Explainability and AI Confidence in Clinical Decision Support Systems: Effects on Trust, Diagnostic Performance, and Cognitive Load in Breast Cancer Care
Olya Rezaeian, Alparslan Emrah Bayrak, Onur Asan
TL;DR
This study addresses how explainability and AI confidence cues affect clinician trust, cognitive load, and diagnostic performance in breast cancer CDSS. Using an online interrupted time-series with 28 clinicians, the work demonstrates that high AI confidence can boost trust but provoke overreliance and reduce accuracy, while low confidence lowers trust and agreement and lengthens decision time. Some explainability features reduce cognitive load when well-designed, yet others increase stress, highlighting design trade-offs. Demographic factors such as age, gender, and professional role substantially shape perceptions and interactions with AI. The findings inform design guidelines for AI-driven CDSS that balance transparency, usability, and cognitive demands to improve integration into clinical workflows.
Abstract
Artificial Intelligence (AI) has demonstrated potential in healthcare, particularly in enhancing diagnostic accuracy and decision-making through Clinical Decision Support Systems (CDSSs). However, the successful implementation of these systems relies on user trust and reliance, which can be influenced by explainable AI. This study explores the impact of varying explainability levels on clinicians trust, cognitive load, and diagnostic performance in breast cancer detection. Utilizing an interrupted time series design, we conducted a web-based experiment involving 28 healthcare professionals. The results revealed that high confidence scores substantially increased trust but also led to overreliance, reducing diagnostic accuracy. In contrast, low confidence scores decreased trust and agreement while increasing diagnosis duration, reflecting more cautious behavior. Some explainability features influenced cognitive load by increasing stress levels. Additionally, demographic factors such as age, gender, and professional role shaped participants' perceptions and interactions with the system. This study provides valuable insights into how explainability impact clinicians' behavior and decision-making. The findings highlight the importance of designing AI-driven CDSSs that balance transparency, usability, and cognitive demands to foster trust and improve integration into clinical workflows.