将临床路径图转化为可执行代码，实现癌症诊疗流程的自动化部署。
PathWISE: Multi-Agent Cancer Pathway Triaging Ontology Learning from Clinical Flowcharts
- 用五个阶段的智能体系统解析流程图结构，生成带语义验证的CQL代码。
- 在5个英国癌症路径中覆盖100%患者路径，183个节点全部通过编译验证。
- 适合医疗信息化、临床决策支持系统开发者使用。
临床路径以可视化流程图形式传播，其中空间拓扑、箭头方向、颜色编码和字体粗细等隐含关键分诊逻辑，现有计算系统无法解析。本文提出PathWISE，一个五阶段流水线，融合四个基于大模型的智能体与确定性深度优先搜索审计器及Java编译器评判模块，将这些非可计算的文档转化为经验证的、可执行的HL7临床质量语言（CQL）库，可作为FHIR CDS Hooks服务部署。专设智能体将流程图结构提取为有类型有向图，执行确定性路径枚举，对每个节点进行可计算性结构化语义审计，生成术语约束下的CQL定义，并由官方Java CQL转ELM编译器验证，生成覆盖100%枚举患者路径的路由逻辑。在五个英国NHS癌症路径（结直肠、肺、皮肤、上消化道、乳腺）中测试，审计最多183个节点（182个在混合配置下），识别出4类共544项治理问题，实现100%语法编译成功；不可计算节点以虚假占位符替代，保持编译通过同时暴露治理缺口供临床审查，且对字典覆盖概念未产生任何幻觉术语码。关键在于，仅将非确定性大模型推理用于知识提取，所有验证步骤均由确定性图数学与标准编译器支撑。
原文摘要 · Abstract (English)
Clinical pathways are disseminated as visual flowcharts where spatial topology, arrow direction, colour coding, and font weight encode critical triage logic that remains inaccessible to computational systems. We present PathWISE, a five-phase pipeline combining four LLM-based agents with a deterministic depth-first search auditor and a Java compiler critic, transforming these non-computable artefacts into validated, executable HL7 Clinical Quality Language (CQL) libraries deployable as FHIR CDS Hooks services. Purpose-built agents extract flowchart structure into a typed directed graph, perform deterministic path enumeration, conduct a structured semantic audit of every node's computability, generate terminology-constrained CQL definitions verified by the official Java CQL-to-ELM compiler, and produce routing logic covering 100% of enumerated patient journeys. Demonstrated across five UK NHS cancer pathways (colorectal, lung, skin, upper GI, and breast), PathWISE audits up to 183 nodes (182 under the Hybrid configuration), identifies 544 structured governance findings across four issue categories, achieves 100% syntactic compilation success, with UNCOMPUTABLE nodes receiving false placeholders that preserve compilability while surfacing governance gaps for clinical review, and produces zero hallucinated terminology codes for dictionary-covered concepts. Critically, PathWISE confines non-deterministic LLM inference to knowledge extraction while deterministic graph mathematics and a standard compiler underpin every verification step.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。