Breakthrough in breast cancer with new AI that can predict whether the disease will spread – and experts say it could save thousands of lives
- The technology measures the immune response of lymph nodes
- Researchers from King’s College London tested 5,000 patients donated by 345 patients
Scientists have developed artificial intelligence that can predict whether a patient’s breast cancer will spread.
The technology measures the immune response of lymph nodes, pea-sized blobs of tissue that help the body fight infection.
Tests on the lymph nodes of people with triple-negative breast cancer — an aggressive disease most likely to spread or return — found it could predict whether metastasis was likely.
Experts said the breakthrough could lead to a tailored treatment based on a woman’s individual risk profile that could stop the disease before it becomes incurable.
Researchers at King’s College London developed an AI model that they tested on more than 5,000 lymph nodes donated by 345 patients.
Scientists have developed artificial intelligence that can predict whether a patient’s breast cancer will spread (stock image)
Breast cancer cells typically first spread to the lymph nodes in the armpit or armpit closest to the tumor.
When this happens, patients are usually given more intensive treatment to prevent spread elsewhere.
But scientists found that even when the breast cancer cells hadn’t spread to the lymph nodes, their immune responses made it possible to predict the likelihood of the cancer spreading elsewhere.
Using a computer program, they performed an image analysis of the lymph nodes of cancer patients, which they then compared to the patient’s chart and checked whether their breast cancer had spread.
dr Anita Grigoriadis, who led the research at the Breast Cancer Now Unit at King’s College London, said: “With our AI, we looked at a lot of lymph node images and focused on specific patterns.”
“What we have seen is that when we look at many of the lymph nodes of many patients, we have found that when we find these features, they seem to be a sign that the patient is somehow capable of inferring the development of cancer in other organs longer.” than in these patients, where we did not find these features in the lymph nodes.”
She added, “By demonstrating that lymph node changes can predict whether triple-negative breast cancer is spreading, we have built on our growing knowledge of the important role that the immune response can play in understanding a patient’s prognosis.”
About 15 percent of breast cancers are triple negative, and few targeted treatments currently exist.
It is more common in women who have inherited an altered BRCA gene made famous by Angelina Jolie, as well as in black women, premenopausal women and women under 40 years of age.
They publish their findings in the Journal of Pathology and hope to test the AI model in clinical trials.
dr Simon Vincent, Director of Research, Support and Influence at Breast Cancer Now said: “Each year around 8,000 women in the UK are diagnosed with triple-negative breast cancer, a more aggressive form of breast cancer that often produces worse outcomes.”
“If, thanks to this research, it is possible to offer women more personalized treatment and care based on the likelihood of breast cancer spreading, it could help save lives and reduce stress and worry.” to understand how this might work in practice for the benefit of women affected by this type of breast cancer.”