Performance of large language models in urological decision support: a guideline-based comparative evaluation in urolithiasis
Adem Tunçekin, Yasin Aktaş · 2026
Read Performance of large language models in urological decision support: a guideline-based comparative evaluation in urolithiasis by Adem Tunçekin, Yasin Aktaş (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13242490.txt.
Description
Adem Tunçekin and Yasin Aktaş graded four large language models on how faithfully they answer questions about kidney stone disease. Their study appeared in Urolithiasis in 2026. The authors wrote 105 clinical questions from guideline principles covering nine areas of stone management. The GPT-4 and GPT-4 Turbo systems, plus Claude and Gemini, each answered every question twice, and two experienced urologists scored the replies against guideline advice.
All four models scored high on guideline agreement, with Claude at the top and Gemini at the bottom of a narrow range. The two expert raters agreed only fairly with each other, a reminder that judging answers involves judgment. No model clearly won across the nine topics, and each model answered consistently between its two sessions. The authors see these tools as promising helpers for guideline-based education. They caution that real clinical use still needs wider validation first.
Catalog record
| CREATOR | Adem Tunçekin, Yasin Aktaş |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 18 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |