Saved in:
Bibliographic Details
Main Authors: Moukheiber, Dana, Mahindre, Saurabh, Moukheiber, Lama, Moukheiber, Mira, Gao, Mingchen
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.18196
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917623837491200
author Moukheiber, Dana
Mahindre, Saurabh
Moukheiber, Lama
Moukheiber, Mira
Gao, Mingchen
author_facet Moukheiber, Dana
Mahindre, Saurabh
Moukheiber, Lama
Moukheiber, Mira
Gao, Mingchen
contents There has been significant progress in implementing deep learning models in disease diagnosis using chest X- rays. Despite these advancements, inherent biases in these models can lead to disparities in prediction accuracy across protected groups. In this study, we propose a framework to achieve accurate diagnostic outcomes and ensure fairness across intersectional groups in high-dimensional chest X- ray multi-label classification. Transcending traditional protected attributes, we consider complex interactions within social determinants, enabling a more granular benchmark and evaluation of fairness. We present a simple and robust method that involves retraining the last classification layer of pre-trained models using a balanced dataset across groups. Additionally, we account for fairness constraints and integrate class-balanced fine-tuning for multi-label settings. The evaluation of our method on the MIMIC-CXR dataset demonstrates that our framework achieves an optimal tradeoff between accuracy and fairness compared to baseline methods.
format Preprint
id arxiv_https___arxiv_org_abs_2403_18196
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Looking Beyond What You See: An Empirical Analysis on Subgroup Intersectional Fairness for Multi-label Chest X-ray Classification Using Social Determinants of Racial Health Inequities
Moukheiber, Dana
Mahindre, Saurabh
Moukheiber, Lama
Moukheiber, Mira
Gao, Mingchen
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Computers and Society
There has been significant progress in implementing deep learning models in disease diagnosis using chest X- rays. Despite these advancements, inherent biases in these models can lead to disparities in prediction accuracy across protected groups. In this study, we propose a framework to achieve accurate diagnostic outcomes and ensure fairness across intersectional groups in high-dimensional chest X- ray multi-label classification. Transcending traditional protected attributes, we consider complex interactions within social determinants, enabling a more granular benchmark and evaluation of fairness. We present a simple and robust method that involves retraining the last classification layer of pre-trained models using a balanced dataset across groups. Additionally, we account for fairness constraints and integrate class-balanced fine-tuning for multi-label settings. The evaluation of our method on the MIMIC-CXR dataset demonstrates that our framework achieves an optimal tradeoff between accuracy and fairness compared to baseline methods.
title Looking Beyond What You See: An Empirical Analysis on Subgroup Intersectional Fairness for Multi-label Chest X-ray Classification Using Social Determinants of Racial Health Inequities
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Computers and Society
url https://arxiv.org/abs/2403.18196