Evaluating a large language model's ability to answer clinicians' requests for evidence summaries.

Journal: Journal of the Medical Library Association : JMLA
PMID: 39975503

Abstract

OBJECTIVE: This study investigated the performance of a generative artificial intelligence (AI) tool using GPT-4 in answering clinical questions in comparison with medical librarians' gold-standard evidence syntheses.

Authors

  • Mallory N Blasingame
    mallory.n.blasingame@vumc.org, Information Scientist & Assistant Director for Evidence Provision, Center for Knowledge Management, Vanderbilt University Medical Center, Nashville, TN.
  • Taneya Y Koonce
    Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
  • Annette M Williams
    annette.williams@vumc.org, Senior Information Scientist and Associate Director for Metadata Management, Center for Knowledge Management, Vanderbilt University Medical Center, Nashville, TN.
  • Dario A Giuse
    Department of Biomedical Informatics, Vanderbilt University School of Medicine, Nashville, Tennessee.
  • Jing Su
    Indiana University School of Medicine.
  • Poppy A Krump
    poppy.krump@vumc.org, Information Scientist, Center for Knowledge Management, Vanderbilt University Medical Center, Nashville, TN.
  • Nunzia Bettinsoli Giuse
    nunzia.giuse@vumc.org, Professor of Biomedical Informatics and Professor of Medicine; Vice President for Knowledge Management; and Director, Center for Knowledge Management, Vanderbilt University Medical Center, Nashville, TN.

Keywords

External Resources

Popular Topics
Recent Journals