Accuracy of large language models in head and neck cancers: a comparative analysis of ChatGPT and Gemini in TNM staging and clinical decision support
Deniz Baklaci, Hüseyin Işık, Duygu Erdem, Gökhan F. Kılıç · 2026
Read Accuracy of large language models in head and neck cancers: a comparative analysis of ChatGPT and Gemini in TNM staging and clinical decision support by Deniz Baklaci, Hüseyin Işık, Duygu Erdem, Gökhan F. Kılıç (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-13193848.txt.
Description
Deniz Baklaci and three co-authors grade two chatbots on head and neck cancer work in a 2026 study. Doctors stage such cancers by a shared code, TNM, that sizes the tumor and its spread, then plan care as a team. Language models now sit in clinic software, so their staging skill needs proof.
Charts of 180 patients were fed to ChatGPT and Gemini through set prompts. Both staged the cancers right about three times in four, matching expert calls well. Care plans split them, with Gemini ahead in the part of the read shown here. Body site twists tested each model's grip.
Catalog record
| CREATOR | Deniz Baklaci, Hüseyin Işık, Duygu Erdem, Gökhan F. Kılıç |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 38 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |