TRV-2026-1730Certified recordPeer-reviewed

Reliability, quality, and readability of large language models in carpal tunnel syndrome: A comparative cross-linguistic, cross-sectional observational study

BackgroundAI-based chatbots are increasingly used for health information, while cross-linguistic studies suggest that response performance may vary by language. Given the high prevalence of carpal tunnel syndrome (CTS), this study evaluated the reliability, quality, patient education suitability, and readability of AI-generated responses to CTS questions in English and Turkish.Materials and methodsSeventeen patient-centered CTS questions were directed to ChatGPT ® (GPT-5 Mini), Gemini ® 3 Flash, and Claude ® 4.5…

Health · Problem Space — documented harm · certified 2026-10-17 · v1 · article view · machine-readable

Current reading — problem

None of the three tested chatbots produced carpal tunnel syndrome answers at recommended readability levels in English or Turkish, and quality varied by model and language.

What this doesn’t fix

The mDISCERN instrument partly reflects whether references are provided and does not directly assess factual clinical accuracy, so score differences between models should be interpreted cautiously.

Evidence

Reader signal

How should this claim be treated?

Cite this record

Truvace Impact Record TRV-2026-1730, v1: “Reliability, quality, and readability of large language models in carpal tunnel syndrome: A comparative cross-linguistic, cross-sectional observational study.” Truvace, 2026-10-17. /record/TRV-2026-1730 (accessed at citation time). sha256 1ffb5329939cf5f9…

Calibration history

Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.

  1. Certifiedv11ffb5329939c…

    Certified into the record

Verify this record
How to verify without trusting this page

Fetch the canonical text of any version from /api/record/TRV-2026-1730 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.