aceLarge language model-based simplification of breast imaging reports: a prospective multicentre study with 2965 patient-based evaluations
Objective To compare patient perceptions of radiologist-written and artificial intelligence (AI)-generated simplifications of breast imaging reports in terms of simplicity, comprehensibility, empathy, and overall preference. Materials and methods In this prospective multicentre survey-based study, 10 anonymized breast imaging reports (5 ultrasound, 5 mammography; one BI-RADS category 1-5 per modality) were simplified by ChatGPT-4 within a 50-word limit. After assessment by a panel of 20 physicians, paired radiol…
In a multicentre survey of 314 patients, ChatGPT-4 simplified breast imaging reports were preferred in 63.3% of 2,965 evaluations and rated simple by 70.0% versus 43.4% for radiologist-written reports.
The study used only 10 anonymized breast imaging reports, each AI summary was limited to 50 words, and it measured patient perceptions rather than understanding or clinical outcomes.
Sources
- Peer-reviewedInsights into Imaging2026-11-02
What do you make of this one?
Truvace Impact Record TRV-2026-2396, v1: “Large language model-based simplification of breast imaging reports: a prospective multicentre study with 2965 patient-based evaluations.” Truvace, 2026-11-06. /record/TRV-2026-2396 (accessed on the day you copy it). sha256 61ff7cbef22bb184…
Change history
Every change made to this record since it was first published, and why. Nothing has changed since it went up.
Certified into the record
How to check it yourself, without trusting this page
Download any version from /api/record/TRV-2026-2396 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.