Wednesday, November 29 | 3:20 p.m.-3:30 p.m. | SSM01-03 | Room E451A
The use of mammography screening services varies widely at the county level, based on factors such as income, race, and primary care access, as well as whether a county is more or less metropolitan, according to research being presented in this Wednesday session.A group led by Dr. Samantha Heller, PhD, of NYU Langone Medical Center investigated county-level geographic patterns of mammographic screening uptake throughout the U.S. to assess the effect of breast cancer preventive services in rural versus urban locations.
The study used information from the County Health Rankings dataset to identify the percentage of Medicare enrollees between the ages of 67 and 69 per U.S. county who had at least one mammogram in 2013. Heller and colleagues identified the counties as metropolitan versus nonmetropolitan based on a scale of 1 to 9 from the U.S. Department of Agriculture's rural atlas.
The mean mammographic uptake per county was 60%, with a range of 26% to 86%, the researchers found. Use of screening mammography was significantly higher in metropolitan counties than their more rural counterparts in 19 states, significantly lower in four states, and not significantly different in the remaining states.
In addition, Heller's team found that county-level mammographic uptake was positively correlated with the number of Medicare enrollees, the percentage of white residents, higher income levels, and the percentage of residents with some college education. It was negatively correlated with the ratio of population to primary care providers, age-adjusted mortality, and the percentage of Hispanic residents.
"In conjunction with predictive factors such as income, race, and primary care access, county-level geographic categorizations may help identify communities needing breast cancer screening education," the researchers concluded.












![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)






