EUVIMEDEUVIMED entdecken
Open Access

Evaluating algorithmic bias on biomarker classification of breast cancer pathology reports

Jordan Tschida iD, Mayanka Chandrashekar iD, Alina Peluso, Zachary Fox, Patrycja Krawczuk, Dakota Murdock, Xiao-Cheng Wu iD, John Gounley, Heidi A Hanson

JAMIA Open · 02.05.2025 · 8 (3)

DOI: 10.1093/jamiaopen/ooaf033 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JAMIA Open, online erschienen am 09.05.2025. Verfasst von Jordan Tschida und 8 weiteren Autor:innen. Beteiligte Einrichtung: Advanced Computing for Health Sciences, Oak Ridge National Laboratory, Oak Ridge, TN 37830, United States. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCCDPHP CDC HHS, Department of Energy, National Cancer Institute.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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. Materials and Methods We utilized 594 875 electronic pathology reports from 178 121 tumors diagnosed in Kentucky, Louisiana, New Jersey, New Mexico, Seattle, and Utah to train 2 deep-learning algorithms to classify breast cancer patients using their biomarkers test results. We used balanced error rate (BER), demographic parity (DP), equalized odds (EOD), and equal opportunity (EOP) to assess bias.

Results

We found differences in predictive accuracy between registries, with the highest accuracy in the registry that contributed the most data (Seattle Registry, BER ratios for all registries >1.25). BER showed no significant algorithmic bias in extracting biomarkers (estrogen receptor, progesterone receptor, human epidermal growth factor receptor 2) for race, Hispanic ethnicity, age at diagnosis, or socioeconomic subgroups (BER ratio <1.25). DP, EOD, and EOP all showed insignificant results.

Discussion

We observed significant differences in BER by registry, but no significant bias using the DP, EOD, and EOP metrics for socio-demographic or racial categories. This highlights the importance of employing a diverse set of metrics for a comprehensive evaluation of model fairness.

Conclusion

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.

Schlagwörter

Stichwörter der Autor:innen

algorithmic biasartificial intelligencebiomarkersbreast cancerpopulation-level

Autor:innen und Institutionen

  • Advanced Computing for Health Sciences, Oak Ridge National Laboratory, Oak Ridge, TN 37830, United States.
  • Department of Epidemiology, Louisiana State University New Orleans School of Public Health, New Orleans, LA 70112, United States.

ORCID-Profile: Jordan Tschida, Mayanka Chandrashekar, Xiao-Cheng Wu

Förderung

  • NCCDPHP CDC HHS
  • Department of Energy
  • National Cancer Institute
  • National Institutes of Health
  • National Laboratory
  • Lawrence Livermore National Laboratory
  • Los Alamos National Laboratory
  • Oak Ridge National Laboratory

Zitieren

APA

Tschida, J., Chandrashekar, M., Peluso, A., Fox, Z., Krawczuk, P., Murdock, D., Wu, X. C., Gounley, J., & Hanson, H. A. (2025). Evaluating algorithmic bias on biomarker classification of breast cancer pathology reports. JAMIA Open, 8(3). https://doi.org/10.1093/jamiaopen/ooaf033

Vancouver

Tschida J, Chandrashekar M, Peluso A, Fox Z, Krawczuk P, Murdock D, et al. Evaluating algorithmic bias on biomarker classification of breast cancer pathology reports. JAMIA Open. 2025;8(3). doi:10.1093/jamiaopen/ooaf033

BibTeX
@article{Tschida2025,
  author = {Tschida, Jordan and Chandrashekar, Mayanka and Peluso, Alina and Fox, Zachary and Krawczuk, Patrycja and Murdock, Dakota and Wu, Xiao-Cheng and Gounley, John and Hanson, Heidi A},
  title = {Evaluating algorithmic bias on biomarker classification of breast cancer pathology reports},
  journal = {JAMIA Open},
  year = {2025},
  volume = {8},
  number = {3},
  doi = {10.1093/jamiaopen/ooaf033}
}
Kostenlos starten →