Assessing the quality of Japanese online breast cancer treatment information using large language models: a comparison of ChatGPT, Claude, and expert evaluations.

Journal: Breast cancer (Tokyo, Japan)
Published Date: May 21, 2025

Abstract

BACKGROUND: The internet is a primary source of health information for breast cancer patients, but online content quality varies widely. This study aimed to evaluate the capability of large language models (LLMs), including ChatGPT and Claude, to assess the quality of online Japanese breast cancer treatment information by calculating and comparing their DISCERN scores with those of expert raters.

Authors

  • Atsushi Fushimi
    General Incorporated Association, BC TUBE, 1-5-6 Kudan-minami, Chiyoda-ku, Tokyo, 102-0074, Japan. fushimi@jikei.ac.jp.
  • Mitsuo Terada
    General Incorporated Association, BC TUBE, 1-5-6 Kudan-minami, Chiyoda-ku, Tokyo, 102-0074, Japan.
  • Rie Tahara
    General Incorporated Association, BC TUBE, 1-5-6 Kudan-minami, Chiyoda-ku, Tokyo, 102-0074, Japan.
  • Yuko Nakazawa
    General Incorporated Association, BC TUBE, 1-5-6 Kudan-minami, Chiyoda-ku, Tokyo, 102-0074, Japan.
  • Madoka Iwase
    General Incorporated Association, BC TUBE, 1-5-6 Kudan-minami, Chiyoda-ku, Tokyo, 102-0074, Japan.
  • Tomoko Shibayama
    General Incorporated Association, BC TUBE, 1-5-6 Kudan-minami, Chiyoda-ku, Tokyo, 102-0074, Japan.
  • Samy Kotti
    General Incorporated Association, BC TUBE, 1-5-6 Kudan-minami, Chiyoda-ku, Tokyo, 102-0074, Japan.
  • Nami Yamashita
    General Incorporated Association, BC TUBE, 1-5-6 Kudan-minami, Chiyoda-ku, Tokyo, 102-0074, Japan.
  • Asumi Iesato
    Laboratory of Human Thyroid Cancers Preclinical and Translational Research, Division of Experimental Pathology, Cancer Research Institute (CRI), Cancer Center, Department of Pathology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA 02215, USA.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals