AI-guided patient stratification improves outcomes and efficiency in the AMARANTH Alzheimer’s Disease clinical trial
Bibliographic record
Abstract
Alzheimer's Disease (AD) drug discovery has been hampered by patient heterogeneity, and the lack of sensitive tools for precise stratification. Here, we demonstrate that our robust and interpretable AI-guided tool (predictive prognostic model, PPM) enhances precision in patient stratification, improving outcomes and decreasing sample size for a AD clinical trial. The AMARANTH trial of lanabecestat, a BACE1 inhibitor, was deemed futile, as treatment did not change cognitive outcomes, despite reducing β-amyloid. Employing the PPM, we re-stratify patients precisely using baseline data and demonstrate significant treatment effects; that is, 46% slowing of cognitive decline for slow progressive patients at earlier stages of neurodegeneration. In contrast, rapid progressive patients did not show significant change in cognitive outcomes. Our results provide evidence for AI-guided patient stratification that is more precise than standard patient selection approaches (e.g. β-amyloid positivity) and has strong potential to enhance efficiency and efficacy of future AD 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 | 0.038 | 0.074 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".