Safety-Oriented Evaluation of Large Language Models in Health Care: Guideline-Informed Systematic Review

Hikaru Matsuoka   ^{1, 2, 3 *} , PhD ;   Takayuki Takahashi   ^{3, 4 *} , MD, PhD ;   Takayuki Semitsu   ^{2 *} , MSc ;   Keiko Matsuoka   ^{5 *} , MD ;   Ryoma Hayashi   ^{4 *} , MD

¹ Department of Information Security, Faculty of Information Systems, University of Nagasaki, Nagasaki, Nagasaki, Japan

² Information-Technology Promotion Agency, Minato, Tokyo, Japan

³ Statistical Genetics Team, RIKEN Center for Advanced Intelligence Project, Tokyo, Japan

⁴ Department of Obstetrics and Gynecology, Keio University School of Medicine, Shinjuku-ku, Tokyo, Japan

⁵ Department of Obstetrics and Gynecology, Shonan Atsugi Hospital, Atsugi, Kanagawa, Japan

*all authors contributed equally