Machine learning–enhanced screening funnel for clinical trials in Alzheimer's disease
Bibliographic record
Abstract
INTRODUCTION: Alzheimer's disease (AD) clinical trials with therapeutic interventions require hundreds of subjects to be studied over many months/years due to variable and slow disease progression. This article presents a novel screening paradigm integrating disease progression models to improve trial efficiency by identifying appropriate candidates for early phase clinical studies. METHODS: A traditional screening funnel is enhanced using machine learning models, including 3D convolutional neural networks and ensemble models, which integrate neuroimaging, demographic, genetic, and clinical data. RESULTS: This approach predicts clinical progression (2-year Clinical Dementia Rating Sum of Boxes change > 1) with an area under the curve of 0.836. Incorporating it into trials (with maximized sensitivity/specificity optimization) could reduce the number of subjects required by 55%, shorten recruitment by 13 months, and reduce screening amyloid positron emission tomography scans by 72%. DISCUSSION: By reducing patient burden and shortening timelines in clinical trials, this enhanced screening funnel could accelerate the development of AD therapies. Highlights: An innovative screening funnel was developed to improve Alzheimer's disease clinical trial efficiency.The funnel incorporates machine learning (ML)-based disease progression models.The ML model identifies patients with progression rate optimal for clinical trials.Unsuitable patients would fail early in the funnel before burdensome imaging procedures.This screening funnel is customizable to specific study needs.
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 | 0.111 | 0.256 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.004 | 0.005 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 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".