# To which reference class do you belong? Measuring racial fairness of reference classes with normative modeling

arXiv: https://arxiv.org/abs/2407.19114 · HTML: https://mlsanity.com/paper/2407.19114/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 99 references that are in the map.
- First posted on arXiv 26 Jul 2024.

## Builds on (most cited first, 20 of 20)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [Fairness in Criminal Justice Risk Assessments: The State of the Art](https://mlsanity.com/paper/1703.09207/) (2017)
- [Data and its (dis)contents: A survey of dataset development and use in machine learning research](https://mlsanity.com/paper/2012.05345/) (2020)
- [Reading Race: AI Recognises Patient's Racial Identity In Medical Images](https://mlsanity.com/paper/2107.10356/) (2021)
- [A Survey on Data Collection for Machine Learning: a Big Data -- AI Integration Perspective](https://mlsanity.com/paper/1811.03402/) (2018)
- [An Empirical Characterization of Fair Machine Learning For Clinical Risk Prediction](https://mlsanity.com/paper/2007.10306/) (2020)
- [The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations](https://mlsanity.com/paper/2205.03295/) (2022)
- [Benchmarking emergency department triage prediction models with machine learning and large public electronic health records](https://mlsanity.com/paper/2111.11017/) (2021)
- [Write It Like You See It: Detectable Differences in Clinical Notes By Race Lead To Differential Model Recommendations](https://mlsanity.com/paper/2205.03931/) (2022)
- [Potential sources of dataset bias complicate investigation of underdiagnosis by machine learning algorithms](https://mlsanity.com/paper/2201.07856/) (2022)
- [Coarse race data conceals disparities in clinical risk score performance](https://mlsanity.com/paper/2304.09270/) (2023)
- [Compositionally-Warped Gaussian Processes](https://mlsanity.com/paper/1906.09665/) (2019)
- [In the Name of Fairness: Assessing the Bias in Clinical Record De-identification](https://mlsanity.com/paper/2305.11348/) (2023)
- [An Empirical Analysis of Racial Categories in the Algorithmic Fairness Literature](https://mlsanity.com/paper/2309.06607/) (2023)
- [Disparate Censorship & Undertesting: A Source of Label Bias in Clinical Machine Learning](https://mlsanity.com/paper/2208.01127/) (2022)
- [Evaluating the Impact of Social Determinants on Health Prediction in the Intensive Care Unit](https://mlsanity.com/paper/2305.12622/) (2023)
- [The Impact of Differential Feature Under-reporting on Algorithmic Fairness](https://mlsanity.com/paper/2401.08788/) (2024)

## Built on by (most cited first, 1 of 1)

- [Deep Unsupervised Anomaly Detection in Brain Imaging: Large-Scale Benchmarking and Bias Analysis](https://mlsanity.com/paper/2512.01534/) (2025)

## Abstract (arXiv)

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.