AI model predicts five-year breast cancer risk

A new AI model can predict a person’s risk of developing breast cancer up to five years in advance by analysing mammograms.

The technology could make screening more effective by identifying women who need additional imaging.

In one study, women the algorithm flagged as high risk were four times more likely to develop breast cancer than those with a low AI score.

The Clairity Consortium, an international association of 46 research institutions in North and South America and Germany, developed the model, Clairity Breast, trained on more than 420,000 mammograms.

Christiane Kuhl, director of the department of diagnostic and interventional radiology at RWTH Aachen University Hospital, said: “With this newly-developed AI model, we can predict with much greater precision that a woman will develop breast cancer in the next five years, on the basis of mammograms that are normal and show no signs of breast cancer.”

Unlike traditional risk models, the AI does not need family history, genetics or lifestyle data. It calculates risk from mammograms alone and classifies women into risk categories.

The model assesses not only the amount of glandular tissue but also its texture and arrangement, another breast cancer risk factor.

Kuhl said current “one-size-fits-all” screening is outdated.

“The AI model can decide within seconds whether a woman needs an MRI for early detection or not,” she said.

MRI uses magnetic fields and radio waves to create detailed images but is more expensive than mammography.

Kuhl advocated a two-step approach: “First, mammography for early detection; then an AI analysis to determine the risk of disease over the next five years.”