Identifying the 'Right' Level of Explanation in a Given Situation

Abstract

We present a framework for defining the "right" level of explainability based on technical, legal and economic considerations. Our approach involves three logical steps: First, define the main contextual factors, such as who is the audience of the explanation, the operational context, the level of harm that the system could cause, and the legal/regulatory framework. This step will help characterize the operational and legal needs for explanation, and the corresponding social benefits. Second, examine the technical tools available, including post-hoc approaches (input perturbation, saliency maps...) and hybrid AI approaches. Third, as function of the first two steps, choose the right levels of global and local explanation outputs, taking into the account the costs involved. We identify seven kinds of costs and emphasize that explanations are socially useful only when total social benefits exceed costs.

Explainability for artificial intelligence in healthcare: a multidisciplinary perspective

“…Yet, it is important to note that for AI-based CDSS the extent of the information is a priori highly difficult to define, has to be adjusted to the respective use case, and will certainly need clarification from the legislative bodies. For this, a framework for defining the "right" level of explainability, as Beaudouin et al put it [15], should be developed. Clearly, this also raises important questions about the role and tasks of physicians, underscoring the need for tailored training and professional development in the area of medical AI.…”