On Biases in a UK Biobank-based Retinal Image Classification Model
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912084880523264 |
|---|---|
| author | Alloula, Anissa Mustafa, Rima McGowan, Daniel R Papież, Bartłomiej W. |
| author_facet | Alloula, Anissa Mustafa, Rima McGowan, Daniel R Papież, Bartłomiej W. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_02676 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On Biases in a UK Biobank-based Retinal Image Classification Model Alloula, Anissa Mustafa, Rima McGowan, Daniel R Papież, Bartłomiej W. Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Computers and Society Image and Video Processing 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. |
| title | On Biases in a UK Biobank-based Retinal Image Classification Model |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Computers and Society Image and Video Processing |
| url | https://arxiv.org/abs/2408.02676 |