Generative artificial intelligence as a source of breast cancer information for patients: Proceed with caution
Because ChatGPT 3.5 responses were incorrect 24% of the time and did not provide real references 41% of the time, patients should be cautioned about using ChatGPT for medical information.
Authors
- Filipa C. Lynce (ORCID: https://orcid.org/0000-0001-6615-7076)
- Faina Nakhlis (ORCID: https://orcid.org/0000-0003-4752-0161)
- Elizabeth A. Mittendorf (ORCID: https://orcid.org/0000-0002-9762-8536)
- Susan Rafte
- Laura Warren (ORCID: https://orcid.org/0000-0002-7418-6405)
- Ko Un Park (ORCID: https://orcid.org/0000-0002-1495-9920)
- Joel S. Weissman (ORCID: https://orcid.org/0000-0002-4990-6263)
- Tari A. King (ORCID: https://orcid.org/0000-0003-3602-2351)
- Stuart R. Lipsitz (ORCID: https://orcid.org/0000-0003-2619-1389)
- Laura Stewart Dominici (ORCID: https://orcid.org/0000-0001-6053-1979)
- Lourdes Hernández
- Nadine Eidman
- Adrienne G. Waks
- Jeannie Frazier
- Delia Stroud
- Christina A. Minami
- Carla Leslie
Institutions
- Brigham and Women's Hospital (US)
- The University of Texas MD Anderson Cancer Center (US)
- Harvard University (US)
- Dana-Farber Cancer Institute (US)
- Dana-Farber Brigham Cancer Center (US)
Publication Details
- Journal
- Cancer
- Published
- 2024-08-30
- DOI
- https://doi.org/10.1002/cncr.35521
- Citations
- 11
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 1.32