Evaluating algorithmic bias on biomarker classification of breast cancer pathology reports
A thorough evaluation of algorithmic biases that may affect equality in clinical care is a critical step before deploying algorithms in the real world. We found little evidence of algorithmic bias in our biomarker classification tool. Artificial intelligence tools to expedite information extraction from clinical records could accelerate clinical trial matching and improve care.
Authors
- John Gounley
- Patrycja Krawczuk (ORCID: https://orcid.org/0000-0003-4860-9619)
- Heidi A. Hanson (ORCID: https://orcid.org/0000-0003-0056-196X)
- Zachary Fox (ORCID: https://orcid.org/0000-0003-0138-2867)
- Alina Peluso (ORCID: https://orcid.org/0000-0003-2895-0406)
- Xiao‐Cheng Wu (ORCID: https://orcid.org/0000-0003-3663-5027)
- Mayanka Chandrashekar (ORCID: https://orcid.org/0000-0002-3697-5972)
- Dakota Murdock
- Jordan Tschida (ORCID: https://orcid.org/0000-0002-1359-4165)
Institutions
- Louisiana State University (US)
- Oak Ridge National Laboratory (US)
Publication Details
- Journal
- JAMIA Open
- Published
- 2025-05-02
- DOI
- https://doi.org/10.1093/jamiaopen/ooaf033
- Citations
- 1
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 2.48
Funders
- U.S. Department of Energy
- National Institutes of Health
- National Cancer Institute
- Argonne National Laboratory
- Lawrence Livermore National Laboratory
- Oak Ridge National Laboratory
- Los Alamos National Laboratory