Women who use an interactive online tool have a better understanding of breast cancer treatment options than those who simply view an educational website, according to a study published January 24 in the Journal of Clinical Oncology.
University of Michigan researchers developed a decision-support tool called iCanDecide that gives patients key facts about breast cancer surgery, such as how often cancer recurs and the possibility of additional surgery. The group then recruited 537 patients with newly diagnosed early-stage breast cancer and randomized them to use the tool or to view similar information on a website. Participants were surveyed again five weeks later; 496 patients completed this follow-up survey.
Lead author Sarah Hawley, PhD, and colleagues found that 61% of patients who used iCanDecide had a strong understanding of possible treatment options, compared with 42% of patients who viewed the material on the website. Patients who used the tool were also more likely to say they felt prepared to make a treatment decision, at 50%, compared with 33% of patients who only viewed the website.
"Knowledge is a key component of decision-making, and yet it's consistently low even among patients who have received treatment," Hawley said in a statement released by the university. "Instead of throwing the information on the website and hoping patients would figure it out, we gave them the bullet point fact, asked a question to see if they understood, and then allowed them to drill down and look at more detailed information."











![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)






