{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T01:20:37Z","timestamp":1776129637182,"version":"3.50.1"},"reference-count":49,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T00:00:00Z","timestamp":1769558400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T00:00:00Z","timestamp":1769558400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems"],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Modelling the evolution of Alzheimer's disease (AD) requires a thorough spatiotemporal study of longitudinal neuroimaging data. We propose in this paper a novel deep learning framework that uses a parallel combination of Recurrent Neural Networks (RNNs) and Vision Transformers (ViT) to extract temporal disease dynamics and spatial structural changes from serial MRI data. While the RNN evaluates sequential dependencies across timepoints, the ViT branch uses self\u2010attention to derive hierarchical brain\u2010region characteristics. A stacked auto\u2010encoder (SAE) fuses these features into a compact representation, enhancing discriminative power while reducing redundancy. Fully connected layers are given the fused features in order to predict progression and classify AD (CN\/MCI\/AD). We used the ADNI dataset to test our proposed methodology. In terms of disease stage differentiation, our approach reaches state\u2010of\u2010the\u2010art accuracy of 92.3%. Compared to CNN or RNN\u2010only models, it considerably improves the prediction of the early conversion of MCI to AD (AUC\u2009=\u20090.94). When processing heterogeneous neuroimaging data, the SAE\u2010based fusion outperforms attention methods. With potential uses in customised treatment planning, this hybrid approach provides a clinically interpretable tool for longitudinal AD.<\/jats:p>","DOI":"10.1111\/exsy.70191","type":"journal-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T07:41:52Z","timestamp":1769672512000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Longitudinal Alzheimer\u2019s Disease Progression Modelling via Hybrid Vision Transformers and Recurrent Neural Networks With Cross\u2010Modal Feature Fusion"],"prefix":"10.1111","volume":"43","author":[{"given":"Sahbi","family":"Bahroun","sequence":"first","affiliation":[{"name":"LR16ES06 Laboratoire LIMTIC, Higher Institute of Computer Science University Tunis El Manar  Ariana Tunisia"}]},{"given":"Gwanggil","family":"Jeon","sequence":"additional","affiliation":[{"name":"Incheon National University  Incheon South Korea"}]}],"member":"311","published-online":{"date-parts":[[2026,1,28]]},"reference":[{"key":"e_1_2_12_2_1","article-title":"Convolutional Neural Networks for Alzheimer's Disease Detection on MRI Images","volume":"2","author":"Amir E.","year":"2021","journal-title":"Alzheimer's Disease Neuroimaging Initiative"},{"key":"e_1_2_12_3_1","article-title":"Hybvit: A Hybrid Vision Transformer for Multi\u2010Modal Alzheimer's Disease Detection Using Sequential 3D MRI and Clinical Data","volume":"78","author":"Chen J.","year":"2022","journal-title":"Medical Image Analysis"},{"issue":"3","key":"e_1_2_12_4_1","first-page":"287","article-title":"Volumetric Resnettransformer for Longitudinal Alzheimer's Disease Classification: A Multimodal Deep Learning Framework","volume":"6","author":"Chen Z.","year":"2024","journal-title":"Nature Machine Intelligence"},{"issue":"2","key":"e_1_2_12_5_1","first-page":"189","article-title":"Vit\u2010Lstm: Spatiotemporal Modeling of Alzheimer's Progression via 3D Swin Transformers and Recurrent Networks","volume":"6","author":"Chen Z.","year":"2024","journal-title":"Nature Machine Intelligence"},{"key":"e_1_2_12_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3237845"},{"issue":"1","key":"e_1_2_12_7_1","article-title":"Vision Transformers Outperform CNNs in Detecting Preclinical Alzheimer's Disease From Structural MRI","volume":"13","author":"Dosovitskiy A.","year":"2023","journal-title":"Scientific Reports"},{"key":"e_1_2_12_8_1","doi-asserted-by":"publisher","DOI":"10.1017\/S1041610209009405"},{"key":"e_1_2_12_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2020.06.008"},{"key":"e_1_2_12_10_1","article-title":"Masked Autoencoders for Medical Image Analysis: Self\u2010Supervised Pretraining of Vision Transformers on Unlabeled 3D Brain Mris","volume":"91","author":"He K.","year":"2023","journal-title":"Medical Image Analysis"},{"key":"e_1_2_12_11_1","volume-title":"5th International Conference on Computing Methodologies and Communication (ICCMC)","author":"Heta A.","year":"2021"},{"issue":"15","key":"e_1_2_12_12_1","article-title":"Recurrent Neural Networks: A Comprehensive Review of Architectures, Variants, and Applications","volume":"9","author":"Ibomoiye M. D.","year":"2024","journal-title":"MDPI Information Journal"},{"issue":"3","key":"e_1_2_12_13_1","first-page":"869","article-title":"The Alzheimer's Disease Neuroimaging Initiative 3 (Adni\u20103): MRI and Pet Technical Protocols and Biomarker Classifications","volume":"19","author":"Jack C. R.","year":"2023","journal-title":"Alzheimer's & Dementia"},{"key":"e_1_2_12_14_1","article-title":"Survey on Contrastive Self\u2010Supervised Learning for Medical Image Analysis","volume":"138","author":"Jaiswal A.","year":"2023","journal-title":"Artificial Intelligence in Medicine"},{"issue":"4","key":"e_1_2_12_15_1","first-page":"1123","article-title":"Crossmodal Contrastive Learning for Vision Transformers in Neuroimaging: Aligning t1w and t2w MRI Embeddings","volume":"43","author":"Jaiswal A.","year":"2024","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"2","key":"e_1_2_12_16_1","first-page":"666","article-title":"Alzheimer's Disease Drug Development Pipeline: 2023","volume":"9","author":"Jeffrey C.","year":"2023","journal-title":"Alzheimer's & Dementia: Translational Research & Clinical Interventions"},{"issue":"8","key":"e_1_2_12_17_1","first-page":"2236","article-title":"Fedcor: Correlation\u2010Based Active Client Selection for Heterogeneous Federated Learning in Medical Imaging","volume":"42","author":"Jiang M.","year":"2023","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"6","key":"e_1_2_12_18_1","first-page":"1781","article-title":"Longitudinal 3D CNN\u2010Lstm for Alzheimer's Disease Progression Modeling From Sequential MRI","volume":"42","author":"Khvostikov A.","year":"2023","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"e_1_2_12_19_1","article-title":"Hybrid CNN\u2010Rnn Architecture for Longitudinal FMRI Analysis in Neurodegenerative Disorders","volume":"267","author":"Khvostikov A.","year":"2023","journal-title":"NeuroImage"},{"key":"e_1_2_12_20_1","article-title":"Temporal Modeling of Neurodegenerative Progression From Fmri via Hybrid 3D CNN\u2010Rnn Architectures","volume":"272","author":"Khvostikov A.","year":"2023","journal-title":"NeuroImage"},{"key":"e_1_2_12_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2017.7950647"},{"key":"e_1_2_12_22_1","article-title":"Self\u2010Supervised Pretraining of CNN\u2010Rnn Architectures for Longitudinal Neuroimaging Analysis With Limited Labeled Data","volume":"84","author":"Kumar A.","year":"2023","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"e_1_2_12_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2019.06.4945"},{"key":"e_1_2_12_24_1","first-page":"972","article-title":"Multi\u2010Modal Multi\u2010Task Learning for Joint Prediction of Multiple Regression and Classification Variables in Alzheimer's Disease","volume":"183","author":"Li H.\u2010I.","year":"2018","journal-title":"NeuroImage"},{"issue":"7","key":"e_1_2_12_25_1","first-page":"1956","article-title":"Interpretable Spatiotemporal Modeling of Alzheimer's Progression Using CNN\u2010Attention\u2010Lstm Networks","volume":"42","author":"Li X.","year":"2023","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"3","key":"e_1_2_12_26_1","first-page":"725","article-title":"Graph\u2010Ad: A Graph Neural Network for Analysis of Alzheimer's Disease With Geometric Deep Learning","volume":"25","author":"Li X.","year":"2021","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"e_1_2_12_27_1","article-title":"Deepmrs: An End\u2010to\u2010End Deep Learning Framework for Multi\u2010Modal MRI\u2010Based Alzheimer's Disease Classification","volume":"67","author":"Liu M.","year":"2020","journal-title":"Medical Image Analysis"},{"key":"e_1_2_12_28_1","first-page":"412","volume-title":"Medical Image Computing and Computer Assisted Intervention","author":"Liu Y.","year":"2024"},{"key":"e_1_2_12_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(24)01296-0"},{"key":"e_1_2_12_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.103339"},{"key":"e_1_2_12_31_1","doi-asserted-by":"publisher","DOI":"10.3390\/make6010024"},{"issue":"1","key":"e_1_2_12_32_1","article-title":"Spatiotemporal Graph Neural Networks for Modeling Functional Network Deterioration in Alzheimer's Disease","volume":"15","author":"Park J.","year":"2024","journal-title":"Nature Communications"},{"key":"e_1_2_12_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(20)32205-4"},{"issue":"103000","key":"e_1_2_12_34_1","first-page":"1361","article-title":"Progression Along Data\u2010Driven Disease Timelines Is Predictive of Alzheimer's Disease in a Population\u2010Based Cohort","volume":"91","author":"Reza A.","year":"2024","journal-title":"Medical Image Analysis"},{"issue":"1","key":"e_1_2_12_35_1","first-page":"1","article-title":"Transformer\u2010Based Deep Learning for Predicting Alzheimer's Disease Progression Considering Neuroimaging and Tabular Clinical Data","volume":"11","author":"Shaker A.","year":"2021","journal-title":"Scientific Reports"},{"key":"e_1_2_12_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-024-02105-8"},{"key":"e_1_2_12_37_1","volume-title":"Conference ICICPE","author":"Uttam K.","year":"2023"},{"issue":"118233","key":"e_1_2_12_38_1","first-page":"1053","article-title":"Progression Along Data\u2010Driven Disease Timelines Is Predictive of Alzheimer's Disease in a Population\u2010Based Cohort","volume":"238","author":"Vikram V.","year":"2021","journal-title":"NeuroImage"},{"key":"e_1_2_12_39_1","article-title":"Resnet\u2010Transformer Hybrid Network for Multi\u2010Stage Alzheimer's Disease Classification From 3D MRI","volume":"89","author":"Wang L.","year":"2023","journal-title":"Image Analysis"},{"key":"e_1_2_12_40_1","article-title":"Resnet\u2010Transformergru: A Hierarchical Hybrid Network for Longitudinal Alzheimer's Disease Progression Modeling","volume":"89","author":"Wang L.","year":"2023","journal-title":"Medical Image Analysis"},{"key":"e_1_2_12_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102591"},{"key":"e_1_2_12_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2016.10.006"},{"issue":"12","key":"e_1_2_12_43_1","first-page":"3336","article-title":"Structural Graph Convolutional Network With Spatial\u2010Temporal Transformer for Alzheimer's Disease Analysis","volume":"40","author":"Xiao Z.","year":"2021","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"e_1_2_12_44_1","doi-asserted-by":"publisher","DOI":"10.54254\/2755\u20102721\/75\/20240535"},{"issue":"4","key":"e_1_2_12_45_1","first-page":"512","article-title":"Deep Learning for Longitudinal Neuroimaging Analysis in Neurodegenerative Disorders: A Robust Framework for Handling Variability","volume":"26","author":"Yang X.","year":"2023","journal-title":"Nature Neuroscience"},{"issue":"2","key":"e_1_2_12_46_1","first-page":"987","article-title":"Lightweight CNN\u2010Gru Architecture Search for Efficient Alzheimer's Disease Classification From MRI","volume":"28","author":"Yang X.","year":"2024","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"issue":"5","key":"e_1_2_12_47_1","first-page":"1321","article-title":"Mobilevit\u2010Gru: A Lightweight Hybrid Architecture for Alzheimer's Disease Classification From 3D MRI","volume":"43","author":"Yang X.","year":"2024","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"e_1_2_12_48_1","first-page":"123","article-title":"Robust Feature Integration in Stacked Denoising Auto\u2010Encoders for Multimodal Data Fusion","volume":"158","author":"Zhang L.","year":"2023","journal-title":"Neural Networks"},{"key":"e_1_2_12_49_1","article-title":"Cross\u2010Modal CNN\u2010Rnn Fusion of Neuroimaging and Cognitive Biomarkers for Alzheimer's Disease Diagnosis","volume":"88","author":"Zhang Y.","year":"2023","journal-title":"Medical Image Analysis"},{"key":"e_1_2_12_50_1","article-title":"Multi\u2010Modal Late\u2010Fusion CNN for Alzheimer's Disease Diagnosis Using Structural MRI, Pet, and CSF Biomarkers","volume":"89","author":"Zhang Y.","year":"2023","journal-title":"Medical Image Analysis"}],"container-title":["Expert Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70191","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/exsy.70191","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70191","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T23:21:59Z","timestamp":1773012119000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/exsy.70191"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,28]]},"references-count":49,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1111\/exsy.70191"],"URL":"https:\/\/doi.org\/10.1111\/exsy.70191","archive":["Portico"],"relation":{},"ISSN":["0266-4720","1468-0394"],"issn-type":[{"value":"0266-4720","type":"print"},{"value":"1468-0394","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,28]]},"assertion":[{"value":"2025-06-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70191"}}