Emerging evidence
Published recordHealthGood Space
More
ChatGPT versus Google Search-linked responses to surgical and fertility-related endometriosis questions: a cross-sectional content analysis
- Truvace record
- TRV-2026-3046raw data (JSON)
- Version
- v1Published
- First published
- Evidence type
- Benchmark or lab evaluation
- Sources
- 1 sourcePeer-reviewed
- sha256
- bb781f49f6a6…check it
Objective: To compare guideline concordance, safety, actionability, and readability of ChatGPT and Google Search-linked responses to patient-facing surgical and fertility-related endometriosis questions. Methods: We performed a cross-sectional comparative digital content analysis of 40 prespecified questions across diagnosis/imaging, minimally invasive surgery, deep organ-involving disease, and fertility/ovarian reserve. For each question, one ChatGPT response and one Google Search-linked response archived on Ma…
The gain
In a content analysis of 40 endometriosis surgery and fertility questions, two blinded physicians gave ChatGPT a higher overall clinical quality score than Google Search-linked answers (4.91 vs 4.53), with no response judged harmful or misleading.
What this doesn’t fix
The analysis used a controlled set of 40 prespecified questions with one response per platform per question archived on a single date, and the authors call for further assessment of patient comprehension.
Sources
1 on file- Journal of Gynecology Obstetrics and Human Reproductiondoi:10.1016/j.jogoh.2026.103330
Cite this record
v1Truvace Impact Record TRV-2026-3046, v1: “ChatGPT versus Google Search-linked responses to surgical and fertility-related endometriosis questions: a cross-sectional content analysis.” Truvace, 2026-11-19. /record/TRV-2026-3046 (accessed on the day you copy it). sha256 bb781f49f6a6ad02…
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-2026-3046 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