Agentic AI-based Framework for Mitigating Premature Diagnostic Handoff and Silent Hallucination in Healthcare Applications

  • 类型：arxiv
  • 标识：2606.18068
  • 链接：http://arxiv.org/abs/2606.18068v1
  • 主分类：agent
  • 形态：application
  • 被引：1
  • 被引来源：Semantic Scholar
  • S2被引：1
  • OpenAlex被引：0
  • 影响力被引：0
  • TLDR：A multi-agent framework that addresses premature diagnostic handoff and silent clinical hallucinations that may go undetected before reaching the patient by replacing ``LLM-as-a-judge''routing with deterministic orchestration constraints is proposed and observes a statistically significant negative correlation between OLDCARTS completeness and semantic entropy, suggesting that structured information gathering is associated with reduced diagnostic uncertainty.
  • OpenAlex ID：W7165010307
  • OpenAlex DOI：10.48550/arxiv.2606.18068
  • DOI：10.48550/arxiv.2606.18068
  • DOI来源：OpenAlex
  • 开放获取：green
  • 开放获取链接：https://doi.org/10.48550/arxiv.2606.18068
  • OpenAlex更新：2026-07-19
  • 待LLM分类：否
  • 标题中文：基于 Agentic AI 的医疗应用中过早诊断交接与静默幻觉缓解框架
  • TLDR中文：提出一种多 Agent 框架，通过以确定性编排约束替代 "LLM-as-a-judge" 路由，解决可能在到达患者前未被发现的过早诊断交接与静默临床幻觉问题；观察到 OLDCARTS 完整度与语义熵之间存在统计显著的负相关，提示结构化信息采集与诊断不确定性降低相关。
  • 来源文件：
  • /inbox/tom/_candidates/2026-06-17-agent-memory-tool-use-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]