Accuracy of large language models in answering ophthalmology board-style questions: A meta-analysis.

Journal: Asia-Pacific journal of ophthalmology (Philadelphia, Pa.)
PMID:

Abstract

PURPOSE: To evaluate the accuracy of large language models (LLMs) in answering ophthalmology board-style questions.

Authors

  • Jo-Hsuan Wu
    Shiley Eye Institute and Viterbi Family Department of Ophthalmology, University of California San Diego, La Jolla, CA, USA.
  • Takashi Nishida
    From the Hamilton Glaucoma Center (A.K., S.M., T.N., G.M., E.H.L., M.C., M.A.F., L.Z., R.N.W.),; Shiley Eye Institute, Viterbi Family Department of Ophthalmology, University of California San Diego, La Jolla; School of Medicine (P.K.),; University of California Irvine, Irvine; Department of Civil, Construction, and Environmental Engineering (M.S.J.),; San Diego State University, San Diego, California; Bernard and Shirlee Brown Glaucoma Research Laboratory (J.M.L.),; Department of Ophthalmology, Edward S. Harkness Eye Institute, Columbia University Medical Center, New York, New York; and the Department of Ophthalmology and Vision Sciences (M.A.F., C.A.G.),; Heersink School of Medicine, The University of Alabama at Birmingham, Birmingham, Alabama, USA.
  • T Y Alvin Liu
    Wilmer Eye Institute at the Johns Hopkins University School of Medicine, Baltimore, MD.