Effect of race and ethnicity on advanced breast cancer risk prediction model performance - Takeaways - MDSpire

Effect of race and ethnicity on advanced breast cancer risk prediction model performance

  • By

  • Karla Kerlikowske

  • Shuai Chen

  • Brian L. Sprague

  • Jeffrey A. Tice

  • Diana L. Miglioretti

  • Rebecca A. Hubbard

  • December 14, 2025

  • 0 min

Share

  • 1

    Excluding race and ethnicity from the advanced breast cancer risk model overestimated risk in Asian women and underestimated risk in Black women.

  • 2

    The percentage of Asian women classified as intermediate/high risk increased significantly when race and ethnicity were excluded from the model.

  • 3

    Fewer Black women were identified as intermediate/high advanced breast cancer risk when race and ethnicity were removed, leading to worse calibration.

  • 4

    The study highlights the importance of including race and ethnicity in risk prediction models to avoid algorithmic bias and ensure equitable healthcare.

  • 5

    Overall discrimination was slightly higher in the model that included race and ethnicity, indicating better predictive performance across diverse groups.

Original Source(s)

Effect of race and ethnicity on advanced breast cancer risk prediction model performance

  • by Karla Kerlikowske, Shuai Chen, Brian L. Sprague, Jeffrey A. Tice, Diana L. Miglioretti, Rebecca A. Hubbard

  • December 14, 2025

Related Content

The ‘brain drain’ narrative about health professionals misses half of the story

Genetic Variations in DNA Methyltransferases and Their Link to Breast Cancer: Findings from a Nested Case-Control Analysis in the Arkansas Rural Community Health Study

Recent findings indicate progress in health equity, but experts express concerns about its sustainability.