Retrieval Augmented Generation Enabled Generative Pre-Trained Transformer 4 (GPT-4) Performance for Clinical Trial Screening.

Journal: medRxiv : the preprint server for health sciences
Published Date:

Abstract

BACKGROUND: Subject screening is a key aspect of all clinical trials; however, traditionally, it is a labor-intensive and error-prone task, demanding significant time and resources. With the advent of large language models (LLMs) and related technologies, a paradigm shift in natural language processing capabilities offers a promising avenue for increasing both quality and efficiency of screening efforts. This study aimed to test the Retrieval-Augmented Generation (RAG) process enabled Generative Pretrained Transformer Version 4 (GPT-4) to accurately identify and report on inclusion and exclusion criteria for a clinical trial.

Authors

  • Ozan Unlu
    Accelerator for Clinical Transformation, Brigham and Women's Hospital, Boston, MA.
  • Jiyeon Shin
    Accelerator for Clinical Transformation, Brigham and Women's Hospital, Boston, MA.
  • Charlotte J Mailly
    Accelerator for Clinical Transformation, Brigham and Women's Hospital, Boston, MA.
  • Michael F Oates
    Accelerator for Clinical Transformation, Brigham and Women's Hospital, Boston, MA.
  • Michela R Tucci
    Accelerator for Clinical Transformation, Brigham and Women's Hospital, Boston, MA.
  • Matthew Varugheese
    Accelerator for Clinical Transformation, Brigham and Women's Hospital, Boston, MA.
  • Kavishwar Wagholikar
    Accelerator for Clinical Transformation, Brigham and Women's Hospital, Boston, MA.
  • Fei Wang
    Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York, NY, United States.
  • Benjamin M Scirica
    Accelerator for Clinical Transformation, Brigham and Women's Hospital, Boston, MA.
  • Alexander J Blood
    Accelerator for Clinical Transformation, Brigham and Women's Hospital, Boston, MA.
  • Samuel J Aronson
    Accelerator for Clinical Transformation, Brigham and Women's Hospital, Boston, MA.

Keywords

No keywords available for this article.