Explanation Ontology in Action: A Clinical Use-Case

TL;DR

This paper introduces an Explanation Ontology designed to semantically represent user-centric explanations in AI, demonstrated through a clinical use-case to aid system designers in explanation planning.

Contribution

It presents a novel Explanation Ontology and provides practical guidance and an example for integrating explanations into AI system design, especially in clinical contexts.

Findings

Ontology effectively models explanation types and user needs.

Guidance improves explanation integration in AI systems.

Clinical case demonstrates practical application.

Abstract

We addressed the problem of a lack of semantic representation for user-centric explanations and different explanation types in our Explanation Ontology (https://purl.org/heals/eo). Such a representation is increasingly necessary as explainability has become an important problem in Artificial Intelligence with the emergence of complex methods and an uptake in high-precision and user-facing settings. In this submission, we provide step-by-step guidance for system designers to utilize our ontology, introduced in our resource track paper, to plan and model for explanations during the design of their Artificial Intelligence systems. We also provide a detailed example with our utilization of this guidance in a clinical setting.