Post-hoc Orthogonalization for Mitigation of Protected Feature Bias in CXR Embeddings

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Weber, Tobias, Ingrisch, Michael, Bischl, Bernd, Rügamer, David
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913385569845248
author Weber, Tobias
Ingrisch, Michael
Bischl, Bernd
Rügamer, David
author_facet Weber, Tobias
Ingrisch, Michael
Bischl, Bernd
Rügamer, David
contents Purpose: To analyze and remove protected feature effects in chest radiograph embeddings of deep learning models. Methods: An orthogonalization is utilized to remove the influence of protected features (e.g., age, sex, race) in CXR embeddings, ensuring feature-independent results. To validate the efficacy of the approach, we retrospectively study the MIMIC and CheXpert datasets using three pre-trained models, namely a supervised contrastive, a self-supervised contrastive, and a baseline classifier model. Our statistical analysis involves comparing the original versus the orthogonalized embeddings by estimating protected feature influences and evaluating the ability to predict race, age, or sex using the two types of embeddings. Results: Our experiments reveal a significant influence of protected features on predictions of pathologies. Applying orthogonalization removes these feature effects. Apart from removing any influence on pathology classification, while maintaining competitive predictive performance, orthogonalized embeddings further make it infeasible to directly predict protected attributes and mitigate subgroup disparities. Conclusion: The presented work demonstrates the successful application and evaluation of the orthogonalization technique in the domain of chest X-ray image classification.
format Preprint
id arxiv_https___arxiv_org_abs_2311_01349
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Post-hoc Orthogonalization for Mitigation of Protected Feature Bias in CXR Embeddings
Weber, Tobias
Ingrisch, Michael
Bischl, Bernd
Rügamer, David
Machine Learning
Computers and Society
Purpose: To analyze and remove protected feature effects in chest radiograph embeddings of deep learning models. Methods: An orthogonalization is utilized to remove the influence of protected features (e.g., age, sex, race) in CXR embeddings, ensuring feature-independent results. To validate the efficacy of the approach, we retrospectively study the MIMIC and CheXpert datasets using three pre-trained models, namely a supervised contrastive, a self-supervised contrastive, and a baseline classifier model. Our statistical analysis involves comparing the original versus the orthogonalized embeddings by estimating protected feature influences and evaluating the ability to predict race, age, or sex using the two types of embeddings. Results: Our experiments reveal a significant influence of protected features on predictions of pathologies. Applying orthogonalization removes these feature effects. Apart from removing any influence on pathology classification, while maintaining competitive predictive performance, orthogonalized embeddings further make it infeasible to directly predict protected attributes and mitigate subgroup disparities. Conclusion: The presented work demonstrates the successful application and evaluation of the orthogonalization technique in the domain of chest X-ray image classification.
title Post-hoc Orthogonalization for Mitigation of Protected Feature Bias in CXR Embeddings
topic Machine Learning
Computers and Society
url https://arxiv.org/abs/2311.01349