{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T14:50:45Z","timestamp":1791298245866,"version":"4.1.0"},"posted":{"date-parts":[[2025,12,15]]},"group-title":"Neurology","reference-count":46,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T00:00:00Z","timestamp":1765756800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,12,15]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                <jats:sec>\n                  <jats:title>INTRODUCTION<\/jats:title>\n                  <jats:p>Alzheimer\u2019s disease (AD) is heterogeneous, complicating diagnosis and prognosis. Uncovering patterns that link abnormalities across amyloid-tau-neurodegeneration (A-T-N) framework may improve prediction of clinical diagnosis.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>METHODS<\/jats:title>\n                  <jats:p>\n                    We applied SuperBigFLICA (SBF), a semi-supervised multimodal data fusion method, to maps of gray matter density, cortical thickness, pial surface area, amyloid PET, and tau PET in 274 ADNI-3 participants. The model was trained to derive 50 latent components most predictive of a continuous measure of cognitive decline. Latent components\u2019 subject loadings were subsequently used to predict diagnosis (cognitively normal, mild cognitive impairment, dementia) and\n                    <jats:italic>APOE4<\/jats:italic>\n                    status using LASSO logistic regression, and were compared against demographic, single-modality, and na\u00efve fusion baselines.\n                  <\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>RESULTS<\/jats:title>\n                  <jats:p>\n                    While SuperBigFLICA modestly predicted cognitive decline (r = 0.21), SBF loadings-based models outperformed baselines (AUROC = 0.80 for diagnosis; 0.83 for\n                    <jats:italic>APOE4<\/jats:italic>\n                    ). Amyloid alterations in sensory areas along the sensory\u2013association axis best separated dementia, while a multimodal A-T-N pattern was related to early cognitive decline. Subject loadings on these two patterns were associated with cerebrospinal fluid (CSF) biomarkers, highlighting how CSF AD biomarkers relate to spatial patterns of brain A-T-N burden.\n                  <\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>DISCUSSION<\/jats:title>\n                  <jats:p>\n                    Semi-supervised multimodal fusion improves prediction and reveals interpretable imaging patterns that predict\n                    <jats:italic>APOE4<\/jats:italic>\n                    and clinical diagnoses better than traditional approaches.\n                  <\/jats:p>\n                <\/jats:sec>","DOI":"10.64898\/2025.12.11.25341830","type":"posted-content","created":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T01:15:20Z","timestamp":1765847720000},"source":"Crossref","is-referenced-by-count":1,"title":["Investigating the Amyloid-Tau-Neurodegeneration Framework in Alzheimer\u2019s Disease Using Semi-Supervised Multimodal Imaging Data Fusion"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3141-0104","authenticated-orcid":false,"given":"You","family":"Cheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adri\u00e1n","family":"Medina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2562-9617","authenticated-orcid":false,"given":"Cole","family":"Korponay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3373-3193","authenticated-orcid":false,"given":"Christian F.","family":"Beckmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Harper","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lisa","family":"Nickerson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"the Alzheimer\u2019s Disease Neuroimaging Initiative","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2025121712211401000_2025.12.11.25341830v1.1","unstructured":"Alzheimer, Association . Alzheimer\u2019s Disease Facts and Figures. 2025."},{"key":"2025121712211401000_2025.12.11.25341830v1.2","unstructured":"Wolk DA , Dickerson BC . Clinical features and diagnosis of Alzheimer disease. UpToUpdate 2023."},{"key":"2025121712211401000_2025.12.11.25341830v1.3","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/awm336"},{"key":"2025121712211401000_2025.12.11.25341830v1.4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2011.01.008"},{"key":"2025121712211401000_2025.12.11.25341830v1.5","doi-asserted-by":"publisher","DOI":"10.1212\/01.wnl.0000324924.91351.7d"},{"key":"2025121712211401000_2025.12.11.25341830v1.6","doi-asserted-by":"publisher","DOI":"10.3233\/JAD-179920"},{"key":"2025121712211401000_2025.12.11.25341830v1.7","doi-asserted-by":"publisher","DOI":"10.1186\/S12874-024-02284-5"},{"key":"2025121712211401000_2025.12.11.25341830v1.8","doi-asserted-by":"publisher","DOI":"10.1186\/S12877-024-05293-7"},{"key":"2025121712211401000_2025.12.11.25341830v1.9","doi-asserted-by":"publisher","DOI":"10.1016\/J.NEUROIMAGE.2019.01.031"},{"key":"2025121712211401000_2025.12.11.25341830v1.10","doi-asserted-by":"publisher","DOI":"10.1002\/ALZ.13565"},{"key":"2025121712211401000_2025.12.11.25341830v1.11","doi-asserted-by":"publisher","DOI":"10.1016\/J.NICL.2018.101645"},{"key":"2025121712211401000_2025.12.11.25341830v1.12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2019.02.007"},{"key":"2025121712211401000_2025.12.11.25341830v1.13","doi-asserted-by":"publisher","DOI":"10.3389\/FNEUR.2020.576029"},{"key":"2025121712211401000_2025.12.11.25341830v1.14","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2021.688926"},{"key":"2025121712211401000_2025.12.11.25341830v1.15","doi-asserted-by":"publisher","DOI":"10.1038\/s41398-024-02819-w"},{"key":"2025121712211401000_2025.12.11.25341830v1.16","unstructured":"Ajmera S , Rajagopal S , Ur Rehman R , Sridharan D. Infra-slow brain dynamics as a marker for cognitive function and decline. Adv Neural Inf Process Syst, vol. 32, 2019."},{"key":"2025121712211401000_2025.12.11.25341830v1.17","doi-asserted-by":"publisher","DOI":"10.3389\/FNAGI.2023.1195424\/PDF"},{"key":"2025121712211401000_2025.12.11.25341830v1.18","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/awm288"},{"key":"2025121712211401000_2025.12.11.25341830v1.19","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102050"},{"key":"2025121712211401000_2025.12.11.25341830v1.20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2010.09.073"},{"key":"2025121712211401000_2025.12.11.25341830v1.21","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.20508"},{"key":"2025121712211401000_2025.12.11.25341830v1.22","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.20166"},{"key":"2025121712211401000_2025.12.11.25341830v1.23","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3218720"},{"key":"2025121712211401000_2025.12.11.25341830v1.24","doi-asserted-by":"publisher","DOI":"10.1212\/wnl.43.11.2412-a"},{"key":"2025121712211401000_2025.12.11.25341830v1.25","doi-asserted-by":"publisher","DOI":"10.1001\/archneur.65.8.1091"},{"key":"2025121712211401000_2025.12.11.25341830v1.26","unstructured":"Alzheimer\u2019s Disease Neuroimaging Initiative. Alzheimer\u2019s Disease Neuroimaging Initiative 3 (ADNI3) Protocol 2016."},{"key":"2025121712211401000_2025.12.11.25341830v1.27","doi-asserted-by":"publisher","DOI":"10.1016\/J.JALZ.2016.10.006"},{"key":"2025121712211401000_2025.12.11.25341830v1.28","unstructured":"Alzheimer\u2019s Disease Neuroimaging Initiative. ADNI3 PET Technical Procedures Manual Version 2.0 2016."},{"key":"2025121712211401000_2025.12.11.25341830v1.29","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-018-0235-4"},{"key":"2025121712211401000_2025.12.11.25341830v1.30","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.852659"},{"key":"2025121712211401000_2025.12.11.25341830v1.31","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2011.00013"},{"key":"2025121712211401000_2025.12.11.25341830v1.32","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.596855"},{"key":"2025121712211401000_2025.12.11.25341830v1.33","unstructured":"Andersson JLR , Jenkinson M , Smith S. Non-linear registration aka Spatial normalisation FMRIB Technial Report TR07JA2. 2007."},{"key":"2025121712211401000_2025.12.11.25341830v1.34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2004.07.051"},{"key":"2025121712211401000_2025.12.11.25341830v1.35","doi-asserted-by":"publisher","DOI":"10.1006\/nimg.2001.0786"},{"key":"2025121712211401000_2025.12.11.25341830v1.36","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/awm184"},{"key":"2025121712211401000_2025.12.11.25341830v1.37","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2012.01.021"},{"key":"2025121712211401000_2025.12.11.25341830v1.38","unstructured":"Landau S , Ward TJ , Murphy A , Jagust W. Flortaucipir (AV-1451) processing methods. Alzheimer\u2019s Disease Neuroimaging Initiative 2016."},{"key":"2025121712211401000_2025.12.11.25341830v1.39","unstructured":"Landau S , Jagust W. Florbetapir processing methods. Alzheimer\u2019s Disease Neuroimaging Initiative 2015."},{"key":"2025121712211401000_2025.12.11.25341830v1.40","unstructured":"Landau S , Koeppe R , Jagust W. Florbetaben processing and positivity threshold derivation. Alzheimer\u2019s Dis Neuro-Imaging Initiat 2011."},{"key":"2025121712211401000_2025.12.11.25341830v1.41","unstructured":"Kolibash SA , Minhas D , Lopresti BJ . Centiloid Level-2 Analysis of [18F] Florbetaben (FBB) and [18F] Florbetapir (FBP) PET Image Data using the ADNI Pipeline. 2024. LONI n.d. https:\/\/adni.loni.usc.edu\/wp-content\/themes\/freshnews-dev-v2\/documents\/pet\/ADNI%20Centiloids%20Final.pdf (accessed November 20, 2025)."},{"key":"2025121712211401000_2025.12.11.25341830v1.42","doi-asserted-by":"publisher","DOI":"10.1186\/s13195-019-0525-9"},{"key":"2025121712211401000_2025.12.11.25341830v1.43","doi-asserted-by":"publisher","DOI":"10.1002\/ALZ.12638"},{"key":"2025121712211401000_2025.12.11.25341830v1.44","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-29295-9"},{"key":"2025121712211401000_2025.12.11.25341830v1.45","doi-asserted-by":"publisher","DOI":"10.1016\/J.NEURON.2021.06.016"},{"key":"2025121712211401000_2025.12.11.25341830v1.46","doi-asserted-by":"publisher","DOI":"10.1101\/2025.05.22.655469"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2025.12.11.25341830","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T20:21:27Z","timestamp":1766002887000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2025.12.11.25341830"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,15]]},"references-count":46,"URL":"https:\/\/doi.org\/10.64898\/2025.12.11.25341830","relation":{},"subject":[],"published":{"date-parts":[[2025,12,15]]},"subtype":"preprint"}}