Evaluating algorithmic bias on biomarker classification of breast cancer pathology reports.

Journal: JAMIA open
Published Date: May 9, 2025

Abstract

OBJECTIVES: This work evaluated algorithmic bias in biomarkers classification using electronic pathology reports from female breast cancer cases. Bias was assessed across 5 subgroups: cancer registry, race, Hispanic ethnicity, age at diagnosis, and socioeconomic status.

Authors

  • Jordan Tschida
    Advanced Computing for Health Sciences, Oak Ridge National Laboratory, Oak Ridge, TN 37830, United States.
  • Mayanka Chandrashekar
    Advanced Computing for Health Sciences, Oak Ridge National Laboratory, Oak Ridge, TN 37830, United States.
  • Alina Peluso
    Advanced Computing for Health Sciences, Oak Ridge National Laboratory, Oak Ridge, TN 37830, United States.
  • Zachary Fox
    Advanced Computing for Health Sciences, Oak Ridge National Laboratory, Oak Ridge, TN 37830, United States.
  • Patrycja Krawczuk
    Advanced Computing for Health Sciences, Oak Ridge National Laboratory, Oak Ridge, TN 37830, United States.
  • Dakota Murdock
    Advanced Computing for Health Sciences, Oak Ridge National Laboratory, Oak Ridge, TN 37830, United States.
  • Xiao-Cheng Wu
    Department of Epidemiology, Louisiana State University New Orleans School of Public Health, New Orleans, LA 70112, United States.
  • John Gounley
    Advanced Computing for Health Sciences, Oak Ridge National Laboratory, Oak Ridge, TN 37830, United States.
  • Heidi A Hanson
    Advanced Computing for Health Sciences, Oak Ridge National Laboratory, Oak Ridge, TN 37830, United States.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals