Researchers at the University of Virginia (UVA) Health System are developing a personalized risk model to recommend how often a woman should have a mammogram based on her particular risk factors, according to UVA.
Dr. Jennifer Harvey and Dr. William Knaus are part of a research team that received a $5.5 million grant from the U.S. Department of Defense Congressionally Directed Medical Research Programs to fund the initial phase of a study to develop the risk model, UVA said. The two will spend three years developing and validating the screening model at UVA before testing it through a national study.
The risk model will combine medical data with guidance from women gathered via phone surveys and focus groups on how they would like to approach screenings for breast cancer. It will include breast density, which is one of the strongest indicators of a woman's breast cancer risk, according to UVA.










![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)






