Retrieval-augmented generation for generative artificial intelligence in health care
Генерация с дополнением извлечённой информацией для генеративного искусственного интеллекта в здравоохранении
2025-01-25
SCID: 54.1/k7vhje5g
Discuss with AI
external knowledge retrievalgenerative artificial intelligencehealth caremedical applicationsretrieval-augmented generation
Figures from the paper
Abstract (AI)
Generative artificial intelligence has brought disruptive innovations in health care but faces certain challenges. Retrieval-augmented generation (RAG) enables models to generate more reliable content by leveraging the retrieval of external knowledge. In this perspective, we analyze the possible contributions that RAG could bring to health care in equity, reliability, and personalization. Additionally, we discuss the current limitations and challenges of implementing RAG in medical scenarios.
Key Findings
1
RAG can enable more personalized health-care applications through retrieval of information tailored to individual clinical contexts.
2
RAG may contribute to greater equity in health care by supporting access to relevant external medical information.
3
Retrieval-augmented generation can improve the reliability of generative artificial intelligence outputs by retrieving and incorporating external knowledge.
4
The perspective identifies implementation limitations and challenges that must be addressed before RAG can be broadly deployed in medical scenarios.
Research Object
retrieval-augmented generation (RAG) for generative artificial intelligence in health care
Research Subject
RAG’s contributions to equity, reliability, and personalization in health care, along with its implementation limitations and challenges in medical scenarios
Publication Details
Publication Date
2025-01-25
Journal
Publisher
ISSN
Cited by
141
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai6
LLaMA: Open and Efficient Foundation Language Models2023
GPT-4 Technical Report2023
Multimodal biomedical AI2022
Explainability for Large Language Models: A Survey2024
Almanac — Retrieval-Augmented Language Models for Clinical Medicine2024
Augmented non-hallucinating large language models as medical information curators2024