发表机构
Mayo Clinic Arizona（梅奥诊所亚利桑那分院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
RadOnc-Agent利用LLM编排放射治疗工作流，提供26个函数，在测试中实现高完成率，验证了技术可行性。
AI 中文摘要
人工智能已经推进了单个放射治疗任务，但这些能力仍然分散在不同的临床阶段、软件环境和数据模态中。这种碎片化与从治疗决策到随访的纵向放射治疗工作流形成对比。在此，我们提出RadOnc-Agent，一个智能体人工智能框架，将放射治疗形式化为四个临床阶段，并通过对话界面提供26个可调用函数。一个大型语言模型控制器将临床意图映射到受模式约束的调用，保留患者和工作流上下文，并将请求路由到专业服务。我们使用2,600个单函数请求（7,800次重复执行）、200个预指定的合成跨阶段场景（跨越四个阶段，600次执行）以及来自60份去标识化患者记录的120个工作流实例（360次干净执行）评估了系统执行，这些实例代表了从决策到规划和从规划到适应的过程。RadOnc-Agent在单函数执行中选择了预期函数的准确率为98.79%，完成了96.50%的脚本化跨阶段工作流，并完成了96.67%的真实患者工作流执行。在比较消融中，移除纵向状态将跨阶段完成率从96.50%降至84.00%，而禁用模式和身份验证在重放/测试评估中将不匹配的后端调度从0%增加到95.28%。这些发现确立了LLM编排架构在协调纵向工作流中异构放射治疗能力和信息方面的技术可行性；它们并未确立临床正确性、临床实用性或前瞻性益处。
英文摘要
Artificial intelligence has advanced individual radiotherapy tasks, yet these capabilities remain separated across clinical stages, software environments and data modalities. This fragmentation contrasts with the longitudinal radiotherapy workflow from treatment decision-making through follow-up. Here we present RadOnc-Agent, an agentic artificial-intelligence framework that formalizes radiotherapy into four clinical phases and provides 26 callable functions through a conversational interface. A large-language-model controller maps clinical intent to schema-constrained calls, preserves patient and workflow context, and routes requests to specialist services. We evaluated system execution using 2,600 single-function requests (7,800 repeat executions), 200 prespecified synthetic cross-stage scenarios spanning four phases (600 executions), and 120 workflow instances from 60 de-identified patient records (360 clean executions) representing decision-to-planning and planning-to-adaptation. RadOnc-Agent selected the intended function in 98.79% of single-function executions, completed 96.50% of scripted cross-stage workflows, and completed 96.67% of real-patient workflow executions. In comparative ablations, removing longitudinal state reduced cross-stage completion from 96.50% to 84.00%, while disabling schema and identity validation increased mismatched backend dispatch from 0% to 95.28% in a replay/test evaluation. These findings establish the technical feasibility of an LLM-orchestrated architecture for coordinating heterogeneous radiotherapy capabilities and information across longitudinal workflows; they do not establish clinical correctness, clinical utility or prospective benefit.
