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

Synopsis

Simulated diagnostic study with 223 physicians/nurses (1,338 decisions on wound-maceration images with AI recommendations); correct AI raised accuracy 10x, incorrect AI lowered it, with stronger AI influence than provider-related factors — indicating overreliance is a safety risk.

Keywords

·CDSS ·over-reliance ·automation bias ·diagnostic accuracy ·wound assessment

Related entries

• How the different explanation classes impact trust calibration: The case of clinical decision support systems
  October 2022 · International Journal of Human-Computer Studies 2022
• 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
• Automation Bias in AI-Assisted Medical Decision-Making Under Time Pressure in Computational Pathology
  November 1, 2024 · arXiv
• In ChatGPT they trust: a study of students' perceptions and misuse of ChatGPT in higher education
  December 1, 2025 · AI and Ethics 2025
• Impact of AI Tools on Learning Outcomes: Decreasing Knowledge and Over-Reliance
  October 15, 2025 · arXiv