HALO：面向纵向临床记录的分层证据选择与强化学习预算标签优化框架

View PDF HTML (experimental)

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.

Subjects:	Computation and Language (cs.CL); Machine Learning (cs.LG); Machine Learning (stat.ML)
Cite as:	arXiv:2611.00986 [cs.CL]
	(or arXiv:2611.00986v1 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2611.00986 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Huaiyuan Ying [view email]
[v1] Sat, 31 Oct 2026 14:24:20 UTC (5,453 KB)