Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.19114 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909533188653056 |
|---|---|
| author | Rutherford, Saige Wolfers, Thomas Fraza, Charlotte Harnett, Nathaniel G. Beckmann, Christian F. Ruhe, Henricus G. Marquand, Andre F. |
| author_facet | Rutherford, Saige Wolfers, Thomas Fraza, Charlotte Harnett, Nathaniel G. Beckmann, Christian F. Ruhe, Henricus G. Marquand, Andre F. |
| contents | Reference classes in healthcare establish healthy norms, such as pediatric growth charts of height and weight, and are used to chart deviations from these norms which represent potential clinical risk. How the demographics of the reference class influence clinical interpretation of deviations is unknown. Using normative modeling, a method for building reference classes, we evaluate the fairness (racial bias) in reference models of structural brain images that are widely used in psychiatry and neurology. We test whether including race in the model creates fairer models. We predict self-reported race using the deviation scores from three different reference class normative models, to better understand bias in an integrated, multivariate sense. Across all of these tasks, we uncover racial disparities that are not easily addressed with existing data or commonly used modeling techniques. Our work suggests that deviations from the norm could be due to demographic mismatch with the reference class, and assigning clinical meaning to these deviations should be done with caution. Our approach also suggests that acquiring more representative samples is an urgent research priority. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_19114 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | To which reference class do you belong? Measuring racial fairness of reference classes with normative modeling Rutherford, Saige Wolfers, Thomas Fraza, Charlotte Harnett, Nathaniel G. Beckmann, Christian F. Ruhe, Henricus G. Marquand, Andre F. Machine Learning Computer Vision and Pattern Recognition Computers and Society Reference classes in healthcare establish healthy norms, such as pediatric growth charts of height and weight, and are used to chart deviations from these norms which represent potential clinical risk. How the demographics of the reference class influence clinical interpretation of deviations is unknown. Using normative modeling, a method for building reference classes, we evaluate the fairness (racial bias) in reference models of structural brain images that are widely used in psychiatry and neurology. We test whether including race in the model creates fairer models. We predict self-reported race using the deviation scores from three different reference class normative models, to better understand bias in an integrated, multivariate sense. Across all of these tasks, we uncover racial disparities that are not easily addressed with existing data or commonly used modeling techniques. Our work suggests that deviations from the norm could be due to demographic mismatch with the reference class, and assigning clinical meaning to these deviations should be done with caution. Our approach also suggests that acquiring more representative samples is an urgent research priority. |
| title | To which reference class do you belong? Measuring racial fairness of reference classes with normative modeling |
| topic | Machine Learning Computer Vision and Pattern Recognition Computers and Society |
| url | https://arxiv.org/abs/2407.19114 |