Skip to main content

Thank you for visiting nature.com. 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.

  • NEWS

Dozens of AI disease-prediction models were trained on dubious data

The models are designed to predict someone’s risk of diabetes or stroke. A few might already have been used on patients.
By
  1. Mohana Basu
Save article
View saved research

Dubious data sets are being used to train artificial-intelligence models that are designed to predict people’s risk of stroke and diabetes, researchers report in a preprint1 on medRxiv. Some of the models seem to have been used in clinical settings, although it’s not clear whether this has led to flawed diagnoses. At least two journals are investigating studies that used these data sets.

Access options

Access through your institution

Rent or buy this article

Prices vary by article type

from$1.95

to$39.95

Learn more

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

doi: https://doi.org/10.1038/d41586-026-00697-4

References

  1. Gibson, A. D., White, N. M., Collins, G. S. & Barnett, A. G. Preprint at medRxiv https://doi.org/10.64898/2026.02.24.26347028 (2026).

  2. Karpagam, M. et al. Sci. Rep. 15, 11633 (2025).

    Article  Google Scholar 

  3. Lu’o, N. I. S., Sengkey, D. F. & Joseph, V. F. F. Indones. J. Electron. Electromed. Eng. Med. Inform. 7, 387–400 (2025).

    Article  Google Scholar 

Download references

Related Articles

Subjects

Latest on:

Nature Careers

Jobs

  • Talent Recruitment Announcement at the College of Artificial Intelligence

    Join HZAU's global faculty team to advance research with competitive benefits.

    Wuhan, Hubei (CN)

    Huazhong Agricultural University (HZAU)

  • Associate or Senior Editor, BMC Nursing

    Job Title:    Associate or Senior Editor, BMC Nursing Location:   Shanghai or Pune – hybrid working model Application Deadline: 30th October 2026  ...

    Shanghai or Pune – hybrid working model

    Springer Nature Ltd

  • Associate or Senior Editor, BMC Psychology

    Job Title:    Associate or Senior Editor, BMC Psychology Location:   Shanghai or London – hybrid working model Application Deadline: 30th October, ...

    Shanghai or London – hybrid working model

    Springer Nature Ltd

  • Publisher or Senior Publisher

    Job Title: Publisher or Senior Publisher Location: Beijing or Shanghai - Hybrid Working Model Application Deadline: 25th October 2026       About S...

    Beijing or Shanghai - Hybrid Working Model

    Springer Nature Ltd

  • Global Recruitment of Outstanding Young Talents

    We are seeking exceptional candidates who qualify for the National Science Fund for Excellent Young Scholars (Overseas)

    1068 Xueyuan Avenue, Shenzhen 518055 P. R. China

    Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences（CAS)

Search

Advanced search

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