发表机构
University of Pennsylvania（宾夕法尼亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ETHOS是可与现有临床多智能体系统集成的模块化伦理框架，通过分层治理提升决策可靠性，将AI伦理原则转化为可部署的安全保障。
AI 中文摘要
大语言模型的快速应用推动了临床多智能体系统（MAS）的开发，这类系统能够整合多模态患者数据，支持日益复杂的临床决策。然而，这些系统在现实医疗场景中的部署引发了与安全性、公平性、问责制、透明度及患者信任相关的关键伦理问题。尽管世界卫生组织、美国国家医学院、FUTURE-AI联盟等众多机构已提出医疗AI的伦理框架与治理原则，但这些努力在很大程度上仍停留在概念层面。为应对这一挑战，本文提出ETHOS（Ethics and Trust through Hierarchical Oversight System，即通过分层监督系统实现伦理与信任），这是一个模块化伦理框架，被设计为治理元智能体，可与任何现有多智能体系统集成，无需修改其底层架构。ETHOS通过分层治理方法将利益相关者告知的伦理需求转化为可执行的运行时监督，该方法包含确定性检查、情境审查及最终伦理批评者，这些组件持续评估中间推理步骤与最终输出，使系统能够识别伦理风险、请求修订或抑制不符合预定义安全与可信赖性标准的响应。我们在肝病临床决策支持MAS中对ETHOS进行了验证，结果显示ETHOS通过检测不完整、不一致或超出范围的证据，并在无法支持安全建议时适当增加弃权（不执行）的情况，从而提升了决策可靠性。通过将伦理治理直接嵌入系统运行，ETHOS提供了一种实用且可审计的机制，将高层AI伦理原则转化为可部署的安全保障措施。
英文摘要
The rapid adoption of large language models has enabled the development of clinical multi-agent systems (MAS) capable of integrating multimodal patient data and supporting increasingly complex clinical decision-making. However, the deployment of these systems in real-world healthcare settings raises critical ethical concerns related to safety, fairness, accountability, transparency, and patient trust. While numerous organizations, including the World Health Organization, the National Academy of Medicine, and the FUTURE-AI consortium, have proposed ethical frameworks and governance principles for healthcare AI, these efforts remain largely conceptual. To address this challenge, we present ETHOS (Ethics and Trust through Hierarchical Oversight System), a modular ethics framework designed as a governance meta-agent that can be integrated with any existing multi-agent system without requiring changes to its underlying architecture. ETHOS translates stakeholder-informed ethical requirements into executable runtime oversight through a layered governance approach consisting of deterministic checks, contextual reviews, and a final ethics critic. These components continuously evaluate intermediate reasoning steps and final outputs, enabling the system to identify ethical risks, request revisions, or suppress responses that fail predefined safety and trustworthiness criteria. We demonstrate ETHOS within a hepatology clinical decision-support MAS. Results show that ETHOS improves decision reliability by detecting incomplete, inconsistent, or out-of-scope evidence and appropriately increasing abstention when safe recommendations cannot be supported. By embedding ethical governance directly into system operation, ETHOS provides a practical and auditable mechanism for transforming high-level AI ethics principles into deployable safeguards.
CommentsPreprint of an article submitted for consideration in Pacific Symposium on Biocomputing ©2027 World Scientific Publishing Company. \url{https://psb.stanford.edu/}
