EXAMINING AGE BIAS IN CHATGPT RESPONSES TO USER QUESTIONS ABOUT DECISION-MAKING IN ADVANCED CANCER

Meghan McDarby, Emily Mroz, Jessica Hahne, Brian Carpenter, Patricia Parker · 2024

Read EXAMINING AGE BIAS IN CHATGPT RESPONSES TO USER QUESTIONS ABOUT DECISION-MAKING IN ADVANCED CANCER by Meghan McDarby, Emily Mroz, Jessica Hahne, Brian Carpenter, Patricia Parker (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11690016.txt.

Description

Meghan McDarby and co-authors probe ChatGPT for age bias in cancer advice. They fed the chatbot one patient's hard question: with advanced cancer, chase more treatment or guard quality of life? The patient's stated age changed across runs, forty-five, sixty-five, or eighty-five, while race, ethnicity, and insurance status also varied in turn. Trained coders scored the replies for nine decision topics.

Responses to the forty-five-year-old mentioned considering clinical trials clearly more often than replies to the older patients. A softer trend pointed the same way for suggesting second opinions. Hospice, palliative care, and talking with doctors came up evenly across ages. The authors flag a tilt toward aggressive paths for the young that patients and clinicians should know about.

Catalog record

CREATORMeghan McDarby, Emily Mroz, Jessica Hahne, Brian Carpenter, Patricia Parker
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE2 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11690016

Browse the full library · About the Tower of Babel