Peer-Reviewed Publication
Npj Health Syst2025;2(1)January 25, 2025Journal Article
Retrieval-augmented generation for generative artificial intelligence in health care.
Rui Yang1, Yilin Ning1, Emilia Keppo2, Mingxuan Liu1, Chuan Hong3, Danielle S Bitterman4, Jasmine Chiat Ling Ong5, Daniel Shu Wei Ting1,6,7, Nan Liu8,9,10
1Center for Quantitative Medicine, Duke-NUS Medical School, Singapore, Singapore.
2Faculty of Arts and Science, University of Toronto, Toronto, ON, Canada.
3Department of Biostatistics and Bioinformatics, Duke University, Durham, NC, USA.
4Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, MA, USA.
5Division of Pharmacy, Singapore General Hospital, Singapore, Singapore.
6Singapore Eye Research Institute, Singapore National Eye Center, Singapore, Singapore.
7Byers Eye Institute, Stanford University, Stanford, CA, USA.
8Center for Quantitative Medicine, Duke-NUS Medical School, Singapore, Singapore. liu.nan@duke-nus.edu.sg.
9Program in Health Services and Systems Research, Duke-NUS Medical School, Singapore, Singapore. liu.nan@duke-nus.edu.sg.
10NUS Artificial Intelligence Institute, National University of Singapore, Singapore, Singapore. liu.nan@duke-nus.edu.sg.
Abstract
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. Addition…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans