Improved Performance of ChatGPT-4 on the OKAP Exam: A Comparative Study with ChatGPT-3.5 [preprint]
Teebagy, Sean ; Colwell, Lauren ; Wood, Emma ; Yaghy, Antonio ; Faustina, Misha
Citations
Student Authors
Faculty Advisor
Academic Program
UMass Chan Affiliations
Document Type
Publication Date
Subject Area
Embargo Expiration Date
Link to Full Text
Abstract
This 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.
Source
Improved 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/10.1101/2023.04.03.23287957
Year of Medical School at Time of Visit
Sponsors
Dates of Travel
DOI
Permanent Link to this Item
PubMed ID
Other Identifiers
Notes
This article is a preprint. Preprints are preliminary reports of work that have not been certified by peer review.