Interdisciplinary Expertise to Advance Equitable Explainable AI

The field of artificial intelligence (AI) is rapidly influencing health and healthcare, but bias and poor performance persists for populations who face widespread structural oppression. Previous work has clearly outlined the need for more rigorous attention to data representativeness and model perfo...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-05
Main Authors: Bennett, Chloe R, Cole-Lewis, Heather, Farquhar, Stephanie, Haamel, Naama, Babenko, Boris, Lang, Oran, Fleck, Mat, Traynis, Ilana, Lau, Charles, Horn, Ivor, Lyles, Courtney
Format: Article
Language:English
Subjects:
Artificial intelligence
Best practice
Bias
Explainable artificial intelligence
Interdisciplinary aspects
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The field of artificial intelligence (AI) is rapidly influencing health and healthcare, but bias and poor performance persists for populations who face widespread structural oppression. Previous work has clearly outlined the need for more rigorous attention to data representativeness and model performance to advance equity and reduce bias. However, there is an opportunity to also improve the explainability of AI by leveraging best practices of social epidemiology and health equity to help us develop hypotheses for associations found. In this paper, we focus on explainable AI (XAI) and describe a framework for interdisciplinary expert panel review to discuss and critically assess AI model explanations from multiple perspectives and identify areas of bias and directions for future research. We emphasize the importance of the interdisciplinary expert panel to produce more accurate, equitable interpretations which are historically and contextually informed. Interdisciplinary panel discussions can help reduce bias, identify potential confounders, and identify opportunities for additional research where there are gaps in the literature. In turn, these insights can suggest opportunities for AI model improvement.
ISSN:2331-8422