Investigating the Amyloid-Tau-Neurodegeneration Framework in Alzheimer’s Disease Using Semi-Supervised Multimodal Imaging Data Fusion
Bibliographic record
Abstract
ABSTRACT INTRODUCTION Alzheimer’s 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. METHODS 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’ subject loadings were subsequently used to predict diagnosis (cognitively normal, mild cognitive impairment, dementia) and APOE4 status using LASSO logistic regression, and were compared against demographic, single-modality, and naïve fusion baselines. RESULTS While SuperBigFLICA modestly predicted cognitive decline (r = 0.21), SBF loadings-based models outperformed baselines (AUROC = 0.80 for diagnosis; 0.83 for APOE4 ). Amyloid alterations in sensory areas along the sensory–association 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. DISCUSSION Semi-supervised multimodal fusion improves prediction and reveals interpretable imaging patterns that predict APOE4 and clinical diagnoses better than traditional approaches.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".