HALO: Hierarchical Evidence Selection and Reinforcement Learning for Allocating Budgeted Label Optimization from Longitudinal Clinical Records
Abstract
Learning from extensive longitudinal clinical records--spanning repeated encounters, evolving conditions, and heterogeneous documentation--under a finite labeling budget requires solving two coupled problems: deciding what evidence to keep and deciding which patients deserve higher-fidelity labels. Prior work on active learning and multi-fidelity label acquisition mainly addresses the second problem, while treating the evidence presented to the acquisition policy as fixed. We present HALO, a Hierarchical Evidence Selection and Reinforcement Learning pipeline for Allocating Budgeted Label Optimization from Longitudinal Clinical Records. This framework jointly learns what to read and what label source to acquire under budget. HALO first selects informative evidence from longitudinal records and then uses a budget-aware policy to allocate free-, silver-, and gold-fidelity label sources. For frozen policies, our theory characterizes asymmetric acquired-label channels and gives a budget-constrained finite-sample gold-risk bound for a common downstream logistic model. In a heart-failure case study, HALO attained the highest MedAlign acquired-label F1 at six of eight target budgets. A downstream classifier trained on HALO-acquired labels attained the highest external MGB F1 at budgets 15-60 and remained within 0.01 of the best comparator at budgets 75-120.
Related
- Reinforcement Learning for Hierarchical Reasoning Rewards: Minimax-Optimal Rates with Transformers
- Average-Reward Reinforcement Learning for Multichain MDPs: A Hierarchical Decomposition Approach
- Safety-Certified Hierarchical Control of DC Microgrids via Continuous Deep Reinforcement Learning and Covariance-Weighted Sliding Mode Synthesis
- Continuous-Time Mean-Variance Portfolio Selection Reinforcement Learning Problems for a Markov Regime-Switching System with No-Shorting Constraints
- Bayesian Hierarchical Models for Longitudinal Meta-Analysis in Sports Science: A Practical Tutorial Using brms
BibTeX
@misc{ying2026halo,
title = {{HALO: Hierarchical Evidence Selection and Reinforcement Learning for Allocating Budgeted Label Optimization from Longitudinal Clinical Records}},
author = {Huaiyuan Ying and Feiqing Huang and Ryumei Nakada and Katherine P. Liao and Tianxi Cai},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.00986},
eprint = {2611.00986},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.00986},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - HALO: Hierarchical Evidence Selection and Reinforcement Learning for Allocating Budgeted Label Optimization from Longitudinal Clinical Records
AU - Huaiyuan Ying
AU - Feiqing Huang
AU - Ryumei Nakada
AU - Katherine P. Liao
AU - Tianxi Cai
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.00986
UR - https://arxiv.org/abs/2611.00986
AB - Learning from extensive longitudinal clinical records--spanning repeated encounters, evolving conditions, and heterogeneous documentation--under a finite labeling budget requires solving two coupled problems: deciding what evidence to keep and deciding which patients deserve higher-fidelity labels. Prior work on active learning and multi-fidelity label acquisition mainly addresses the second problem, while treating the evidence presented to the acquisition policy as fixed. We present HALO, a Hierarchical Evidence Selection and Reinforcement Learning pipeline for Allocating Budgeted Label Optimization from Longitudinal Clinical Records. This framework jointly learns what to read and what label source to acquire under budget. HALO first selects informative evidence from longitudinal records and then uses a budget-aware policy to allocate free-, silver-, and gold-fidelity label sources. For frozen policies, our theory characterizes asymmetric acquired-label channels and gives a budget-constrained finite-sample gold-risk bound for a common downstream logistic model. In a heart-failure case study, HALO attained the highest MedAlign acquired-label F1 at six of eight target budgets. A downstream classifier trained on HALO-acquired labels attained the highest external MGB F1 at budgets 15-60 and remained within 0.01 of the best comparator at budgets 75-120.
ER -