# MedPAO: A Protocol-Driven Agent for Structuring Medical Reports

arXiv: https://arxiv.org/abs/2510.04623 · HTML: https://mlsanity.com/paper/2510.04623/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 6 Oct 2025.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 12 of 12)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [R2GenGPT: Radiology Report Generation with Frozen LLMs](https://mlsanity.com/paper/2309.09812/) (2023)
- [MAIRA-1: A specialised large multimodal model for radiology report generation](https://mlsanity.com/paper/2311.13668/) (2023)
- [Creation and Validation of a Chest X-Ray Dataset with Eye-tracking and Report Dictation for AI Development](https://mlsanity.com/paper/2009.07386/) (2020)
- [Two-stage LLM Fine-tuning with Less Specialization and More Generalization](https://mlsanity.com/paper/2211.00635/) (2022)
- [Interpretable Medical Diagnostics with Structured Data Extraction by Large Language Models](https://mlsanity.com/paper/2306.05052/) (2023)
- [CXR-Agent: Vision-language models for chest X-ray interpretation with uncertainty aware radiology reporting](https://mlsanity.com/paper/2407.08811/) (2024)
- [NCBO Ontology Recommender 2.0: An Enhanced Approach for Biomedical Ontology Recommendation](https://mlsanity.com/paper/1611.05973/) (2016)
- [CLEAR: A Clinically-Grounded Tabular Framework for Radiology Report Evaluation](https://mlsanity.com/paper/2505.16325/) (2025)
- [Large Multimodal Model based Standardisation of Pathology Reports with Confidence and their Prognostic Significance](https://mlsanity.com/paper/2405.02040/) (2024)
- [Structuring the Unstructured: A Multi-Agent System for Extracting and Querying Financial KPIs and Guidance](https://mlsanity.com/paper/2505.19197/) (2025)

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

- [FetalAgents: A Multi-Agent System for Fetal Ultrasound Image and Video Analysis](https://mlsanity.com/paper/2603.09733/) (2026)

## Abstract (arXiv)

The deployment of Large Language Models (LLMs) for structuring clinical data is critically hindered by their tendency to hallucinate facts and their inability to follow domain-specific rules. To address this, we introduce MedPAO, a novel agentic framework that ensures accuracy and verifiable reasoning by grounding its operation in established clinical protocols such as the ABCDEF protocol for CXR analysis. MedPAO decomposes the report structuring task into a transparent process managed by a Plan-Act-Observe (PAO) loop and specialized tools. This protocol-driven method provides a verifiable alternative to opaque, monolithic models. The efficacy of our approach is demonstrated through rigorous evaluation: MedPAO achieves an F1-score of 0.96 on the critical sub-task of concept categorization. Notably, expert radiologists and clinicians rated the final structured outputs with an average score of 4.52 out of 5, indicating a level of reliability that surpasses baseline approaches relying solely on LLM-based foundation models. The code is available at: https://github.com/MiRL-IITM/medpao-agent