","first-page":"1418969","DOI":"10.3389\/fpsyt.2024.1418969","article-title":"Cardiovascular disease prediction model based on patient behavior patterns in deep learning","volume":"15","author":"Wang","year":"2024","journal-title":"Front. Psych."},{"key":"ref62","doi-asserted-by":"publisher","first-page":"736491","DOI":"10.3389\/fcvm.2021.736491","article-title":"A machine learningbased prediction model for cardiovascular risk in women with preeclampsia","volume":"8","author":"Wang","year":"2021","journal-title":"Front. Cardiovasc. Med."},{"key":"ref63","doi-asserted-by":"publisher","first-page":"107879","DOI":"10.1016\/j.cmpb.2023.107879","article-title":"DeepXplainer: An interpretable deep learning based approach for lung Cancer detection using explainable artificial intelligence","volume":"243","author":"Wani","year":"2024","journal-title":"Comput. Methods Prog. Biomed."},{"key":"ref64","doi-asserted-by":"publisher","first-page":"3142","DOI":"10.1001\/jamacardio.2023.3142","article-title":"Deep learning for cardiovascular imaging: a review","volume":"8","author":"Wehbe","year":"2023","journal-title":"JAMA Cardiol."},{"key":"ref65","doi-asserted-by":"publisher","first-page":"713191","DOI":"10.3389\/fcvm.2021.713191","article-title":"Circulating biomarkers for cardiovascular disease risk prediction in patients with cardiovascular disease","volume":"8","author":"Wong","year":"2021","journal-title":"Front. Cardiovasc. Med."},{"key":"ref66","article-title":"AI-powered CVD risk modeling from longitudinal multimodal imaging","author":"Yang","year":"2024","journal-title":"Front. Radiol."},{"key":"ref67","doi-asserted-by":"publisher","first-page":"14539","DOI":"10.1109\/jsen.2024.3373429","article-title":"DEEP-CARDIO: recommendation system for cardiovascular disease prediction using IoT network","volume":"24","author":"Yashudas","year":"2024","journal-title":"IEEE Sensors J."},{"key":"ref68","doi-asserted-by":"publisher","first-page":"8","DOI":"10.31083\/j.rcm2301008","article-title":"Genetic risk scores used in cardiovascular disease prediction models: a systematic review","volume":"23","author":"Yun","year":"2022","journal-title":"Rev. Cardiovasc. Med."},{"key":"ref69","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1155\/2021\/6260022","article-title":"Heart disease prediction based on the embedded feature selection method and deep neural network","volume":"2021","author":"Zhang","year":"2021","journal-title":"J. Healthcare Eng."},{"key":"ref70","doi-asserted-by":"publisher","first-page":"18505","DOI":"10.1109\/jiot.2023.3240536","article-title":"A physics-guided deep learning approach for functional assessment of cardiovascular disease in IoT-based smart health","volume":"10","author":"Zhang","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"ref71","author":"Zhu","year":"2023"},{"key":"ref72","article-title":"Dual-scale deep residual network for multimodal cardiovascular disease detection","volume":"171","author":"Zhu","year":"2025","journal-title":"Comput. Biol. Med."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1840804\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T05:46:34Z","timestamp":1782452794000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1840804\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,26]]},"references-count":72,"alternative-id":["10.3389\/frai.2026.1840804"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1840804","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,26]]},"article-number":"1840804"}}