• NEWS AND VIEWS

An open AI model could help medical experts to interpret chest X-rays

An accessible and adaptable artificial-intelligence model trained on a diverse set of X-ray images is better than existing models at spotting rare chest diseases.
By
  1. Namkug Kim

    1. Namkug Kim is in the Department of Convergence Medicine and the Department of Radiology, University of Ulsan College of Medicine, Seoul 05506, South Korea.

Access through your institution
Buy or subscribe

Chest X-ray is the main imaging tool used to diagnose lung diseases because it is accessible, affordable and efficient. As a first-line modality in clinical practice, it is widely used to assess serious respiratory conditions such as COVID-19 complications, pneumonia, tuberculosis and lung cancer1. Its non-invasive nature, rapid image acquisition and low radiation levels make it an indispensable diagnostic tool1. However, the projection of multiple anatomical structures onto a single image presents challenges for accurate interpretation2. Writing in Nature, Ma et al.3 introduce an artificial intelligence (AI) model designed to address the key challenges of interpreting chest X-rays.

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/d41586-025-01525-x

References

  1. Kim, J. & Kim, K. H. Transl. Lung Cancer Res. 9, 522–531 (2020).

    Article  PubMed  Google Scholar 

  2. Philip, B. et al. Indian J. Thorac. Cardiovasc. Surg. 39, 42–52 (2023).

    Article  PubMed  Google Scholar 

  3. Ma, D., Pang, J., Gotway, M. B. & Liang, J. Nature https://doi.org/10.1038/s41586-025-09079-8 (2025).

    Article  Google Scholar 

  4. Hosny, A., Parmar, C., Quackenbush, J., Schwartz, L. H. & Aerts, H. J. W. L. Nature Rev. Cancer 18, 500–510 (2018).

    Article  PubMed  Google Scholar 

  5. Bommasani, R. et al. Preprint at arXiv https://doi.org/10.48550/arXiv.2108.07258 (2021).

  6. Zhou, Y. et al. Nature 622, 156–163 (2023).

    Article  PubMed  Google Scholar 

  7. Christensen, M., Vukadinovic, M., Yuan, N. & Ouyang, D. Nature Med. 30, 1481–1488 (2024).

    Article  PubMed  Google Scholar 

  8. Huang, Z., Bianchi, F., Yuksekgonul, M., Montine, T. J. & Zou, J. Nature Med. 29, 2307–2316 (2023).

    Article  PubMed  Google Scholar 

  9. Yu, A. C., Mohajer, B. & Eng, J. Radiol. Artif. Intell. 4, e210064 (2022).

    Article  PubMed  Google Scholar 

  10. Fang, X., Ye, M. & Du, B. IEEE Trans. Pattern Anal. Mach. Intell. 47, 2693–2705 (2025).

    Article  PubMed  Google Scholar 

Download references

Competing Interests

The author declares no competing interests.

Subjects

Latest on:

Nature Careers

Jobs

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