{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T06:01:47Z","timestamp":1785132107233,"version":"3.55.0"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T00:00:00Z","timestamp":1785110400000},"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:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Alzheimer\u2019s disease (AD) is a progressive neurodegenerative disorder with the gradual loss of cognitive functions and neuronal degeneration. Early and accurate diagnosis is essential for timely therapeutic intervention and improved patient management. However, effectively integrating complementary multimodal information for reliable AD classification remains a significant challenge.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study proposes TriFusion-ADFormer, a multimodal deep learning framework for multiclass classification of Alzheimer\u2019s disease (AD), mild cognitive impairment (MCI), and cognitively normal (CN) subjects. The framework extracts structural MRI features and MRI-derived clinical text summary based on volumetric measurements and cognitive assessment features such as MMSE, GDS, Global CDR, FAQ, and NPI-Q, then fuses them to classify the disease.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed TriFusion-ADFormer achieved an overall classification accuracy of 86.0%, a Macro AUC of 0.93, and an F1-score of 86.0% for multiclass AD classification. Moreover, the MRI-based clinical summaries were also consistently consistent with structural abnormalities typically associated with AD, such as diffuse brain atrophy, which further supports the interpretability of the proposed framework.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The results show that the combination of multimodal information from structural MRI, semantic clinical summary generated from the MRI, and cognitive assessment scores enhances the accuracy and interpretability of Alzheimer\u2019s diagnosis. The results highlight the potential of incorporating complementary imaging, semantic, and cognitive features for better multiclass classification of AD, MCI, and CN in a transformer framework.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1849315","type":"journal-article","created":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T05:40:48Z","timestamp":1785130848000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["TriFusion-ADFormer: a deep learning framework for early Alzheimer\u2019s disease detection using MRI and cognitive metrics"],"prefix":"10.3389","volume":"9","author":[{"given":"S.","family":"Sabari Vasan","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":"P.","family":"Jayalakshmi","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":[[2026,7,27]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"3135","DOI":"10.3390\/diagnostics15243135","article-title":"Multimodal self-supervised learning for early Alzheimer's: cross-modal MRI-PET, longitudinal signals, and site invariance","volume":"15","author":"Ali","year":"2025","journal-title":"Diagnostics (Basel, Switzerland)"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"77131","DOI":"10.1109\/ACCESS.2020.2989396","article-title":"Alzheimer's disease detection by using deep learning algorithms: a mini-review","volume":"8","author":"Al-Shoukry","year":"2020","journal-title":"IEEE Access"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"464","DOI":"10.3390\/make6010024","article-title":"Alzheimer\u2019s disease detection using deep learning on neuroimaging: a systematic review","volume":"6","author":"Alsubaie","year":"2024","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"ref4","year":""},{"key":"ref5","doi-asserted-by":"publisher","first-page":"e38544","DOI":"10.7759\/cureus.38544","article-title":"Neuroimaging in Alzheimer's disease for early diagnosis: a comprehensive review","volume":"15","author":"Aramadaka","year":"2023","journal-title":"Cureus"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1186\/s40708-023-00195-7","article-title":"A systematic review on machine learning and deep learning techniques in the effective diagnosis of Alzheimer\u2019s disease","volume":"10","author":"Arya","year":"2023","journal-title":"Brain Informatics"},{"key":"ref7","first-page":"2404","volume-title":"MedBLIP: Bootstrapping Language-Image pre-Training from 3D Medical Images and Texts","author":"Chen","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1563016","DOI":"10.3389\/frai.2025.1563016","article-title":"An efficient method for early Alzheimer\u2019s disease detection based on MRI images using deep convolutional neural networks","volume":"8","author":"Dardouri","year":"2025","journal-title":"Front. Artif. Intell."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1658776","DOI":"10.3389\/fnins.2025.1658776","article-title":"A multi-view multimodal deep learning framework for Alzheimer's disease diagnosis","volume":"19","author":"Feng","year":"2025","journal-title":"Front. Neurosci."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1111\/joim.20098","article-title":"Implementing early detection of cognitive impairment in primary care to improve care for older adults","volume":"298","author":"Fowler","year":"2025","journal-title":"J. Intern. Med."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"2014","DOI":"10.1093\/jamia\/ocac168","article-title":"Multimodal attention-based deep learning for Alzheimer's disease diagnosis","volume":"29","author":"Golovanevsky","year":"2022","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1527582","DOI":"10.3389\/fninf.2025.1527582","article-title":"Contrastive self-supervised learning for neurodegenerative disorder classification","volume":"19","author":"Gryshchuk","year":"2025","journal-title":"Front. Neuroinform."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1641548","DOI":"10.3389\/fneur.2025.1641548","article-title":"Meta-analysis of the diagnostic efficacy of transformer-based multimodal fusion deep learning models in early Alzheimer's disease","volume":"16","author":"Guo","year":"2025","journal-title":"Front. Neurol."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1083","DOI":"10.3844\/jcssp.2025.1083.1098","article-title":"Deep learning in early Alzheimer's disease detection: a comprehensive survey of classification, segmentation, and feature extraction methods","volume":"21","author":"Hafeez","year":"2025","journal-title":"J. Comput. Sci."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1102869","DOI":"10.3389\/fnagi.2023.1102869","article-title":"Vision transformers for the prediction of mild cognitive impairment to Alzheimer\u2019s disease progression using mid-sagittal sMRI","volume":"15","author":"Hoang","year":"2023","journal-title":"Front. Aging Neurosci."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1007\/s13246-022-01165-9","article-title":"Multi-modality MRI for Alzheimer's disease detection using deep learning","volume":"45","author":"Houria","year":"2022","journal-title":"Phys. Eng. Sci. Med."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"100362","DOI":"10.1016\/j.tjpad.2025.100362","article-title":"Early Alzheimer's disease (mild cognitive impairment or mild dementia): prevalence, diagnostics, treatment options, and guidelines in Asia, Australasia, and Pacific nations","volume":"12","author":"Hsu","year":"2025","journal-title":"J. Prev Alzheimers Dis."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"113718","DOI":"10.1109\/access.2025.3582853","article-title":"Multi-modal integration analysis of Alzheimer's disease using large language models and knowledge graphs","volume":"13","author":"Kiguchi","year":"2025","journal-title":"IEEE Access: Pract. Innov. Open Sol."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"102762","DOI":"10.1016\/j.media.2023.102762","article-title":"Transforming medical imaging with transformers? A comparative review of key properties, current progress, and future perspectives","volume":"85","author":"Li","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"859","DOI":"10.3390\/biology10090859","article-title":"An automated in-depth feature learning algorithm for breast abnormality prognosis and robust characterization from mammography images using deep transfer learning","volume":"10","author":"Mahmood","year":"2021","journal-title":"Biology"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"165779","DOI":"10.1109\/access.2020.3021343","article-title":"A brief survey on breast cancer diagnosis with deep learning schemes using multi-image modalities","volume":"8","author":"Mahmood","year":"2020","journal-title":"IEEE Access"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e0263126","DOI":"10.1371\/journal.pone.0263126","article-title":"Breast lesions classifications of mammographic images using a deep convolutional neural network-based approach","volume":"17","author":"Mahmood","year":"2022","journal-title":"PLoS One"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"113623","DOI":"10.1109\/access.2023.3313977","article-title":"Recent advancements and prospects in active deep learning for medical image segmentation and classification","volume":"11","author":"Mahmood","year":"2023","journal-title":"IEEE Access: Pract. Innov. Open Sol."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"106721","DOI":"10.1016\/j.bspc.2024.106721","article-title":"Alzheimer\u2019s disease unveiled: cutting-edge multi-modal neuroimaging and computational methods for enhanced diagnosis","volume":"97","author":"Mahmood","year":"","journal-title":"Biomed. Signal Process. Control"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s40537-025-01114-9","article-title":"Breast cancer diagnosis with MFF-HistoNet: a multi-modal feature fusion network integrating CNNs and quantum tensor networks","volume":"12","author":"Mahmood","year":"2025","journal-title":"J. Big Data"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"123747","DOI":"10.1016\/j.eswa.2024.123747","article-title":"Harnessing the power of radiomics and deep learning for improved breast cancer diagnosis with multiparametric breast mammography","volume":"249","author":"Mahmood","year":"","journal-title":"Expert Syst. Appl."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"2976","DOI":"10.3390\/electronics14152976","article-title":"Evaluation of vision transformers for multi-organ tumor classification using MRI and CT imaging","volume":"14","author":"Mart\u00edn","year":"2025","journal-title":"Electronics"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"e70175","DOI":"10.1002\/alz.70175","article-title":"Early detection of Alzheimer's disease using deep learning methods","volume":"21","author":"Mmadumbu","year":"2025","journal-title":"Alzheimers Dement."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"101551","DOI":"10.1016\/j.imu.2024.101551","article-title":"Detection of Alzheimer's disease using deep learning models: a systematic literature review","volume":"50","author":"Mohammed","year":"2024","journal-title":"Inform. Med. Unlocked"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"3798","DOI":"10.1038\/s41598-025-33957-w","article-title":"Enhancing Alzheimer\u2019s disease classification with a transformer-based model using self-supervised learning","volume":"16","author":"Priyadharshini","year":"2026","journal-title":"Sci. Rep."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1016\/j.dadm.2018.08.013","article-title":"Fusion of deep learning models of MRI scans, Mini-mental state examination, and logical memory test enhances the diagnosis of mild cognitive impairment","volume":"10","author":"Qiu","year":"2018","journal-title":"Alzheimers Dement."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1107","DOI":"10.3390\/bioengineering12101107","article-title":"NeuroNet-AD: a multimodal deep learning framework for multiclass Alzheimer's disease diagnosis","volume":"12","author":"Rahman","year":"2025","journal-title":"Bioengineering"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1557177","DOI":"10.3389\/fninf.2025.1557177","article-title":"Advancements in deep learning for early diagnosis of Alzheimer\u2019s disease using multimodal neuroimaging: challenges and future directions","volume":"19","author":"Raza","year":"2025","journal-title":"Front. Neuroinform."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"114984","DOI":"10.1016\/j.expneurol.2024.114984","article-title":"Neuro-inflammatory pathways in COVID-19-induced central nervous system injury: implications for prevention and treatment strategies","volume":"382","author":"Raza","year":"2024","journal-title":"Exp. Neurol."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"112518","DOI":"10.1016\/j.asoc.2024.112518","article-title":"Robust kidney carcinoma prognosis and characterization using Swin-ViT and DeepLabV3+ with multi-model transfer learning","volume":"170","author":"Rehman","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"43242","DOI":"10.1038\/s41598-025-27360-8","article-title":"Early detection of Alzheimer\u2019s disease progression: comparative evaluation of deep learning models","volume":"15","author":"Shetty","year":"2025","journal-title":"Sci. Rep."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"953","DOI":"10.1007\/s00062-021-01057-7","article-title":"Systematic review of different neuroimaging correlates in mild cognitive impairment and Alzheimer's disease","volume":"31","author":"Talwar","year":"2021","journal-title":"Clin. Neuroradiol."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/s12938-024-01204-4","article-title":"Multimodal diagnosis model of Alzheimer's disease based on an improved transformer","volume":"23","author":"Tang","year":"2024","journal-title":"Biomed. Eng. Online"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"100222","DOI":"10.1016\/j.dscb.2025.100222","article-title":"Neuroimaging biomarkers: a critical review of their role in neurological disease diagnosis and management","volume":"18","author":"Wankhede","year":"2025","journal-title":"Brain Disorders"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"3420","DOI":"10.3390\/s23073420","article-title":"High-resolution Swin transformer for automatic medical image segmentation","volume":"23","author":"Wei","year":"2023","journal-title":"Sensors"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"108979","DOI":"10.1016\/j.compbiomed.2024.108979","article-title":"A transformer-based unified multimodal framework for Alzheimer's disease assessment","volume":"180","author":"Yu","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"108795","DOI":"10.1016\/j.jneumeth.2020.108795","article-title":"Multi-modal neuroimaging feature fusion for diagnosis of Alzheimer's disease","volume":"341","author":"Zhang","year":"2020","journal-title":"J. Neurosci. Methods"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1849315\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T05:40:48Z","timestamp":1785130848000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1849315\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,27]]},"references-count":42,"alternative-id":["10.3389\/frai.2026.1849315"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1849315","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,27]]},"article-number":"1849315"}}