让医疗决策更公平安全，自动调节各群体风险阈值。
Feasibility-Guided Fair Adaptive Offline Reinforcement Learning for Medicaid Care Management
- 根据群体特性动态调整风险控制阈值，保障公平性。
- 在保持决策效果接近基线的同时，显著提升公平性指标。
- 适合关注医疗公平与安全的政策制定者与临床系统开发者。
我们提出可行性引导的公平自适应离线强化学习（FG-FARL），通过为不同群体校准安全阈值，在降低伤害的同时实现特定公平目标（覆盖率或伤害率）的群体均衡。基于某联邦医疗补助计划的去标识化纵向轨迹数据，我们将FG-FARL与行为克隆（BC）及HACO（混合自适应共形离线强化学习；全局共形安全基线）进行对比。报告了带自助法95%置信区间的离策略价值估计和带有p值的子群差异分析。结果表明，FG-FARL在价值表现上与基线相当，同时改善了公平性度量，为更安全、更公平的决策支持提供了可行路径。
原文摘要 · Abstract (English)
We introduce Feasibility-Guided Fair Adaptive Reinforcement Learning (FG-FARL), an offline RL procedure that calibrates per-group safety thresholds to reduce harm while equalizing a chosen fairness target (coverage or harm) across protected subgroups. Using de-identified longitudinal trajectories from a Medicaid population health management program, we evaluate FG-FARL against behavior cloning (BC) and HACO (Hybrid Adaptive Conformal Offline RL; a global conformal safety baseline). We report off-policy value estimates with bootstrap 95% confidence intervals and subgroup disparity analyses with p-values. FG-FARL achieves comparable value to baselines while improving fairness metrics, demonstrating a practical path to safer and more equitable decision support.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。