arXiv cs.AI· Xuewen Zhou, Zhen Chen·· 14 小时前AI 评分39
GDGraph：从放射学指南构建决策图，实现高效临床决策支持
Radiology Guideline-derived Decision Graph for Efficient Clinical Decision Support
AI 导读
研究提出 Guideline-derived Decision Graph（GDGraph）框架，将指南编译与病例评估解耦：由大语言模型把指南切分为章节块并抽取局部决策子图，聚合成可执行决策图，推理时用快速 System One 模型回答局部临床问题、由确定性遍历解析布尔逻辑。
正文 · 原文
Abstract:Radiological risk stratification and management planning are essential downstream tasks in medical imaging. Automating these tasks is challenging because clinical guideline criteria are distributed across prose, tables, and cross-referenced definitions. We present Guideline-derived Decision Graph (GDGraph), a framework that decouples guideline compilation from case evaluation. During compilation, a large language model partitions guidelines into section-based chunks, extracts local decision subgraphs with linked definitions, and aggregates related branches into an executable decision graph. During inference, a fast System One model answers localized clinical questions while deterministic traversal resolves Boolean logic, turning opaque single-pass predictions into a traceable decision path without task-specific training. Across 347 cases spanning renal cyst, adnexal mass, and thyroid nodule guidelines, GDGraph improves System One accuracy from 57.3% to 90.8%, outperforming retrieval-augmented GPT-4o (80.1%) and graph-guided GPT-4o with chain-of-thought (82.7%) at substantially lower latency and cost. The source code will be available.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.40327 [cs.CV] |
| (or arXiv:2610.40327v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.40327 arXiv-issued DOI via DataCite |
Submission history
From: Zhen Chen [view email]
[v1]
Thu, 29 Oct 2026 15:56:27 UTC (1,894 KB)
来源：arXiv cs.AI · arxiv.org