Can incorrect artificial intelligence (AI) results impact radiologists, and if so, what can we do about it? A multi-reader pilot study of lung cancer detection with chest radiography - Takeaways - MDSpire

Can incorrect artificial intelligence (AI) results impact radiologists, and if so, what can we do about it? A multi-reader pilot study of lung cancer detection with chest radiography

  • By

  • Michael H. Bernstein

  • Michael K. Atalay

  • Elizabeth H. Dibble

  • Aaron W. P. Maxwell

  • Adib R. Karam

  • Saurabh Agarwal

  • Robert C. Ward

  • Terrance T. Healey

  • Grayson L. Baird

  • June 2, 2023

  • 0 min

Share

  • 1

    AI usage in radiology has surged, with 141 systems approved from 2020 to 2022, indicating widespread adoption among radiologists.

  • 2

    AI systems exhibit sensitivity and specificity rates of 0.87 and 0.89, respectively, leading to potential false negatives and positives in diagnoses.

  • 3

    Incorrect AI results can negatively influence radiologist decisions, as evidenced by studies showing lower cancer detection rates with false negative AI feedback.

  • 4

    The study aims to explore how human factors, such as AI result presentation, can be optimized to mitigate the adverse effects of incorrect AI feedback.

  • 5

    This research is the first to empirically investigate the impact of incorrect AI results on radiologist performance and the role of human factors in AI implementation.

Original Source(s)

Related Content