Researchers from Johns Hopkins University have developed a new model for estimating breast cancer risk, according to a study published online in JAMA Oncology.
The model could help guide public health strategies for breast cancer prevention, wrote lead author Nilanjan Chatterjee, PhD, and colleagues.
To develop the new framework, Chatterjee's group used data from 17,171 cases and 19,862 controls taken from the Breast and Prostate Cancer Cohort Consortium (BPC3), as well as from 5,879 women who participated in the U.S. Centers for Disease Control and Prevention's 2010 National Health Interview Survey. The researchers included 92 genetic markers (called susceptibility single nucleotide polymorphisms, or SNPs) and a variety of epidemiologic measures such as family history and anthropometric, menstrual/reproductive, and lifestyle factors (JAMA Oncol, May 26, 2016).
Using this new risk assessment tool, Chatterjee and colleagues found that the average absolute breast cancer risk for U.S. women ranges from 4.4% to 23.5%. They also found that a 30-year-old white woman in the U.S. has an 11.3% risk, on average, of developing invasive breast cancer by the time she is 80.
"Our results illustrate the potential value of risk stratification to improve breast cancer prevention, particularly to aid decisions on risk factor modification at the individual level," the researchers wrote.











![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&fit=crop&h=112&q=70&w=112)






