Retrieval-Augmented Generation Assistant for Anatomical Pathology Laboratories

TL;DR

This paper develops and evaluates a Retrieval-Augmented Generation system tailored for Anatomical Pathology labs, improving access to protocols through domain-specific retrieval and chunking strategies, enhancing workflow and safety.

Contribution

It introduces a novel RAG assistant for AP labs, utilizing domain-specific embeddings and optimized retrieval strategies, demonstrating improved accuracy and relevance over baseline methods.

Findings

Recursive chunking and hybrid retrieval improve baseline performance.

Biomedical-specific embeddings (MedEmbed) enhance answer relevance and faithfulness.

Retrieving a single top chunk maximizes efficiency and accuracy.

Abstract

Accurate and efficient access to laboratory protocols is essential in Anatomical Pathology (AP), where up to 70% of medical decisions depend on laboratory diagnoses. However, static documentation such as printed manuals or PDFs is often outdated, fragmented, and difficult to search, creating risks of workflow errors and diagnostic delays. This study proposes and evaluates a Retrieval-Augmented Generation (RAG) assistant tailored to AP laboratories, designed to provide technicians with context-grounded answers to protocol-related queries. We curated a novel corpus of 99 AP protocols from a Portuguese healthcare institution and constructed 323 question-answer pairs for systematic evaluation. Ten experiments were conducted, varying chunking strategies, retrieval methods, and embedding models. Performance was assessed using the RAGAS framework (faithfulness, answer relevance, context recall) alongside top-k retrieval metrics. Results show that recursive chunking and hybrid retrieval delivered the strongest baseline performance. Incorporating a biomedical-specific embedding model (MedEmbed) further improved answer relevance (0.74), faithfulness (0.70), and context recall (0.77), showing the importance of domain-specialised embeddings. Top-k analysis revealed that retrieving a single top-ranked chunk (k=1) maximized efficiency and accuracy, reflecting the modular structure of AP protocols. These findings highlight critical design considerations for deploying RAG systems in healthcare and demonstrate their potential to transform static documentation into dynamic, reliable knowledge assistants, thus improving laboratory workflow efficiency and supporting patient safety.