Artificial intelligence in combination with human expertise could be the optimal approach to improving diagnostic accuracy while maintaining a safety net in clinical imaging.
References
Dvijotham, K. et al. Nat. Med. https://doi.org/10.1038/s41591-023-02437-x (2023).
McKinney, S. M. et al. Nature 577, 89–94 (2020).
Hickman, S. E. et al. Radiology 302, 88–104 (2022).
Freeman, K. et al. Br. Med. J. 374, 1872 (2021).
Centre for Clinical Artificial Intelligence. https://cai-x.com/projects/magic (accessed 5 June 2023).
Cancer Registry of Norway. https://www.kreftregisteret.no/en/Research/Projects/aims/ (accessed 5 June 2023).
Lauritzen, A. D. et al. Radiology 304, 41–49 (2022).
Gur, D. et al. J. Natl. Cancer Inst. 96, 185–190 (2004).
Lehman, C. et al. JAMA Intern. Med. 175, 1828–1837 (2015).
Vela, D. et al. Sci. Rep. 12, 11654 (2022).
Chen, Y. et al. Radiol. Imaging Cancer 2, 5 (2020).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
F.G. undertakes consultancy for Bayer and Alphabet Inc and has research collaborations with GE Healthcare, Lunit, Volpara, Screenpoint, iCad and Merantix.
Rights and permissions
About this article
Cite this article
Gilbert, F. Balancing human and AI roles in clinical imaging. Nat Med 29, 1609–1610 (2023). https://doi.org/10.1038/s41591-023-02441-1
Published:
Issue Date:
DOI: https://doi.org/10.1038/s41591-023-02441-1
- Springer Nature America, Inc.