What question did this study set out to answer?

The aim is to assess the reliability and readability of large language model-generated information on congenital hypothyroidism.

April 23, 2026Journal of Clinical Research in Pediatric Endocrinology0 citationsOpen Access

A Comparative Assessment of Large Language Models in Congenital Hypothyroidism: Reliability, Quality and Readability

EÇEbru Barsal ÇetinerAkdeniz University Hospital BSBerna SinginAntalya Eğitim ve Araştırma Hastanesi

Key Points

The aim is to assess the reliability and readability of large language model-generated information on congenital hypothyroidism.
Compared outputs of various LLM-based chatbots for quality and readability of information.
Evaluated performance metrics of ChatGPT-5.2 against other models.
Assessed the suitability of LLM outputs for patient education.
Most LLMs provided moderate-to-high quality information on congenital hypothyroidism.
Readability of the information was found to be suboptimal for effective patient education.
ChatGPT-5.2 demonstrated the best performance among the evaluated models.

Abstract

LLM-based chatbots generated generally moderate-to-high quality CH information, but readability remains suboptimal for patient education. ChatGPT-5.2 showed the best overall performance. LLM outputs may support patient information needs but should complement, not replace, clinician-provided counseling.

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper