Research map / Reinforcement learning / Visual and representation RL
DPSCREEN: Dynamic Personalized Screening
Kartik Ahuja, William Zame, Mihaela van der Schaar
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 |
|---|---|---|---|
| DPSCREEN personalized policy instead of annual screening, with self-examination (low risk) | DPSCREEN · Breast cancer, Low risk | E[N|R] tests per year: 1 -> 0.32 | Improved |
| DPSCREEN instead of annual screening, with self-examination (high risk) | DPSCREEN · Breast cancer, High risk | E[N|R] tests per year: 1 -> 0.43 | Improved |
| remove self-examination information (low risk) (ablation) | DPSCREEN · Breast cancer, Low risk, annual comparison | E[N|R] tests per year: 0.32 -> 0.55 | Hurt |
| remove self-examination information (high risk) (ablation) | DPSCREEN · Breast cancer, High risk, annual comparison | E[N|R] tests per year: 0.43 -> 0.72 | Hurt |
| DPSCREEN without self-examination instead of annual screening (low risk) | DPSCREEN · Breast cancer, Low risk | E[N|R] tests per year: 1 -> 0.55 | Improved |
| DPSCREEN without self-examination instead of annual screening (high risk) | DPSCREEN · Breast cancer, High risk | E[N|R] tests per year: 1 -> 0.72 | Improved |
| remove self-examination under fixed delay tolerance (low risk) (ablation) | DPSCREEN · Breast cancer, Table 2 Low | E[N|R] tests per year: 0.12 -> 0.32 | Hurt |
| remove self-examination under fixed delay tolerance (high risk) (ablation) | DPSCREEN · Breast cancer, Table 2 High | E[N|R] tests per year: 0.80 -> 1.09 | Hurt |
| quadratic delay cost instead of linear delay cost (ablation) | DPSCREEN · Synthetic, same weights w | E[N|R] tests per year | Hurt |
| DPSCREEN versus annual screening on delay given cancer (low risk) | DPSCREEN · Breast cancer, Low risk | E[Delta|R,D] expected delay given cancer: 9.6 -> 9.2 | Improved |
Closest papers by meaning
- Unified Screening for Multiple Diseases (ICML 2025 · similarity 0.86)
- PersonalizedUS: Interpretable Breast Cancer Risk Assessment with Local Coverage Uncertainty Quantification (AAAI 2025 · similarity 0.83)
- ScreenShot: A Foundation Model for Few-Shot Combination Drug Screening (NeurIPS 2026 · similarity 0.81)
- Deep Reinforcement Learning for Early Diagnosis of Lung Cancer (AAAI 2024 · similarity 0.80)
- Domain constraints improve risk prediction when outcome data is missing (ICLR 2024 · similarity 0.80)
- Dynamic Decision Learning: Test-Time Evolution for Abnormality Grounding in Rare Diseases (ICML 2026 · similarity 0.80)
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.
