Identifying ChatGPT-Written Patient Education Materials Using Text Analysis and Readability.

Journal: American journal of perinatology
Published Date: Apr 9, 2024

Abstract

OBJECTIVE:  Artificial intelligence (AI)-based text generators such as Chat Generative Pre-Trained Transformer (ChatGPT) have come into the forefront of modern medicine. Given the similarity between AI-generated and human-composed text, tools need to be developed to quickly differentiate the two. Previous work has shown that simple grammatical analysis can reliably differentiate AI-generated text from human-written text.

Authors

  • Silas Monje
    The Warren Alpert Medical School, Brown University, Providence, Rhode Island.
  • Sophie Ulene
    Columbia University Vagelos College of Physicians and Surgeons, New York.
  • Alexis C Gimovsky
    Division of Maternal-Fetal Medicine, Department of Obstetrics and Gynecology, Women & Infants Hospital of Rhode Island, Alpert Medical School of Brown University, Providence, Rhode Island.

Keywords

External Resources

Popular Topics
Recent Journals