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

📅 2026-04-02
📈 Citations: 0
Influential: 0
📄 PDF

career value

141K/year
🤖 AI Summary
Clinical practice guidelines, as lengthy multimodal documents with intricate branching structures, pose significant challenges for translation into structured, auditable, and executable clinical decision support systems. This work proposes a decomposition-first pipeline that leverages topological-aware chunking, interface-constrained block graph generation, semantic deduplication, and global provenance aggregation, all built upon a unified vision-language model to ensure cross-page control-flow continuity and logical coherence. Moving beyond single-pass generation paradigms, the approach achieves substantial performance gains on a prostate guideline benchmark: edge and triple precision/recall improve to 69.0%/87.5% (from 19.6%/16.1%), and node recall rises from 78.1% to 93.8%.

Technology Category

Application Category

📝 Abstract
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.
Problem

Research questions and friction points this paper is trying to address.

clinical decision support
clinical practice guidelines
multimodal parsing
decision graph
cross-page continuity
Innovation

Methods, ideas, or system contributions that make the work stand out.

decomposition-first
topology-aware chunking
interface-constrained graph generation
provenance-preserving aggregation
executable clinical decision graph
🔎 Similar Papers
2024-05-27International Conference on Information and Knowledge ManagementCitations: 4
O
Onur Selim Kilic
Georgia Institute of Technology
Y
Yeti Z. Gurbuz
MetaDialog
C
Cem O. Yaldiz
Georgia Institute of Technology
A
Afra Nawar
Georgia Institute of Technology
E
Etrit Haxholli
MetaDialog
O
Ogul Can
Infuse Inc.
E
Eli Waxman
MetaDialog