How explainable AI affects human performance: A systematic review of the behavioural consequences of saliency maps
R Müller - International Journal of Human–Computer Interaction, 2024 - Taylor & Francis
Saliency maps can explain how deep neural networks classify images. But are they actually
useful for humans? The present systematic review of 68 user studies found that while …
useful for humans? The present systematic review of 68 user studies found that while …
[HTML][HTML] Evidence-based XAI: An empirical approach to design more effective and explainable decision support systems
This paper proposes a user study aimed at evaluating the impact of Class Activation Maps
(CAMs) as an eXplainable AI (XAI) method in a radiological diagnostic task, the detection of …
(CAMs) as an eXplainable AI (XAI) method in a radiological diagnostic task, the detection of …
Invisible to Machines: Designing AI that Supports Vision Work in Radiology
In this article we provide an analysis focusing on clinical use of two deep learning-based
automatic detection tools in the field of radiology. The value of these technologies conceived …
automatic detection tools in the field of radiology. The value of these technologies conceived …
Algorithmic Authority & AI Influence in Decision Settings: Theories and Implications for Design
This workshop explores the influence of AI systems on human decision-making-algorithmic
authority-and the broader concept of technology dominance, which includes both positive …
authority-and the broader concept of technology dominance, which includes both positive …