Evaluation of retrieval-augmented generation and large language models in clinical guidelines for degenerative spine conditions.

Journal: European spine journal : official publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society
Published Date: Jul 7, 2025

Abstract

PURPOSE: Degenerative spinal diseases often require complex, patient-specific treatment, presenting a compelling challenge for artificial intelligence (AI) integration into clinical practice. While existing literature has focused on ChatGPT-4o performance in individual spine conditions, this study compares ChatGPT-4o, a traditional large language model (LLM), against NotebookLM, a novel retrieval-augmented model (RAG-LLM) supplemented with North American Spine Society (NASS) guidelines, for concordance with all five published NASS guidelines for degenerative spinal diseases.

Authors

  • Audrey Y Su
    Warren Alpert Medical School at Brown University, Providence, USA.
  • Ashley Knebel
    Cognoa, Inc, Palo Alto, CA, United States.
  • Andrew Y Xu
    Warren Alpert Medical School, Brown University, Providence, RI, USA.
  • Marco Kaper
    Warren Alpert Medical School at Brown University, Providence, USA.
  • Phillip Schmitt
    The Warren Alpert Medical School of Brown University, Providence, Rhode Island, U.S.A.
  • Joseph E Nassar
    Faculty of Medicine, American University of Beirut, Lebanon.
  • Manjot Singh
    Warren Alpert Medical School, Brown University, Providence, RI, USA.
  • Michael J Farias
  • Jinho Kim
    Department of Chemistry, Incheon National University, Incheon, Republic of Korea.
  • Bassel G Diebo
    Department of Orthopedics, Warren Alpert Medical School, Brown University, Providence, RI, USA.
  • Alan H Daniels
    1Division of Spine Surgery and.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals