Mixed methods assessment of the influence of demographics on medical advice of ChatGPT.

Journal: Journal of the American Medical Informatics Association : JAMIA
PMID: 38679900

Abstract

OBJECTIVES: To evaluate demographic biases in diagnostic accuracy and health advice between generative artificial intelligence (AI) (ChatGPT GPT-4) and traditional symptom checkers like WebMD.

Authors

  • Katerina Andreadis
    Department of Population Health, NYU Grossman School of Medicine, New York, New York, United States of America.
  • Devon R Newman
    Department of Population Health, NYU Grossman School of Medicine, New York, NY 10016, United States.
  • Chelsea Twan
    Department of Population Health, NYU Grossman School of Medicine, New York, NY 10016, United States.
  • Amelia Shunk
    Department of Population Health, NYU Grossman School of Medicine, New York, NY 10016, United States.
  • Devin M Mann
    Department of Population Health, New York University Grossman School of Medicine, New York University, New York, NY, United States.
  • Elizabeth R Stevens
    Department of Population Health, NYU Grossman School of Medicine, New York, NY 10016, United States.

Keywords

External Resources

Popular Topics
Recent Journals