Crossmark

Comparative evaluation of four large language models (ChatGPT-5, Gemini 2.5 Pro, Claude Sonnet-4, and DeepSeek-R1) for diagnostic and therapeutic decision-making in real-world otolaryngology scenarios

Crossref DOI link: https://doi.org/10.1007/s00405-026-10222-y

Published Online: 2026-04-23

Update policy: https://doi.org/10.1007/springer_crossmark_policy

Authors

Subay, Enes Ahmet https://orcid.org/0009-0007-2758-9950
Pamuk, Erim

Gökçınar, Yasin

Kaplan, Büşra

Kuşçu, Oğuz
Funding

Funding for this research was provided by:

Hacettepe University
License Information

Text and Data Mining valid from 2026-04-23

Version of Record valid from 2026-04-23
More Information

Article History

Received: 11 November 2025

Accepted: 28 March 2026

First Online: 23 April 2026

Declarations

:

: The study protocol (Project ID: SBA 25/609) was reviewed by the Hacettepe University Non-Interventional Clinical Research Ethics Committee (Ankara, Türkiye) and deemed exempt from additional review, as all patient data were fully anonymized.

: The authors declare that they have no conflict of interest.

Document is current

Any future updates will be listed below