# The Role of Subgroup Separability in Group-Fair Medical Image Classification

Source: [The Role of Subgroup Separability in Group-Fair Medical Image Classification](<https://www.sota2.com/research/paper/68fa70031e209131cea48937>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T04:37:08.858Z

Authors: Charles Jones, M\\'elanie Roschewitz, Ben Glocker

Published: 2023-07-06T06:06:47.000Z

## Abstract

We investigate performance disparities in deep classifiers. We find that the ability of classifiers to separate individuals into subgroups varies substantially across medical imaging modalities and protected characteristics; crucially, we show that this property is predictive of algorithmic bias. Through theoretical analysis and extensive empirical evaluation, we find a relationship between subgroup separability, subgroup disparities, and performance degradation when models are trained on data with systematic bias such as underdiagnosis. Our findings shed new light on the question of how models become biased, providing important insights for the development of fair medical imaging AI.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2307.02791>)

[PDF](<https://arxiv.org/pdf/2307.02791.pdf>)

[Implementation](<https://github.com/biomedia-mira/subgroup-separability>)