AI 中文总结
本文提出CKG临床解释引擎，为临床知识图谱推理器增加可审计的下游层，将推理状态转化为类型化事实和轨迹，在6,720名患者数据上实现100%来源和保真度，确立了结构和实现的可审计性。
AI 中文摘要
临床决策支持输出可能缺乏患者观察、编码知识、结论和建议之间的可审计联系。我们提出了CKG临床解释引擎，这是一个用于冻结的、无需训练临床知识图谱推理器的下游层，它将患者推理状态和疾病知识转换为类型化事实、显式规则应用轨迹、有来源关联的结论以及政策许可的建议。该设计将测量可用性、表示完整性和疾病特定激活分离开来；因此，观察到的零激活证据不被视为缺失，部分表示与未观察到的证据不同。可选的语言生成仅限于符号许可的内容。在五个可用工作簿（6,720名患者；20,160条患者-疾病轨迹；1,021,440行特征证据）中，IG范围有效性和知识来源均为100%，数值跨表保真度为100%（120,960/120,960），导出的逻辑/报告轨迹完整性为100%（20,160/20,160）。可用性表示一致性为99.7028%（1,018,404/1,021,440）；所有3,036处不一致均局限于三种系统性特征队列模式。语料库包含86,783个观察到的零激活实例和139,949个观察到的部分表示实例。一个单独的、有种子设定的25名患者端到端审计在执行过程中无失败完成，并通过了所有预先指定的轨迹、许可、来源和状态一致性检查。这些结果确立了结构和实现的可审计性，而非临床正确性或实用性。
英文摘要
Clinical decision-support outputs can lack an au- ditable link between patient observations, encoded knowledge, conclusions, and recommendations. We present the CKG Clinical Explanation Engine, a downstream layer for a frozen, training-free clinical knowledge-graph reasoner that converts patient inference states and disease knowledge into typed facts, explicit rule-application traces, provenance-linked conclusions, and policy-licensed recommendations. The design separates measurement availability, representation completeness, and disease-specific activation; consequently, observed zero-activation evience is not treated as missing and partial representation is distinct from unobserved evidence. Optional language generation is restricted to symbolically licensed content. Across five usable workbooks (6,720 patients; 20,160 patient-disease traces; 1,021,440 feature-evidence rows), IG-range validity and knowledge provenance were 100%, numerical cross-sheet fidelity was 100% (120,960/120,960), and exported logical/report trace completeness was 100% (20,160/20,160). Availability representation consistency was 99.7028% (1,018,404/1,021,440); all 3,036 disagreements were confined to three systematic feature-cohort patterns. The corpus contained 86,783 observed zero-activation and 139,949 observed partially represented instances. A separate seeded 25-patient end-to-end audit completed without execution failure and passed all pre-specified trace, licensing, provenance, and state-consistency checks. These results establish structural and implementation auditability, not clinical correctness or utility.
