Skip to main content

Thank you for visiting You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

The reproducibility issues that haunt health-care AI

Access options

Rent or buy this article

Get just this article for as long as you need it


Prices may be subject to local taxes which are calculated during checkout

Nature 613, 402-403 (2023)


Updates & Corrections

  • Correction 12 January 2023: An earlier version of this feature erroneously stated that Sayash Kapoor discovered reproducibility failures and pitfalls in 329 studies across 17 fields. In fact, those studies had themselves reported reproducibility failures and pitfalls.


  1. Yu, K. H. et al. J. Med. Internet Res. 22, e16709 (2020).

    Article  PubMed  Google Scholar 

  2. Roberts, M. et al. Nature Mach. Intell. 3, 199–217 (2021).

    Article  Google Scholar 

  3. McDermott, M. B. A. et al. Sci. Transl. Med. 13, eabb1655 (2021).

    Article  PubMed  Google Scholar 

  4. Wong, A. et al. JAMA Intern. Med. 181, 1065–1070 (2021).

    Article  PubMed  Google Scholar 

  5. Mongan, J., Moy, L. & Kahn, C. E. Radiol. Artif. Intell. 2, e200029 (2020).

    Article  PubMed  Google Scholar 

Download references


Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing


Quick links