Auditing Fairness and Explainability in Chest X-Ray Image Classifiers

Gemma Bel Bordes, Alan Perotti

2024

Abstract

Advancements in Artificial Intelligence have produced several tools that can be used in medical decision support systems. However, these models often exhibit the so-called ’black-box problem’: an algorithmic diagnosis is produced, but no human-understandable details about the decision process can be obtained. This raises critical questions about fairness and explainability, crucial for equitable healthcare. In this paper we focus on chest X-ray image classification, auditing the reproducibility of previous results in terms of model bias, exploring the applicability of Explainable AI (XAI) techniques, and auditing the fairness of the produced explanations. We highlight the challenges in assessing the quality of explanations provided by XAI methods, particularly in the absence of ground truth. In turn, this strongly hampers the possibility of comparing explanation quality across patients sub-groups, which is a cornerstone in fairness audits. Our experiments illustrate the complexities in achieving transparent AI interpretations in medical diagnostics, underscoring the need both for reliable XAI techniques and more robust fairness auditing methods.

Paper Citation

in Harvard Style

Bel Bordes G. and Perotti A. (2024). Auditing Fairness and Explainability in Chest X-Ray Image Classifiers. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 1308-1315. DOI: 10.5220/0012472400003636

in Bibtex Style

@conference{icaart24,
author={Gemma Bel Bordes and Alan Perotti},
title={Auditing Fairness and Explainability in Chest X-Ray Image Classifiers},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={1308-1315},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012472400003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Auditing Fairness and Explainability in Chest X-Ray Image Classifiers
SN - 978-989-758-680-4
AU - Bel Bordes G.
AU - Perotti A.
PY - 2024
SP - 1308
EP - 1315
DO - 10.5220/0012472400003636
PB - SciTePress