从单一聊天机器人到受管控的智能体生态系统：面向关键任务型医院信息管理系统的智能体AI模式目录与编排框架
From Single Chatbots to Governed Agent Ecosystems: An Agentic AI Pattern Catalogue and Orchestration Framework for Mission-Critical Hospital Information Management Systems
浏览论文内容
中文总结 AI 辅助
本研究针对医院信息管理系统提出以合规为核心的智能体AI模式目录与编排框架，可减少文档处理时间等成本、强化管控，助力医院将AI投资转化为可持续回报。
中文摘要 AI 辅助
医院正争相将AI嵌入分诊管理、文档处理、排班及收入周期工作流程，同时应对其他行业对该技术应用激增带来的挑战，但大多数部署仍停留在零散试点阶段，未能实现量产，使患者和机构面临运营脆弱性、不受管控的风险及不断增加的技术债务。据Fortune Business Insights报告，全球医疗AI市场预计到2034年将超过近1万亿美元，这放大了架构失误和扩展策略失败带来的财务后果。本研究提出一种以合规为首要原则的智能体AI模式目录与编排框架，专为医院信息管理系统（HIMS）构建，超越单一大型语言模型（LLM）聊天机器人，转向由自主和半自主智能体组成的受管控生态系统。该框架通过新增以下内容进行扩展：（i）智能体角色分类；（ii）正式的风险分层模型，将每个模式映射至风险层级、人在回路检查点及管控挂钩；（iii）统一编排运行时，能够协调Epic、Cerner和MEDITECH等电子病历（EHR）/HIMS环境中的多智能体工作流程。技术层面，该框架结合基于vLLM的推理、优化分页内存、机密计算及基于MCP的本地部署，实施端到端加密和代码即政策控制，符合HIPAA、GDPR、欧盟AI法案、印度DPDP和DISHA法案、ISO 27001、ISO 27002、ISO 14971及IEC 62304标准。我们展示了所提架构能够高效减少文档处理时间、集成工作量及AI试点流失率，同时强化管控和可审计性，为医院管理者和监管机构提供将AI投资转化为可持续临床、运营及财务投资回报的迫切需要的蓝图。
英文摘要
Hospitals are racing to embed AI, while coping with the surge in adaptation of the technology in other industries, into the triage management, documentation, scheduling, and revenue-cycle workflows, yet most deployments remain as fragmented pilots that stall at the edge of production, exposing patients and institutions to operational fragility, ungoverned risk, and mounting technical debt. At the same time, the global AI-in-healthcare market is projected to exceed nearly USD 1 trillion by 2034, according to the report of Fortune Business Insights, amplifying the financial consequences of architectural missteps and failed scaling strategies. This research proposes a compliance-first Agentic AI pattern catalogue and orchestration framework, purposely built for HIMS, moving beyond the single LLM chatbots and towards a governed ecosystem of autonomous and semi-autonomous agents. The framework extends by adding (i) a taxonomy of Agentic roles, (ii) a formal risk-stratification model that maps each pattern to risk tiers, human-in-the-loop checkpoints, and governance hooks, and (iii) a unified orchestration runtime capable of coordinating multi-agent workflows across EHR/HIMS landscapes such as Epic, Cerner, and MEDITECH. Technically the framework combines vLLM-based inference, optimized paging memory, confidential computing, and MCP based on-premise deployment, enforcing end-to-end encryption and policy-as-code controls aligned with HIPAA, GDPR, the EU AI Act, India's DPDP and DISHA Acts, ISO 27001, ISO 27002, ISO 14971 and IEC 62304. We exhibit how the proposed architecture is capable and efficient to reduce the documentation time, integration effort, and AI pilot attrition while constricting the governance and auditability, offering hospital leaders and governing authorities an urgently needed blueprint to convert AI investment into sustainable clinical, operational, and financial ROI
