Research map / Reinforcement learning / Visual and representation RL
Reinforcement Learning based Disease Progression Model for Alzheimer’s Disease
Krishnakant V. Saboo, Anirudh Choudhary, Yurui Cao, Gregory Worrell, David T Jones, Ravi Iyer
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add RL for combining DEs (vs grid-search w/o RL) (ablation) | Proposed model · Synthetic data | MAE: 1.009 -> 0.641 | Improved |
| Add RL for combining DEs (vs grid-search w/o RL) (ablation) | Proposed model · Synthetic data | MSE: 3.806 -> 0.910 | Improved |
| Add RL for combining DEs (vs grid-search w/o RL) (ablation) | Proposed model · ADNI | MAE: 0.595 -> 0.537 | Improved |
| Add RL for combining DEs (vs grid-search w/o RL) (ablation) | Proposed model · ADNI | MSE: 1.112 -> 0.761 | Improved |
| Proposed model vs minimalRNN | Proposed (with RL) · Synthetic data | MSE: 6.971 -> 0.910 | Improved |
| Proposed model vs minimalRNN | Proposed (with RL) · ADNI | MSE: 0.984 -> 0.761 | Improved |
| Proposed model vs SVR | Proposed (with RL) · ADNI | MSE: 0.574 -> 0.761 | Hurt |
| Proposed model vs SVR | Proposed (with RL) · Synthetic data | MAE: 0.658 -> 0.641 | No clear effect |
| Reward with only cognition mismatch term or only energetic cost term (ablation) | Reward function · ADNI | recovery/compensatory processes | Hurt |
| Use year 2 instead of year 0 as baseline | Proposed (with RL) · ADNI (134 participants) | trajectory correlation: 0.93 | No clear effect |
| Missing values in synthetic data | Parameter estimators · Synthetic data | parameter estimation error | Hurt |
Closest papers by meaning
- Conditional Diffusion with Ordinal Regression: Longitudinal Data Generation for Neurodegenerative Disease Studies (ICLR 2025 · similarity 0.86)
- A Stage-Aware Mixture of Experts Framework for Neurodegenerative Disease Progression Modelling (AAAI 2026 · similarity 0.86)
- Learning Riemannian metric for disease progression modeling (NeurIPS 2021 · similarity 0.84)
- Unscrambling disease progression at scale: fast inference of event permutations with optimal transport (NeurIPS 2024 · similarity 0.83)
- EpiCare: A Reinforcement Learning Benchmark for Dynamic Treatment Regimes (NeurIPS 2024 · similarity 0.82)
- Real-Time Recurrent Reinforcement Learning (AAAI 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
