Solving the 'Goldilocks problem' in dementia clinical trials with multimodal AI
Bibliographic record
Abstract
The development of effective therapeutics for Alzheimer's Disease and related dementias (ADRD) has been hindered by patient heterogeneity and the limitations of current diagnostic tools. New treatments have no chance of working if given to patients who cannot benefit from them. This perspective explores how advances in Artificial Intelligence (AI), particularly multimodal machine learning, can solve the 'Goldilocks problem' of identifying patients for inclusion in clinical trials and support precision treatment in real-world healthcare settings. We examine the challenges of patient stratification, grounded by a conceptual framework of identifying each person's stage and subtype of dementia. We review data from several clinical trials of Alzheimer's disease therapeutics, to explore how AI-guided patient stratification can improve trial outcomes, reduce costs and improve recruitment. Further, we discuss the integration of AI into clinical workflows, the importance of model interpretability and generalizability, and ethical imperative to address algorithmic bias. By combining AI with scientific insight, clinical expertise, and patient experience, we argue that intelligent analytics can accelerate the discovery and delivery of new diagnostics and therapeutics, ultimately transforming dementia care and improving outcomes for patients around the globe.
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 | 0.651 | 0.728 |
| Meta-epidemiology (narrow) | 0.002 | 0.003 |
| Meta-epidemiology (broad) | 0.008 | 0.007 |
| Bibliometrics | 0.006 | 0.006 |
| Science and technology studies | 0.003 | 0.020 |
| Scholarly communication | 0.015 | 0.017 |
| Open science | 0.006 | 0.010 |
| Research integrity | 0.009 | 0.015 |
| 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".