---
title: "Radiology Guideline-derived Decision Graph for Efficient Clinical Decision Support"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.40327v1"
permalink: "https://feed.astralor.com/items/itm_ec66286eeb3678b7a4377b2f"
published: "2026-10-29T15:56:27.000Z"
score: 54
channel: "tech"
tags: ["LLM","OpenAI","推理效率","RAG","Radiology Guideline-derived Decision","Graph","Efficient Clinical Decision","Support Radiological"]
---

# Radiology Guideline-derived Decision Graph for Efficient Clinical Decision Support

## 速览

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,…

## 关键点

- 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.

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_ec66286eeb3678b7a4377b2f