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.

Clinical decisions using AI must consider patient values

Built-in decision thresholds for AI diagnostics are ethically problematic, as patients may differ in their attitudes about the risk of false-positive and false-negative results, which will require that clinicians assess patient values.

This is a preview of subscription content

Access options

Buy article

Get time limited or full article access on ReadCube.


All prices are NET prices.

Fig. 1: Six possible decision pathways using AI algorithms for breast cancer screening.


  1. McCradden, M. D. et al. Nat. Med. 26, 1325–1326 (2020).

    CAS  Article  Google Scholar 

  2. Grote, T. & Berens, P. J. Med. Ethics 46, 205–211 (2019).

    Article  Google Scholar 

  3. Tschandl, P. et al. Nat. Med. 26, 1229–1234 (2020).

    CAS  Article  Google Scholar 

  4. McKinney, S. M. et al. Nature 577, 89–94 (2020).

    CAS  Article  Google Scholar 

  5. Liu, Z. et al. Phys. Med. Biol. 66, 124002 (2021).

    Article  Google Scholar 

  6. Komorowski, M. et al. Nat. Med. 24, 1716–1720 (2018).

    CAS  Article  Google Scholar 

  7. Turbé, V. et al. Nat. Med. 27, 1165–1170 (2021).

    Article  Google Scholar 

  8. Claassen, J. et al. N. Engl. J. Med. 380, 2497–2505 (2019).

    Article  Google Scholar 

  9. Hastie, T. The Elements of Statistical Learning: Data Mining, Inference, and Prediction (Springer, 2009).

  10. Plutynski, A. in Exploring Inductive Risk: Case Studies of Values in Science (eds. Elliott, K. C. & Richards, T.) 149–170 (Oxford University Press, 2017).

  11. Douglas, H.E. Science, Policy, and the Value-free Ideal (University of Pittsburgh Press, 2009).

  12. Bright, L. K. Synthese 195, 2227–2245 (2017).

    Article  Google Scholar 

  13. Wenner, D. M. Int. J. Fem. Approaches Bioeth. 13, 28–48 (2020).

    Article  Google Scholar 

  14. Buchak, L. J. Med. Ethics 43, 90–95 (2016).

    Article  Google Scholar 

  15. Pan, C. H. & Statman, M. J. Invest. Consult. 13, 54–63 (2012).

    Google Scholar 

  16. Ongena, Y. P. et al. J. Am. Coll. Radiol. 18, 79–86 (2021).

    Article  Google Scholar 

  17. Birch, J., Creel, K., Jha, A. & Plutynski, A. Zenodo (2021).

  18. Nagler, R. H. et al. Med. Care 55, 879–885 (2017).

    Article  Google Scholar 

Download references


We thank S. Bhalla, L. Kofi Bright, A. Houston, L. Hudetz, R. Short, J. Swamidass, K. Vredenburgh, Z. Ward, K. Wright and patient groups at Washington University in St Louis, Stanford University and Johns Hopkins University for their input and advice. A.K.J. acknowledges support from the National Institute of Biomedical Imaging and Bioengineering of the US National Institutes of Health (R01-EB031051 and R56-EB028287).

Author information

Authors and Affiliations



All authors contributed to conceptualization, methodology (survey design), investigation (consulting patients), and writing (review and editing). J.B. wrote the original draft.

Corresponding author

Correspondence to Jonathan Birch.

Ethics declarations

Competing interests

The authors declare no competing interests.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Birch, J., Creel, K.A., Jha, A.K. et al. Clinical decisions using AI must consider patient values. Nat Med 28, 229–232 (2022).

Download citation

  • Published:

  • Issue Date:

  • DOI:


Quick links

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