Custom Large Language Models Improve Accuracy: Comparing Retrieval Augmented Generation and Artificial Intelligence Agents to Noncustom Models for Evidence‐Based Medicine
Despite literature surrounding the use of LLM in medicine, there has been considerable and appropriate skepticism given the variably accurate response rates. This study establishes the groundwork to identify whether custom modifications to LLMs using RAG and agentic augmentation can better deliver accurate information in orthopaedic care. With this knowledge, online medical information commonly sought in popular LLMs, such as ChatGPT, can be standardized and provide relevant online medical information to better support shared decision making between surgeon and patient.
Authors
- Benedict U. Nwachukwu (ORCID: https://orcid.org/0000-0002-6170-7769)
- J. Woo (ORCID: https://orcid.org/0000-0002-2255-8510)
- Prem N. Ramkumar (ORCID: https://orcid.org/0000-0002-1704-9156)
- Sayyida Hasan (ORCID: https://orcid.org/0000-0002-4879-4247)
- Danyal H. Nawabi (ORCID: https://orcid.org/0000-0001-6057-3781)
- Reena Olsen (ORCID: https://orcid.org/0000-0002-0012-1481)
- Riley J. Williams (ORCID: https://orcid.org/0000-0003-2991-7173)
- Andrew I. Yang (ORCID: https://orcid.org/0009-0004-0072-3441)
Institutions
- Tufts University (US)
- Hospital for Special Surgery (US)
- Rush University Medical Center (US)
- Brown University (US)
- Creative Commons (US)
Publication Details
- Journal
- Arthroscopy The Journal of Arthroscopic and Related Surgery
- Published
- 2024-11-07
- DOI
- https://doi.org/10.1016/j.arthro.2024.10.042
- Citations
- 40
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 13.90