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

Kentaro Matsui   ^{1, 2} , MD, PhD ;   Tomohiro Utsumi   ^{2, 3} , MD ;   Yumi Aoki   ⁴ , PhD ;   Taku Maruki   ⁵ , MD ;   Masahiro Takeshima   ⁶ , MD, PhD ;   Yoshikazu Takaesu   ⁷ , MD, PhD

¹ Department of Clinical Laboratory, National Center Hospital, National Center of Neurology and Psychiatry, Kodaira, Japan

² Department of Sleep-Wake Disorders, National Institute of Mental Health, National Center of Neurology and Psychiatry, Kodaira, Japan

³ Department of Psychiatry, The Jikei University School of Medicine, Tokyo, Japan

⁴ Graduate School of Nursing Science, St. Luke’s International University, Tokyo, Japan

⁵ Department of Neuropsychiatry, Kyorin University School of Medicine, Tokyo, Japan

⁶ Department of Neuropsychiatry, Akita University Graduate School of Medicine, Akita, Japan

⁷ Department of Neuropsychiatry, Graduate School of Medicine, University of the Ryukyus, Okinawa, Japan