# Automatic Generation of Executable BPMN Models from Medical Guidelines

arXiv: https://arxiv.org/abs/2604.07817 · HTML: https://mlsanity.com/paper/2604.07817/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 30 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Builds on (most cited first, 7 of 7)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [ProMoAI: Process Modeling with Generative AI](https://mlsanity.com/paper/2403.04327/) (2024)
- [Beyond Rule-based Named Entity Recognition and Relation Extraction for Process Model Generation from Natural Language Text](https://mlsanity.com/paper/2305.03960/) (2023)
- [Generating Structured Plan Representation of Procedures with LLMs](https://mlsanity.com/paper/2504.00029/) (2025)
- [Leveraging Generative AI for Extracting Process Models from Multimodal Documents](https://mlsanity.com/paper/2406.04959/) (2024)
- [Structure-Aware Optimization of Decision Diagrams for Health Guidance via Integer Programming](https://mlsanity.com/paper/2603.22996/) (2026)
- [Leveraging Machine Learning and Enhanced Parallelism Detection for BPMN Model Generation from Text](https://mlsanity.com/paper/2507.08362/) (2025)

## Built on by (most cited first, 1 of 1)

- [Ambiguity Detection and Elimination in Automated Executable Process Modeling](https://mlsanity.com/paper/2604.10884/) (2026)

## Abstract (arXiv)

We present an end-to-end pipeline that converts healthcare policy documents into executable, data-aware Business Process Model and Notation (BPMN) models using large language models (LLMs) for simulation-based policy evaluation. We address the main challenges of automated policy digitization with four contributions: data-grounded BPMN generation with syntax auto-correction, executable augmentation, KPI instrumentation, and entropy-based uncertainty detection. We evaluate the pipeline on diabetic nephropathy prevention guidelines from three Japanese municipalities, generating 100 models per backend across three LLMs and executing each against 1,000 synthetic patients. On well-structured policies, the pipeline achieves a 100% ground-truth match with perfect per-patient decision agreement. Across all conditions, raw per-patient decision agreement exceeds 92%, and entropy scores increase monotonically with document complexity, confirming that the detector reliably separates unambiguous policies from those requiring targeted human clarification.