# On Biases in a UK Biobank-based Retinal Image Classification Model

arXiv: https://arxiv.org/abs/2408.02676 · HTML: https://mlsanity.com/paper/2408.02676/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 32 references that are in the map.
- First posted on arXiv 30 Jul 2024.

## Builds on (most cited first, 17 of 17)

- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [SWAD: Domain Generalization by Seeking Flat Minima](https://mlsanity.com/paper/2102.08604/) (2021)
- [Learning Not to Learn: Training Deep Neural Networks with Biased Data](https://mlsanity.com/paper/1812.10352/) (2018)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [Simple data balancing achieves competitive worst-group-accuracy](https://mlsanity.com/paper/2110.14503/) (2021)
- [A Clarification of the Nuances in the Fairness Metrics Landscape](https://mlsanity.com/paper/2106.00467/) (2021)
- [Fairness by Learning Orthogonal Disentangled Representations](https://mlsanity.com/paper/2003.05707/) (2020)
- [MEDFAIR: Benchmarking Fairness for Medical Imaging](https://mlsanity.com/paper/2210.01725/) (2022)
- [Fairness in Cardiac MR Image Analysis: An Investigation of Bias Due to Data Imbalance in Deep Learning Based Segmentation](https://mlsanity.com/paper/2106.12387/) (2021)
- [Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers](https://mlsanity.com/paper/2203.04913/) (2022)
- [FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis](https://mlsanity.com/paper/2310.05055/) (2023)
- [Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification](https://mlsanity.com/paper/2109.09818/) (2021)
- [Minimax Group Fairness: Algorithms and Experiments](https://mlsanity.com/paper/2011.03108/) (2020)
- [The Role of Subgroup Separability in Group-Fair Medical Image Classification](https://mlsanity.com/paper/2307.02791/) (2023)
- [Unveiling Fairness Biases in Deep Learning-Based Brain MRI Reconstruction](https://mlsanity.com/paper/2309.14392/) (2023)
- [Distributionally Robust Optimization and Invariant Representation Learning for Addressing Subgroup Underrepresentation: Mechanisms and Limitations](https://mlsanity.com/paper/2308.06434/) (2023)

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

- [Fool Me Once? Contrasting Textual and Visual Explanations in a Clinical Decision-Support Setting](https://mlsanity.com/paper/2410.12284/) (2024)
- [Subgroups Matter for Robust Bias Mitigation](https://mlsanity.com/paper/2505.21363/) (2025)
- [Exploring the Effectiveness of Deep Features from Domain-Specific Foundation Models in Retinal Image Synthesis](https://mlsanity.com/paper/2506.11753/) (2025)
- [Beyond Predictive Fairness: Quantifying Attribution Consistency Across Demographic Groups in Diabetic Retinopathy Screening](https://mlsanity.com/paper/2608.18759/) (2026)

## Abstract (arXiv)

Recent work has uncovered alarming disparities in the performance of machine learning models in healthcare. In this study, we explore whether such disparities are present in the UK Biobank fundus retinal images by training and evaluating a disease classification model on these images. We assess possible disparities across various population groups and find substantial differences despite strong overall performance of the model. In particular, we discover unfair performance for certain assessment centres, which is surprising given the rigorous data standardisation protocol. We compare how these differences emerge and apply a range of existing bias mitigation methods to each one. A key insight is that each disparity has unique properties and responds differently to the mitigation methods. We also find that these methods are largely unable to enhance fairness, highlighting the need for better bias mitigation methods tailored to the specific type of bias.