Brain metabolic imaging-based model identifies cognitive stability in prodromal Alzheimer’s disease
Bibliographic record
Abstract
The recent approval of anti-amyloid pharmaceuticals for the treatment of Alzheimer's disease (AD) has created a pressing need for the ability to accurately identify optimal candidates for anti-amyloid therapy, specifically those with evidence for incipient cognitive decline, since patients with mild cognitive impairment (MCI) may remain stable for several years even with positive AD biomarkers. Using fluorodeoxyglucose PET and biomarker data from 594 ADNI patients, a neural network ensemble was trained to forecast cognition from MCI diagnostic baseline. Training data comprised PET studies of patients with biological AD. The ensemble discriminated between progressive and stable prodromal subjects (MCI with positive amyloid and tau) at baseline with 88.6% area-under-curve, 88.6% (39/44) accuracy, 73.7% (14/19) sensitivity and 100% (25/25) specificity in the test set. It also correctly classified all other test subjects (healthy or AD continuum subjects across the cognitive spectrum) with 86.4% accuracy (206/239), 77.4% sensitivity (33/42) and 88.23% (165/197) specificity. By identifying patients with prodromal AD who will not progress to dementia, our model could significantly reduce overall societal burden and cost if implemented as a screening tool. The model's high positive predictive value in the prodromal test set makes it a practical means for selecting candidates for anti-amyloid therapy and trials.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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".