
Black women are 1.36 times less likely to receive annual follow-up after breast-conserving surgery, and Medicare patients are 1.84 times less likely, according to research published August 5 in the Journal of the American College of Radiology.
The study results demonstrate that sociodemogaphic disparities are in play when it comes to breast cancer surgery surveillance, wrote a group led by Dr. Derek Nguyen from Johns Hopkins Medicine in Baltimore.
Nguyen and colleagues conducted a study that included 1,082 women who had undergone breast-conserving surgery between 2011 to 2016. Of these, 715 (66.1%) complied with follow-up recommendations during the first three years after surgery (i.e., three annual follow-up visits).
But the investigators found that Black women were 1.36 times less likely to receive annual follow-up after breast-conserving surgery compared to their white counterparts. They also found that Medicare patients were 1.84 times less likely to receive annual follow-up compared with privately insured patients.
"[Our study found] that racial and financial disparities may represent barriers for [breast cancer survivors] to obtain consistent annual follow-up if multiple consecutive years of diagnostic mammography are requested," the group 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=100&q=70&w=100)







![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)







