Explainable AI, but explainable to whom?

TL;DR

This paper investigates how explainable AI (xAI) needs to be tailored to different stakeholders in healthcare, specifically during COVID-19 patient classification, highlighting diverse explanation requirements and practical adjustments for better implementation.

Contribution

It reveals that various stakeholders have distinct explanation needs in healthcare xAI, emphasizing the importance of stakeholder-specific explanations for effective AI deployment.

Findings

Different stakeholder groups have unique explanation needs.

Explanation needs emerge from stakeholder-specific concerns.

Insights for customizing xAI in healthcare contexts.

Abstract

Advances in AI technologies have resulted in superior levels of AI-based model performance. However, this has also led to a greater degree of model complexity, resulting in 'black box' models. In response to the AI black box problem, the field of explainable AI (xAI) has emerged with the aim of providing explanations catered to human understanding, trust, and transparency. Yet, we still have a limited understanding of how xAI addresses the need for explainable AI in the context of healthcare. Our research explores the differing explanation needs amongst stakeholders during the development of an AI-system for classifying COVID-19 patients for the ICU. We demonstrate that there is a constellation of stakeholders who have different explanation needs, not just the 'user'. Further, the findings demonstrate how the need for xAI emerges through concerns associated with specific stakeholder groups i.e., the development team, subject matter experts, decision makers, and the audience. Our findings contribute to the expansion of xAI by highlighting that different stakeholders have different explanation needs. From a practical perspective, the study provides insights on how AI systems can be adjusted to support different stakeholders needs, ensuring better implementation and operation in a healthcare context.