News Research Ethics, Regulation, and Responsible Use Research and Evidence

Study: AI misinformation 'significantly' lowers diagnostic accuracy in novice medical students

“This finding highlights a fundamental safety challenge for AI in medical education.” 

April 08, 2026 By Matthew Solan 3 min read
Share
5 Key Takeaways

  • 1

    Misleading AI-generated explanations significantly reduced diagnostic accuracy among junior medical students in a randomized trial.

  • 2

    Correct AI explanations did not improve diagnostic accuracy compared to no explanation, highlighting a safety challenge in medical education.

  • 3

    Students receiving misleading explanations had a 9% diagnostic accuracy, while those with correct explanations had 23% accuracy.

  • 4

    Confidence ratings increased with any AI-generated explanation, regardless of correctness, indicating a misalignment with actual performance.

  • 5

    The study's limitations include a focus on junior students and the use of fully correct versus fully incorrect explanations.

AACE Endocrine AI is published by Conexiant under a license arrangement with the American Association of Clinical Endocrinology, Inc. (AACE®). The ideas and opinions expressed in AACE Endocrine AI do not necessarily reflect those of Conexiant or AACE. For more information, see Policies.

Related Content