Analysing race and sex bias in brain age prediction

TL;DR

This study investigates racial and sex biases in brain age prediction models using MRI data, revealing significant performance and feature distribution disparities across demographic subgroups, and emphasizing the need for bias mitigation.

Contribution

It provides a comprehensive analysis of demographic biases in a popular brain age prediction model, highlighting the extent of bias and its impact on model performance and features.

Findings

Significant performance differences between racial and sex subgroups.

Distribution shifts in features across demographic groups.

Call for further bias analysis and mitigation in brain age models.

Abstract

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.