Entry

How the different explanation classes impact trust calibration: The case of clinical decision support systems

Mohammad Naiseh, Dena Al-Thani, Nan Jiang, Raian Ali

Synopsis

Evaluates four explanation classes during human-AI decision-making tasks: providing explanations can paradoxically induce over-reliance on AI recommendations, even when two classes are perceived more understandable.

Keywords

·XAI ·trust calibration ·CDSS ·over-reliance ·explanation design

Open paper ↗ Report issue ↗

Related entries

Impact of AI recommendation correctness on diagnostic accuracy in clinical decision-making

November 19, 2025 · International Journal of Medical Informatics 2026
Psychological Factors Influencing Appropriate Reliance on AI-enabled Clinical Decision Support Systems: Experimental Web-Based Study Among Dermatologists

April 4, 2025 · Journal of Medical Internet Research 2025
Facilitating Trust Calibration in Artificial Intelligence-Driven Diagnostic Decision Support Systems for Determining Physicians' Diagnostic Accuracy: Quasi-Experimental Study

November 27, 2024 · JMIR Formative Research 2024
Dynamic calibration of trust and trustworthiness in AI-enabled systems

2026 · International Journal on Software Tools for Technology Transfer 2026
Sometimes right, sometimes wrong: Drivers' responses to inconsistently accurate automated vehicle system confidence information

January 20, 2026 · Accident Analysis & Prevention 2026
Impact of AI Tools on Learning Outcomes: Decreasing Knowledge and Over-Reliance

October 15, 2025 · arXiv