Contact our breast care nurses 0808 800 6000

Researchers develop AI model to predict risk of secondary breast cancer

Researchers have developed an artificial intelligence model that can predict if triple negative breast cancer will spread.

Researchers from our Research Unit at King’s College London have developed an AI model that can predict if someone is likely to develop secondary breast cancer.

By looking at changes in the lymph nodes of women with triple negative breast cancer, they found that the AI model can predict if the disease will spread around the body. 

The researchers hope that this model could one day assist doctors in planning treatment. 

Triple negative breast cancer

Around 15% of breast cancers are classed as triple negative. This form of breast cancer can be more aggressive, and it’s more likely to return or spread during the first years following treatment.

When breast cancer spreads from the breast to other parts of the body it's called secondary breast cancer. Although we can treat secondary breast cancer, it can’t be cured. 

Breast cancer cells can sometimes spread to the lymph nodes under the arm, which are glands that help fight infection. If this has happened, you may be offered additional treatment. This is to stop the disease spreading around the body and becoming secondary breast cancer.

Using AI 

Professor Anita Grigoriadis and her team found that AI could predict if triple negative breast cancer is likely to become secondary breast cancer even before the disease has spread to the lymph nodes. They did this by looking at the immune response in the lymph nodes.

The team tested the AI model on more than 5,000 lymph nodes that 345 patients donated to biobanks, including the Breast Cancer Now Tissue Bank. Through testing, they confirmed that the AI model could predict how likely the disease was to spread to other organs.

Anita added: “By demonstrating that lymph node changes can predict if triple negative breast cancer will spread, we’ve built on our growing knowledge of the important role that immune response can play in understanding a patient’s prognosis.”

Tailoring treatment and care

The researchers hope that eventually this AI model will be tested in clinical trials and that it could one day assist doctors in planning treatment. This could also help reassure people with breast cancer about it spreading to other parts of the body.

Anita added: “We’re planning to test the model further at centres across Europe to make it even more robust and precise. The transition from assessing tissue on glass slides under a microscope to using computers in the NHS is gathering pace.  We want to leverage this change to develop AI-powered software based on our model for pathologists to use to benefit women with this hard-to-treat breast cancer.”

And Dr Simon Vincent, director of research, support and influencing at Breast Cancer Now, added:

“If, thanks to this research, it’s possible to provide women with more tailored treatment and care based on the likelihood of their breast cancer spreading, it could help to save lives and reduce stress and worry. We look forward to further findings to understand how this could work in practice to benefit patients.”

The study was published in the Journal of Pathology and was funded by Breast Cancer Now, Cancer Research UK and the Medical Research Council.

Our research is only possible thanks to the incredible generosity of its supporters. This project’s funding was supported by the Asda Tickled Pink campaign. To learn more about our research, visit the research section.

Share this page