Artificial intelligence (AI) has shown remarkable potential in predicting women at high risk of developing breast cancer years before the disease is diagnosed, according to new findings from the Norwegian Institute of Public Health (FHI). The study, which highlights the AI’s capacity for early detection, could revolutionize how breast cancer is screened and diagnosed.
Five researchers collaborated with the University of California and the University of Washington. They gained access to a commercially available AI program. This program analyzed mammograms from 116,495 women. These women had participated in a Norwegian breast cancer detection program between 2004 and 2018. The study tracked the outcomes of 1,607 women who developed breast cancer. It provided critical insights into the predictive capabilities of AI.
The AI system was able to identify which women had an elevated risk of developing breast cancer. It even predicted which breast would be affected four to six years before diagnosis. Solveig Hofvind, the head of the detection program, noted, “The breast which developed cancer had an AI score about twice as high as the other breast.”
IMPROVING PERSONALIZED DETECTION WITH AI
The findings suggest that AI could enhance breast cancer detection programs, tailoring them to individual risk profiles. AI could provide more personalized screening strategies. This could potentially improve early diagnosis. It would lead to better outcomes for women at higher risk.
“This study shows how AI algorithms available on the market can develop personalized detection programs,” said Hofvind. Personalized screening could help target at-risk populations, reducing unnecessary testing and ensuring those who need closer monitoring receive it.
THE GLOBAL IMPACT OF EARLY DETECTION
According to the World Health Organization, breast cancer remains the leading cause of cancer-related deaths among women. In 2022 alone, 670,000 women died from the disease. Early detection plays a critical role in improving survival rates, and AI offers an opportunity to address this challenge more effectively.
ONGOING RESEARCH TO EVALUATE AI’S DIAGNOSTIC CAPABILITIES
In addition to predicting breast cancer risk, the Norwegian detection program has also launched an ambitious project involving 140,000 women. This study is testing whether AI could match or even surpass the diagnostic accuracy of radiologists. If successful, AI could transform how radiologists approach breast cancer detection, potentially lowering healthcare costs and improving diagnosis efficiency.
The study’s findings were published in the Journal of the American Medical Association Network, a leading collection of medical research journals, further emphasizing the significance of these results for the medical community.
