Patient‐level predicting AD onset using lifespan volumetric trajectories
Bibliographic record
Abstract
BACKGROUND: Predicting dementia risk from neuroimaging and cognitive data is vital for early Alzheimer's disease (AD) management. Coupe [2019] and others have shown that the volume of certain anatomical structures deviate from the normal trajectories. We aim to predict individual AD progression risk by analyzing deviations from expected age and sex-based volumetric measurements at the baseline. METHOD: We utilized T1w MRI scans from several databases: (N Scans, N subjects, age range) : ADNI1,2,3 (8697, 2118, 50-97y), AIBL (1242, 667, 55-97y), HCP (1113, 1113, 28-36y), ICBM (341, 341, 18-80y), MCSA (1801,1801, 49-89y), NIHPD (1089, 442,4-22y), NKI (2306, 1326, 6-85y), OASIS1,2,3 (3212, 1802, 18-97y), UK Biobank (47396, 42912, 44-83y), PreventAD (2400, 387, 54-88y) and TRIAD (914,20-91y) and processed them with AssemblyNET [Coupe 2019]. We used scans from UKBB, ICBM, NKI, HCP, and NIHPD studies, along with half of the cognitively normal (CN) subjects from ADNI1,2,3, to model healthy aging trajectories with cubic b-splines for each brain structure from ages 10 to 90 using a Bayesian multilevel model. We used baseline scans from remaining CN subjects (N = 984, 73 progressed to AD) and MCI subjects (N = 1396, 395 progressed) to calculate deviation from age and sex expected volumes as estimated for 70 ROIs extracted by AssemblyNET. These values, along with sex and baseline diagnosis, were used to perform time-to-event modelling of conversion to AD. We employed a linear Survival Support Vector Machine within a 10-fold cross-validation loop. Additionally, permutation importance was used to identify important ROIs. RESULT: Our results demonstrate that the proposed method effectively identifies individuals with varying levels of risk for AD conversion, achieving a concordance index of 0.82(0.04). The five most important features identified by the method are baseline diagnosis (CN or MCI), and volumes of Amygdala, Inferior lateral ventricles, Superior temporal gyrus and Superior frontal gyrus. CONCLUSION: We have developed a library of healthy aging trajectories for 70 anatomical structures, demonstrating its effectiveness in identifying subjects at high risk of progressing to Alzheimer's Dementia.
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 | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".