Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 11, 2025BMC PediatricsOpen Access

Performance of several large language models when answering common patient questions about type 1 diabetes in children: accuracy, comprehensibility and practicality

View Full Paper
Ask AI
Bookmark
Share

Authors

YÖYasemin Denkboy ÖngenAAAyla İrem AydınMAMeryem Atak

Discussion

Loading...

Member takes

Overview

Cross-sectional comparative analysis reveals large language models can provide reliable answers in pediatric diabetes, suggesting their potential role in healthcare.

Key Points

  • Large language models showed similar performance when answering common questions about type 1 diabetes in children.
  • ChatGPT-4o achieved the highest mean score of 3.78 ± 1.09, while Gemini scored the lowest at 3.40 ± 1.24.
  • The evaluation used a standard prompt and was assessed by pediatric endocrinologists using the General Quality Scale.
  • Despite no significant differences, the study highlights the promise of advanced models in providing patient-friendly answers.

Cite This Study

Öngen et al. (2025) studied this question.

synapsesocial.com/papers/68ea72339f1bd4df558cede9https://doi.org/10.1186/s12887-025-05945-6
View Full Paper
Ask AI
Bookmark
Share