Human-Comparable Sensitivity of Large Language Models in Identifying Eligible Studies Through Title and Abstract Screening: 3-Layer Strategy Using GPT-3.5 and GPT-4 for Systematic Reviews.

Journal: Journal of medical Internet research
PMID:

Abstract

BACKGROUND: The screening process for systematic reviews is resource-intensive. Although previous machine learning solutions have reported reductions in workload, they risked excluding relevant papers.

Authors

  • Kentaro Matsui
    Department of Clinical Laboratory, National Center Hospital, National Center of Neurology and Psychiatry, Kodaira, Japan.
  • Tomohiro Utsumi
    Department of Sleep-Wake Disorders, National Institute of Mental Health, National Center of Neurology and Psychiatry, Kodaira, Japan.
  • Yumi Aoki
    Graduate School of Nursing Science, St. Luke's International University, Tokyo, Japan.
  • Taku Maruki
    Department of Neuropsychiatry, Kyorin University School of Medicine, Tokyo, Japan.
  • Masahiro Takeshima
    Department of Neuropsychiatry, Akita University Graduate School of Medicine, Akita, Japan.
  • Yoshikazu Takaesu
    Department of Neuropsychiatry, Graduate School of Medicine, University of the Ryukyus, Okinawa, Japan.