Retrieval-Augmented Generation in Medicine: A Scoping Review of Technical Implementations, Clinical Applications, and Ethical Considerations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917077683535872 |
|---|---|
| author | Yang, Rui Wong, Matthew Yu Heng Li, Huitao Li, Xin Zhu, Wentao Liao, Jingchi Yu, Kunyu Liew, Jonathan Chong Kai Xuan, Weihao Chen, Yingjian Ke, Yuhe Ong, Jasmine Chiat Ling Teodoro, Douglas Hong, Chuan Ting, Daniel Shi Wei Liu, Nan |
| author_facet | Yang, Rui Wong, Matthew Yu Heng Li, Huitao Li, Xin Zhu, Wentao Liao, Jingchi Yu, Kunyu Liew, Jonathan Chong Kai Xuan, Weihao Chen, Yingjian Ke, Yuhe Ong, Jasmine Chiat Ling Teodoro, Douglas Hong, Chuan Ting, Daniel Shi Wei Liu, Nan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_05901 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Retrieval-Augmented Generation in Medicine: A Scoping Review of Technical Implementations, Clinical Applications, and Ethical Considerations Yang, Rui Wong, Matthew Yu Heng Li, Huitao Li, Xin Zhu, Wentao Liao, Jingchi Yu, Kunyu Liew, Jonathan Chong Kai Xuan, Weihao Chen, Yingjian Ke, Yuhe Ong, Jasmine Chiat Ling Teodoro, Douglas Hong, Chuan Ting, Daniel Shi Wei Liu, Nan Computation and Language Artificial Intelligence 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. |
| title | Retrieval-Augmented Generation in Medicine: A Scoping Review of Technical Implementations, Clinical Applications, and Ethical Considerations |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2511.05901 |