基于知识图谱推理的患者级临床解释引擎:证据链与可审计性验证
Proof-Grounded Patient-Specific Clinical Explanations from Knowledge-Graph Reasoning
AI 导读
研究者提出 CKG Clinical Explanation Engine,在无需训练的临床知识图谱推理器下游,将患者推理状态与疾病知识转化为类型化事实、显式规则轨迹和带溯源的结论。
正文 · 原文
Abstract:Clinical decision support can lack auditable links from observations and encoded knowledge to conclusions and recommendations. Downstream of a frozen, training-free clinical knowledge-graph reasoner, the CKG Clinical Explanation Engine converts patient inference states and disease knowledge into typed facts, explicit rule traces, provenance-linked conclusions, and policy-licensed recommendations. Separate availability, representation completeness, and disease-specific activation distinguish observed zero-activation and partial evidence from unobserved evidence. Language-generation evaluation remains future work. Across six usable workbooks (11,289 patients, 33,867 patient-disease traces, 1,715,928 feature-evidence rows), IG-range validity, knowledge provenance, cross-sheet numerical fidelity (203,202/203,202), and exported fact/report field presence (33,867/33,867) reached 100.00%. Availability-representation consistency reached 99.29% (1,703,811/1,715,928), with 12,117 disagreements across five systematic feature-cohort patterns. Observed zero-activation and partial instances numbered 111,488 and 226,880, respectively. A separate seeded 30-patient end-to-end audit ran failure-free, passing all prespecified trace, licensing, provenance, and state-consistency checks. Paired comparisons (90 traces, fixed inherited diagnostic scores and policy catalogue) showed the availability-only baseline changed every report but no action sets. State collapse changed 20 action sets and removed 10 urgent-review occurrences. Rule replay reproduced all 40 action changes from reclassifying partial evidence as unobserved. The bounded validator detected all 450 single-fault mutants. Structural and implementation auditability were established. Clinical correctness and utility remain unestablished.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.06549 [cs.AI] |
| (or arXiv:2610.06549v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.06549 arXiv-issued DOI via DataCite |
Submission history
From: Surajit Das [view email]
[v1]
Mon, 5 Oct 2026 15:41:31 UTC (11 KB)
[v2]
Fri, 13 Nov 2026 14:04:57 UTC (15 KB)
来源:arXiv cs.AI · arxiv.org