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

TL;DR

This paper introduces a decomposition-first pipeline for converting complex clinical guidelines into executable decision graphs, significantly improving accuracy and continuity over existing methods.

Contribution

It proposes a novel, topology-aware, decomposition-based approach that preserves cross-page control flow and auditability in clinical decision graph generation.

Findings

Edge and triplet precision/recall improved from 19.6%/16.1% to 69.0%/87.5%.

Node recall increased from 78.1% to 93.8%.

Supports more accurate, auditable guideline-to-CDS conversion.

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.