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

**Authors:** Xuewen Zhou, Zhen Chen  
**Lab:** Hong Kong Polytechnic University · **Published:** 29 Oct 2026  
**Links:** [arXiv](https://arxiv.org/abs/2610.40327) · [PDF](https://arxiv.org/pdf/2610.40327) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2610.40327.html)

## Key numbers

- **57.3% → 90.8%**: GDGraph improves System One accuracy from 57.3% to 90.8%
- **80.1%**: outperforming retrieval-augmented GPT-4o (80.1%)
- **82.7%**: and graph-guided GPT-4o with chain-of-thought (82.7%)

## 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.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.