跳到正文
arXiv cs.AI· Yifan Jin, Tao Liu·· 4 小时前AI 评分33

支持门控世界模型:何时信任模拟患者响应用于升压药决策支持

When to Trust Simulated Patient Responses:Support-Gated World Models for Vasopressor Decision Support

AI 导读

研究者提出支持门控世界模型决策支持方法,通过循环动力学集成预测去甲肾上腺素剂量类别下的短期生理响应,并用行为模型估计观测动作支持度,对支持不足或集成分歧过大的预测予以隐藏。

正文 · 原文

View PDF HTML (experimental)

Abstract:Clinical world models expose language-model agents to predicted patient responses, but simulations can be unreliable for poorly supported treatments or unfamiliar hospitals. We introduce Support-Gated World-Model decision support, a lightweight extension of a propose--simulate--refine agent. A recurrent dynamics ensemble predicts short-horizon physiological responses to documented norepinephrine dose categories, while a behavior model estimates observational action support. The interface withholds predictions with insufficient support or excessive ensemble disagreement and abstains when no candidate qualifies. Evaluation on eICU-CRD includes 70 hospitals and 30,700 decision transitions, with 14 hospitals held out for testing. At 62.0% factual-transition coverage, joint gating yields a MAP mean absolute error of 7.3 mmHg, compared with 9.2 mmHg for random selection at the same coverage. The gated agent achieves 60.0% agreement with recorded actions at 81.0% decision coverage, compared with 55.0% agreement and 99.5% coverage for an ungated ensemble agent. Component ablations show lower factual risk with joint gating than with either gate this http URL results characterize a reliability--coverage trade-off in selective clinical simulation; they do not identify individualized treatment effects or establish improved patient outcomes.
Subjects: Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.18458 [cs.AI]
  (or arXiv:2611.18458v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.18458

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yifan Jin [view email]
[v1] Fri, 13 Nov 2026 17:28:25 UTC (20 KB)

来源:arXiv cs.AI · arxiv.org