Show simple item record

dc.contributor.authorTeebagy, Sean
dc.contributor.authorColwell, Lauren
dc.contributor.authorWood, Emma
dc.contributor.authorYaghy, Antonio
dc.contributor.authorFaustina, Misha
dc.date.accessioned2023-04-06T13:02:44Z
dc.date.available2023-04-06T13:02:44Z
dc.date.issued2023-04-03
dc.identifier.citationImproved Performance of ChatGPT-4 on the OKAP Exam: A Comparative Study with ChatGPT-3.5. Sean Teebagy, Lauren Colwell, Emma Wood, Antonio Yaghy, Misha Faustina. medRxiv 2023.04.03.23287957; doi: https://doi.org/10.1101/2023.04.03.23287957en_US
dc.identifier.doi10.1101/2023.04.03.23287957en_US
dc.identifier.urihttp://hdl.handle.net/20.500.14038/51914
dc.descriptionThis article is a preprint. Preprints are preliminary reports of work that have not been certified by peer review.en_US
dc.description.abstractThis study aims to evaluate the performance of ChatGPT-4, an advanced Artificial Intelligence (AI) language model, on the Ophthalmology Knowledge Assessment Program (OKAP) examination compared to its predecessor, ChatGPT-3.5. Both models were tested on 180 OKAP practice questions covering various ophthalmology subject categories. Results showed that ChatGPT-4 significantly outperformed ChatGPT-3.5 (81% vs. 57%; p<0.001), indicating improvements in medical knowledge assessment. The superior performance of ChatGPT-4 suggests potential applicability in ophthalmologic education and clinical decision support systems. Future research should focus on refining AI models, ensuring a balanced representation of fundamental and specialized knowledge, and determining the optimal method of integrating AI into medical education and practice.en_US
dc.description.sponsorshipThis study did not receive any funding.en_US
dc.language.isoen_USen_US
dc.publisherCold Spring Harbor Laboratoryen_US
dc.relation.ispartofmedRxiven_US
dc.relation.urlhttps://doi.org/10.1101/2023.04.03.23287957en_US
dc.rightsThe copyright holder for this preprint is the author/funder, who has granted medRxiv a license to display the preprint in perpetuity. It is made available under a CC-BY-ND 4.0 International license.en_US
dc.rightsAttribution-NoDerivatives 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nd/4.0/*
dc.subjectChatGPTen_US
dc.subjectartificial intelligenceen_US
dc.subjectOphthalmology Knowledge Assessment Program (OKAP) examinationen_US
dc.subjectmedical knowledge assessmenten_US
dc.subjectmedical educationen_US
dc.titleImproved Performance of ChatGPT-4 on the OKAP Exam: A Comparative Study with ChatGPT-3.5 [preprint]en_US
dc.typePreprinten_US
dc.source.journaltitlemedRxiv
refterms.dateFOA2023-04-06T13:02:45Z
dc.contributor.departmentOphthalmology and Visual Sciencesen_US
dc.contributor.departmentT.H. Chan School of Medicineen_US


Files in this item

Thumbnail
Name:
2023.04.03.23287957v1.full.pdf
Size:
179.6Kb
Format:
PDF
Description:
Preprint

This item appears in the following Collection(s)

Show simple item record

The copyright holder for this preprint is the author/funder, who has granted medRxiv a license to display the preprint in perpetuity. It is made available under a CC-BY-ND 4.0 International license.
Except where otherwise noted, this item's license is described as The copyright holder for this preprint is the author/funder, who has granted medRxiv a license to display the preprint in perpetuity. It is made available under a CC-BY-ND 4.0 International license.