Paper 13409-1
Paper 13409-1
Observer performance and eye-tracking variations as a function of AI output format (Invited Paper)
17 February 2025 • 11:00 AM - 11:30 AM PST | Palm 7
Abstract
Artificial intelligence (AI) tools are designed to improve the efficacy and efficiency of data analysis and interpretation by the human decision maker. However, we know little about the optimal ways to present AI output to providers. This study used radiology image interpretation with AI-based decision support to explore the impact of different forms of AI output on reader performance. Four different forms of AI outputs (plus no AI feedback) were evaluated with experienced radiologists and radiology residents. Results reveal that the rates of decision changes prior to and after receiving the AI output differ as a function of the output format and reader experience. More complex output formats (e.g., heat map plus a probability graph) tend to increase reading time and the number of scans between the clinical image and the AI outputs as revealed through eye-tracking.
Presenter
Emory Univ. School of Medicine (United States)
Dr. Krupinski is Professor and Vice-Chair of Research at Emory University in the Departments of Radiology, Psychology and Bioinformatics. She received her BA from Cornell, MA from Montclair State and PhD from Temple, all in Experimental Psychology. Her interests are in medical image perception, observer performance, decision making, human factors, and the interface between humans and computers and how that impacts clinical decision-making efficacy and efficiency. Her research uses eye-tracking to investigate the perceptual and cognitive mechanisms that underlie medical image perception and decision-making, the nature of expertise, the causes of diagnostic error, and the use of technologies like AI to reduce errors, fatigue, and clinician burnout.