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

Onur Selim Kilic, Yeti Z. Gurbuz, Cem Okan Yaldiz, Afra Nawar, Etrit Haxholli, Oğul Can, Eli Waxman

Keywords: Clinical practice guidelines, clinical decision support, multimodal document understanding, vision-language models, long-document parsing, decision graph extraction, graph canonicalization

TL;DR: Guideline2Graph turns long clinical guideline PDFs into one auditable decision graph via profile-aware chunking, chunk-level graph generation with fixed interfaces, and cross-chunk deduplication with edge rewiring.

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.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 3