Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Journal of Glaucoma

Comparing Performance of Large Language Model-Based Tools on Patient-Driven Glaucoma Inquiries

View Full Paper
Ask AI
Bookmark
Share

Authors

DGDhruva GuptaSWSarah WagnerAEAlexandra G. Castillejos Ellenthal

Discussion

Loading...

Member takes

Overview

Cross-sectional study evaluates large language models' accuracy and quality in glaucoma inquiries, suggesting key differences.

Key Points

  • GPT-4o scored higher in accuracy, comprehensiveness, and quality compared to Gemini Pro.
  • GPT-4o Mini also demonstrated higher comprehensiveness and quality than Gemini Pro.
  • No differences were found in readability across the models used for glaucoma inquiries.
  • LLMs produced responses with mostly similar semantics, ensuring consistent information delivery.

Cite This Study

Gupta et al. (2025) studied this question.

synapsesocial.com/papers/68c23d81b210217d6478dfc8https://doi.org/10.1097/ijg.0000000000002627
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Evaluating the competence of large language models in ophthalmology clinical practice: a multi-scenario quantitative study2025 · 1 citations
  2. 2Using large language models to generate child-friendly education materials on myopia2025
  3. 3A Comparative Analysis of Three Large Language Models in Answering Patient Queries on Otolaryngology Emergencies2025
  4. 4Transforming cataract care through artificial intelligence: an evaluation of large language models’ performance in addressing cataract-related queries2025 · 1 citations
  5. 5Performance of several large language models when answering common patient questions about type 1 diabetes in children: accuracy, comprehensibility and practicality2025 · 7 citations