Custom Large Language Models Improve Accuracy: Comparing Retrieval Augmented Generation and Artificial Intelligence Agents to Noncustom Models for Evidence-Based Medicine.

Journal: Arthroscopy : the journal of arthroscopic & related surgery : official publication of the Arthroscopy Association of North America and the International Arthroscopy Association
PMID: 39521391

Abstract

PURPOSE: To show the value of custom methods, namely Retrieval Augmented Generation (RAG)-based Large Language Models (LLMs) and Agentic Augmentation, over standard LLMs in delivering accurate information using an anterior cruciate ligament (ACL) injury case.

Authors

  • Joshua J Woo
    Brown University, Providence, Rhode Island.
  • Andrew J Yang
    Brown University/The Warren Alpert School of Brown University, Providence, Rhode Island, U.S.A.
  • Reena J Olsen
    Sports Medicine Institute, Hospital for Special Surgery, New York, New York.
  • Sayyida S Hasan
    Donald and Barbara Zucker School of Medicine at Hofstra, Uniondale, New York.
  • Danyal H Nawabi
    Sports Medicine - Hip Preservation Service, Hospital for Special Surgery, New York, New York, USA.
  • Benedict U Nwachukwu
    Department of Orthopaedic Surgery, Hospital for Special Surgery, New York, New York, U.S.A.
  • Riley J Williams
    Department of Orthopaedic Surgery, Hospital for Special Surgery, New York, New York, U.S.A.
  • Prem N Ramkumar
    Department of Orthopedic Surgery, Cleveland Clinic, Cleveland, OH.

Keywords

External Resources

Popular Topics
Recent Journals