Efficient Alzheimer's Diagnosis Through Sequential Decision-Making with Reinforcement Learning
Bibliographic record
Abstract
French Alzheimer's disease (AD) is the leading cause of dementia worldwide, with diagnosis often requiring a combination of cognitive assessments, neuroimaging, and biomarker analysis. These procedures, while effective, are resource-intensive, invasive, and time-consuming. This paper investigates reinforcement learning (RL) as a means of optimizing the diagnostic process, aiming to reduce cost and patient burden without compromising accuracy. We formulate AD diagnosis as a sequential decision-making problem and evaluate three approaches: a Deep Q-Network (DQN), a hybrid Proximal Policy Optimization with XGBoost classifier (PPO–XGB), and a hybrid Long Short-Term Memory network with Random Forest classifier (LSTM–RF). Using a subset of the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, the DQN achieved the best balance between accuracy (89.2%) and efficiency, favoring high-yield cognitive assessments over costly modalities. PPO–XGB demonstrated competitive accuracy (86.93%) with fewer tests (5.06 on average), while LSTM–RF performed strongly in temporal pattern recognition but with lower overall accuracy (80.9%). Results highlight RL's potential to serve as a cost-aware, adaptive controller for diagnostic test selection, offering a scalable framework for resource-efficient clinical decision-making in Alzheimer's disease.
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 | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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".