# Guideline2Graph: Profile-Aware Multimodal Parsing for Executable Clinical Decision Graphs

arXiv: https://arxiv.org/abs/2604.02477 · HTML: https://mlsanity.com/paper/2604.02477/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 35 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Builds on (most cited first, 18 of 18)

- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [OCR-free Document Understanding Transformer](https://mlsanity.com/paper/2111.15664/) (2021)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [Deep Entity Matching with Pre-Trained Language Models](https://mlsanity.com/paper/2004.00584/) (2020)
- [Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction](https://mlsanity.com/paper/2404.03868/) (2024)
- [FlowLearn: Evaluating Large Vision-Language Models on Flowchart Understanding](https://mlsanity.com/paper/2407.05183/) (2024)
- [MedDM:LLM-executable clinical guidance tree for clinical decision-making](https://mlsanity.com/paper/2312.02441/) (2023)
- [AutoKG: Efficient Automated Knowledge Graph Generation for Language Models](https://mlsanity.com/paper/2311.14740/) (2023)
- [Docs2KG: Unified Knowledge Graph Construction from Heterogeneous Documents Assisted by Large Language Models](https://mlsanity.com/paper/2406.02962/) (2024)
- [Text2MDT: Extracting Medical Decision Trees from Medical Texts](https://mlsanity.com/paper/2401.02034/) (2024)
- [CPGPrompt: Translating Clinical Guidelines into LLM-Executable Decision Support](https://mlsanity.com/paper/2601.03475/) (2026)

## Built on by (most cited first, 2 of 2)

- [From PDF to Evidence: Structure-Aware Retrieval for Clinical Practice Guidelines](https://mlsanity.com/paper/2609.33447/) (2026)
- [More Reasoning Is Not Always Better: Executing Clinical Guidelines with LLMs and Rules](https://mlsanity.com/paper/2610.15912/) (2026)

## Abstract (arXiv)

Clinical practice guidelines are long, multimodal documents whose branching recommendations are difficult to convert into executable clinical decision support (CDS), and one-shot parsing often breaks cross-page continuity. Recent LLM/VLM extractors are mostly local or text-centric, under-specifying section interfaces and failing to consolidate cross-page control flow across full documents into one coherent decision graph. We present a decomposition-first pipeline that converts full-guideline evidence into an executable clinical decision graph through topology-aware chunking, interface-constrained chunk graph generation, and provenance-preserving global aggregation. Rather than relying on single-pass generation, the pipeline uses explicit entry/terminal interfaces and semantic deduplication to preserve cross-page continuity while keeping the induced control flow auditable and structurally consistent. We evaluate on an adjudicated prostate-guideline benchmark with matched inputs and the same underlying VLM backbone across compared methods. On the complete merged graph, our approach improves edge and triplet precision/recall from 19.6%/16.1% in existing models to 69.0%/87.5%, while node recall rises from 78.1% to 93.8%. These results support decomposition-first, auditable guideline-to-CDS conversion on this benchmark, while current evidence remains limited to one adjudicated prostate guideline and motivates broader multi-guideline validation.