Litcius/Paper detail

Toward Human–AI Interfaces to Support Explainability and Causability in Medical AI

Andreas Holzinger, Heimo Müller

2021Computer93 citationsDOIOpen Access PDF

Abstract

Our concept of causability is a measure of whether and to what extent humans can understand a given machine explanation. We motivate causability with a clinical case from cancer research. We argue for using causability in medical artificial intelligence (AI) to develop and evaluate future human–AI interfaces.

Topics & Concepts

Computer scienceArtificial intelligenceMeasure (data warehouse)Human–computer interactionHuman intelligenceCognitive scienceData sciencePsychologyData miningExplainable Artificial Intelligence (XAI)Machine Learning in HealthcareArtificial Intelligence in Healthcare and Education