Summary of To Which Reference Class Do You Belong? Measuring Racial Fairness Of Reference Classes with Normative Modeling, by Saige Rutherford et al.
To which reference class do you belong? Measuring racial fairness of reference classes with normative modeling
by Saige Rutherford, Thomas Wolfers, Charlotte Fraza, Nathaniel G. Harnett, Christian F. Beckmann, Henricus G. Ruhe, Andre F. Marquand
First submitted to arxiv on: 26 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computer Vision and Pattern Recognition (cs.CV); Computers and Society (cs.CY)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel study investigates the impact of demographics on reference classes in healthcare, particularly in structural brain imaging. The authors propose normative modeling as a method for building reference classes and evaluate the fairness (racial bias) in widely used models. They predict self-reported race using deviation scores from three different reference class normative models to better understand bias in an integrated, multivariate sense. The results reveal racial disparities that are difficult to address with existing data or techniques. The study highlights the importance of considering demographic mismatch when assigning clinical meaning to deviations and underscores the need for more representative samples. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A team of researchers explored how demographics affect reference classes in healthcare, focusing on brain imaging. They created a new way to build these reference classes using “normative modeling” and tested whether including race makes the models fairer. The study found that current brain imaging models are biased towards certain racial groups. This means that when doctors use these models to diagnose patients, they might be making incorrect assumptions about people’s brains based on their race. The researchers think that having more diverse reference classes would help fix this problem. |
