Artificial intelligence has shown the ability to identify women at higher risk of developing breast cancer several years before an official diagnosis, according to an AFP report, citing a research from the Norwegian Institute of Public Health (FHI).
The study, conducted by researchers from FHI, the University of California, and the University of Washington, analyzed mammograms from 116,495 women who participated in a Norwegian breast cancer screening program between 2004 and 2018. Of those, 1,607 women later developed breast cancer.
Using a commercially available AI program, researchers found that the algorithm could accurately predict which women were at greater risk and even pinpoint the specific breast likely to be affected—up to four to six years before diagnosis.
“The breast that developed cancer had an AI score about twice as high as the other breast,” said Solveig Hofvind, head of the screening program and AI project. She noted that the findings suggest AI could play a role in creating more personalized screening programs.
FHI highlighted AI’s potential to improve early detection, reduce healthcare costs, and better focus on at-risk populations. The study, published in the Journal of the American Medical Association Network, adds to growing research on AI’s role in medical diagnostics.
A new project, launched last year by the Norwegian screening program, is now examining whether AI can match or even surpass radiologists in diagnosing breast cancer.
Breast cancer remains the most common cancer among women worldwide, with 670,000 deaths recorded in 2022, according to the World Health Organization.
