Imperial College London
Portrait Picture

Dr Ben Glocker

Faculty of Engineering, Department of Computing

Professor in Machine Learning for Imaging
 
 
 
//

Contact

 

+44 (0)20 7594 8334b.glocker Website CV

 
 
//

Location

 

377Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Glocker:2023:10.1016/j.ebiom.2023.104467,
author = {Glocker, B and Jones, C and Bernhardt, M and Winzeck, S},
doi = {10.1016/j.ebiom.2023.104467},
journal = {EBioMedicine},
pages = {1--19},
title = {Algorithmic encoding of protected characteristics in chest X-ray disease detection models},
url = {http://dx.doi.org/10.1016/j.ebiom.2023.104467},
volume = {89},
year = {2023}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - BackgroundIt has been rightfully emphasized that the use of AI for clinical decision making could amplify health disparities. An algorithm may encode protected characteristics, and then use this information for making predictions due to undesirable correlations in the (historical) training data. It remains unclear how we can establish whether such information is actually used. Besides the scarcity of data from underserved populations, very little is known about how dataset biases manifest in predictive models and how this may result in disparate performance. This article aims to shed some light on these issues by exploring methodology for subgroup analysis in image-based disease detection models.MethodsWe utilize two publicly available chest X-ray datasets, CheXpert and MIMIC-CXR, to study performance disparities across race and biological sex in deep learning models. We explore test set resampling, transfer learning, multitask learning, and model inspection to assess the relationship between the encoding of protected characteristics and disease detection performance across subgroups.FindingsWe confirm subgroup disparities in terms of shifted true and false positive rates which are partially removed after correcting for population and prevalence shifts in the test sets. We find that transfer learning alone is insufficient for establishing whether specific patient information is used for making predictions. The proposed combination of test-set resampling, multitask learning, and model inspection reveals valuable insights about the way protected characteristics are encoded in the feature representations of deep neural networks.InterpretationSubgroup analysis is key for identifying performance disparities of AI models, but statistical differences across subgroups need to be taken into account when analyzing potential biases in disease detection. The proposed methodology provides a comprehensive framework for subgroup analysis enabling further research into the underlyi
AU  - Glocker,B
AU  - Jones,C
AU  - Bernhardt,M
AU  - Winzeck,S
DO  - 10.1016/j.ebiom.2023.104467
EP  - 19
PY  - 2023///
SN  - 2352-3964
SP  - 1
TI  - Algorithmic encoding of protected characteristics in chest X-ray disease detection models
T2  - EBioMedicine
UR  - http://dx.doi.org/10.1016/j.ebiom.2023.104467
UR  - https://www.thelancet.com/journals/ebiom/article/PIIS2352-3964(23)00032-4/fulltext
UR  - http://hdl.handle.net/10044/1/102859
VL  - 89
ER  -
Download