Korean Journal of Radiology

The Korean Society of Radiology (대한영상의학회)
권호 표지
DOI QR코드

DOI QR Code

Caveats in Using Abnormality/Probability Scores from Artificial Intelligence Algorithms: Neither True Probability nor Level of Trustworthiness

  • Seong Ho Park (Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center) ;
  • Eui Jin Hwang (Department of Radiology, Seoul National University Hospital, Seoul National University College of Medicine)
  • Received : 2024.02.07
  • Accepted : 2024.02.08
  • Published : 2024.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

Keywords

References

  1. Faghani S, Gamble C, Erickson BJ. Uncover this tech term: uncertainty quantification for deep learning. Korean J Radiol 2024;25:395-398 https://doi.org/10.3348/kjr.2024.0108
  2. Park SH, Han K. Methodologic guide for evaluating clinical performance and effect of artificial intelligence technology for medical diagnosis and prediction. Radiology 2018;286:800-809 https://doi.org/10.1148/radiol.2017171920
  3. Van Calster B, McLernon DJ, van Smeden M, Wynants L, Steyerberg EW. Calibration: the Achilles heel of predictive analytics. BMC Med 2019;17:230
  4. Zhang K, Khosravi B, Vahdati S, Erickson BJ. FDA review of radiologic AI algorithms: process and challenges. Radiology 2024;310:e230242
  5. U.S. Food & Drug Administration. Clinical performance assessment: considerations for computer-assisted detection devices applied to radiology images and radiology device data in premarket notification (510(k)) submissions [accessed on February 7, 2024]. Available at: https://www.fda.gov/regulatory-information/search-fda-guidance-documents/clinical-performance-assessment-considerations-computerassisted-detection-devices-applied-radiology
  6. Van Calster B, Steyerberg EW, Wynants L, van Smeden M. There is no such thing as a validated prediction model. BMC Med 2023;21:70
  7. Futoma J, Simons M, Panch T, Doshi-Velez F, Celi LA. The myth of generalisability in clinical research and machine learning in health care. Lancet Digit Health 2020;2:e489-e492 https://doi.org/10.1016/S2589-7500(20)30186-2
  8. Hwang EJ, Goo JM, Yoon SH, Beck KS, Seo JB, Choi BW, et al. Use of artificial intelligence-based software as medical devices for chest radiography: a position paper from the Korean Society of Thoracic Radiology. Korean J Radiol 2021;22:1743-1748 https://doi.org/10.3348/kjr.2021.0544
  9. Lee SE, Hong H, Kim E. Positive predictive values of abnormality scores from a commercial artificial intelligencebased computer-aided diagnosis for mammography. Korean J Radiol 2024;25:343-350 https://doi.org/10.3348/kjr.2023.0907
  10. Faghani S, Moassefi M, Rouzrokh P, Khosravi B, Baffour FI, Ringler MD, et al. Quantifying uncertainty in deep learning of radiologic images. Radiology 2023;308:e222217