Emerging evidence
Published recordHealthGood Space
More
Prompt-dependent readability and accuracy of Generative Pre-trained Transformer-5 thinking responses to breast imaging questions derived from European Society of Breast Imaging patient recommendations
- Truvace record
- TRV-2026-2868raw data (JSON)
- Version
- v1Published
- First published
- Evidence type
- Benchmark or lab evaluation
- Sources
- 1 sourcePeer-reviewed
- sha256
- 96bfafb9c4bf…check it
Purpose: Although professional societies provide standardized resources, the reliability of online health content remains inconsistent, particularly as large language models (LLMs) become a growing source of patient information. Therefore, the primary objective of this study was to determine whether patient-focused prompt optimization improves the readability of Generative Pre-trained Transformer-5 (GPT-5) Thinking responses compared with standard prompting while evaluating potential changes in expert-rated fact…
The gain
In a study of 48 European Society of Breast Imaging questions, a patient-focused prompt made GPT-5 Thinking answers significantly easier to read on all four readability indices (P < 0.001), while radiologist-rated accuracy stayed at 4.52 versus 4.54 out of 5.
What this doesn’t fix
The resulting reading grade level remained above widely recommended patient-education thresholds, and the study did not test whether the easier text improves patient comprehension.
Sources
1 on file- Diagnostic and Interventional Radiologydoi:10.4274/dir.2026.264309
Cite this record
v1Truvace Impact Record TRV-2026-2868, v1: “Prompt-dependent readability and accuracy of Generative Pre-trained Transformer-5 thinking responses to breast imaging questions derived from European Society of Breast Imaging patient recommendations.” Truvace, 2026-11-12. /record/TRV-2026-2868 (accessed on the day you copy it). sha256 96bfafb9c4bf5ce8…
Change history
1 versionEvery change made to this record since it was first published, and why. Nothing has changed since it went up.
Certified into the record
Check this record hasn’t been altered
How to check it yourself, without trusting this page
Download any version from /api/record/TRV-2026-2868 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.
ace