Wednesday, December 2 | 3:20 p.m.-3:30 p.m. | SSM01-03 | Room E451A
Patients want to hear breast biopsy results from the healthcare provider who ordered the test, even if they perceive radiologists as important to their care, a group from Beth Israel Deaconess Medical Center has found.The finding contradicts calls from radiology organizations for their members to interact directly with patients, noted Dr. Jordana Phillips and colleagues.
In this Wednesday afternoon presentation, Phillips will share results from a study that assessed who patients want to hear from after image-guided breast biopsy procedures. The study consisted of an anonymous survey offered to patients in March of this year, before and after their biopsy.
Although 100% of participating patients felt that the breast radiologist was an important part of the breast care team, only 64% knew that the radiologist was a physician; 25% believed the radiologist was actually a technologist, and 7% were unsure.
The survey found that patients have distinct preferences as to who delivers their biopsy result, with more than 50% wanting results from the provider who ordered the test, regardless of the time point in their care, according to Phillips and colleagues. In comparison, 19% to 22% wanted results from breast radiologists.
Although patients value breast radiologists, they prefer to hear biopsy results from their ordering provider. Further study could shed additional light on patients' preferences and their understanding of the breast radiologist's role, 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)









