articleOphthalmology ScienceMay 4, 2023GOLD OA

Evaluating the Performance of ChatGPT in Ophthalmology

Hôpital Maisonneuve-Rosemont · Centre Hospitalier de l’Université de Montréal · +3 more institutions

PubMed
Indexed incrossrefdoajpubmed

Abstract

PurposeFoundation models are a novel type of artificial intelligence algorithms, in which models are pretrained at scale on unannotated data and fine-tuned for a myriad of downstream tasks, such as generating text. This study assessed the accuracy of ChatGPT, a large language model (LLM), in the ophthalmology question-answering space.DesignEvaluation of diagnostic test or technology.ParticipantsChatGPT is a publicly available LLM.MethodsWe tested 2 versions of ChatGPT (January 9 “legacy” and ChatGPT Plus) on 2 popular multiple choice question banks commonly used to prepare for the high-stakes Ophthalmic Knowledge Assessment Program (OKAP) examination. We generated two 260-question simulated exams from the…

Citation impact

487
total citations
FWCI
17.66
Percentile
100%
References
29
Citations per year

Authors

5

Topics & keywords

Keywords
  • Logistic regression
  • Test (biology)
  • Set (abstract data type)
  • Computer science
  • Post hoc
  • Artificial intelligence
  • Index (typography)
  • Regression
UN Sustainable Development Goals
  • Quality Education
No related works found for this paper.

Funding