Retrieval-Augmented Generation in Medicine: A Scoping Review of Technical Implementations, Clinical Applications, and Ethical Considerations

TL;DR

This scoping review examines the current state of retrieval-augmented generation (RAG) in medicine, highlighting its applications, limitations, and the need for further validation and ethical considerations to ensure safe clinical use.

Contribution

The paper provides a comprehensive overview of technical implementations, clinical applications, and ethical issues of RAG in medicine, identifying gaps and future directions.

Findings

Most research uses public data and English-centric models.

Evaluation often neglects bias and safety considerations.

Applications mainly focus on question answering and report generation.

Abstract

The rapid growth of medical knowledge and increasing complexity of clinical practice pose challenges. In this context, large language models (LLMs) have demonstrated value; however, inherent limitations remain. Retrieval-augmented generation (RAG) technologies show potential to enhance their clinical applicability. This study reviewed RAG applications in medicine. We found that research primarily relied on publicly available data, with limited application in private data. For retrieval, approaches commonly relied on English-centric embedding models, while LLMs were mostly generic, with limited use of medical-specific LLMs. For evaluation, automated metrics evaluated generation quality and task performance, whereas human evaluation focused on accuracy, completeness, relevance, and fluency, with insufficient attention to bias and safety. RAG applications were concentrated on question answering, report generation, text summarization, and information extraction. Overall, medical RAG remains at an early stage, requiring advances in clinical validation, cross-linguistic adaptation, and support for low-resource settings to enable trustworthy and responsible global use.