Designing Theory-Driven User-Centric Explainable AI

Explore a conference talk that delves into the theoretical foundations of explainable AI (XAI) and its application in human-centered design. Learn about a proposed conceptual framework that bridges algorithm-generated explanations with human decision-making theories, drawing insights from philosophy and psychology. Discover how this framework can be applied to mitigate cognitive biases and improve AI-assisted decision-making in high-stakes fields like healthcare and criminal justice. Gain insights from a case study involving the design and implementation of an explainable clinical diagnostic tool for intensive care phenotyping, including a co-design exercise with clinicians. Understand the implications of this approach for future XAI design and development, and how it can enhance the effectiveness of AI systems in supporting critical human decisions.