# Analysing race and sex bias in brain age prediction

arXiv: https://arxiv.org/abs/2309.10835 · HTML: https://mlsanity.com/paper/2309.10835/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 25 references that are in the map.
- First posted on arXiv 19 Sep 2023.

## Builds on (most cited first, 4 of 4)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Causality matters in medical imaging](https://mlsanity.com/paper/1912.08142/) (2019)
- [Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker](https://mlsanity.com/paper/1612.02572/) (2016)
- [Deep Learning for Brain Age Estimation: A Systematic Review](https://mlsanity.com/paper/2212.03868/) (2022)

## Built on by (most cited first, 4 of 4)

- [FairMedFM: Fairness Benchmarking for Medical Imaging Foundation Models](https://mlsanity.com/paper/2407.00983/) (2024)
- [HyperFusion: A Hypernetwork Approach to Multimodal Integration of Tabular and Medical Imaging Data for Predictive Modeling](https://mlsanity.com/paper/2403.13319/) (2024)
- [The Limits of Fair Medical Imaging AI In The Wild](https://mlsanity.com/paper/2312.10083/) (2023)
- [Predict Patient Self-reported Race from Skin Histological Images](https://mlsanity.com/paper/2507.21912/) (2025)

## Abstract (arXiv)

Brain age prediction from MRI has become a popular imaging biomarker associated with a wide range of neuropathologies. The datasets used for training, however, are often skewed and imbalanced regarding demographics, potentially making brain age prediction models susceptible to bias. We analyse the commonly used ResNet-34 model by conducting a comprehensive subgroup performance analysis and feature inspection. The model is trained on 1,215 T1-weighted MRI scans from Cam-CAN and IXI, and tested on UK Biobank (n=42,786), split into six racial and biological sex subgroups. With the objective of comparing the performance between subgroups, measured by the absolute prediction error, we use a Kruskal-Wallis test followed by two post-hoc Conover-Iman tests to inspect bias across race and biological sex. To examine biases in the generated features, we use PCA for dimensionality reduction and employ two-sample Kolmogorov-Smirnov tests to identify distribution shifts among subgroups. Our results reveal statistically significant differences in predictive performance between Black and White, Black and Asian, and male and female subjects. Seven out of twelve pairwise comparisons show statistically significant differences in the feature distributions. Our findings call for further analysis of brain age prediction models.