Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Sep 13;30(3):173-176.
doi: 10.4103/meajo.meajo_199_23. eCollection 2023 Jul-Sep.

Exploring Artificial Intelligence Programs' Understanding of Lens, Cataract, and Refractive Surgery Information

Eyupcan Sensoy  1 , Mehmet Citirik  1
Affiliations

Exploring Artificial Intelligence Programs' Understanding of Lens, Cataract, and Refractive Surgery Information

Eyupcan Sensoy et al. Middle East Afr J Ophthalmol. .

Abstract

Purpose: We aimed to evaluate the success of Chat Generative Pre-trained Transformer (ChatGPT), Bing, and Bard artificial intelligence programs, which were released free of charge by three different manufacturers, in correctly answering questions about lenses, cataract, and refractive surgery, and to investigate whether they are superior to each other.

Methods: Seventy questions related to lens, cataract, and refractive surgery were obtained from the study questions section of the American Academy of Ophthalmology 2022 to 2023 Basic and Clinical Science Course Lens and Cataract and Refractive Surgery Books. The questions were asked separately for the ChatGPT, Bing, and Bard artificial intelligence programs. The answers were compared with answer keys and grouped as correct or incorrect. The accuracy rates of artificial intelligence programs were compared statistically.

Results: ChatGPT, Bing, and Bard chatbots gave correct answers to 35 (50%), 43 (61.4%), and 50 (71.4%) questions asked, respectively. The rate of correct answers to the questions of the Bard artificial intelligence program was significantly higher than that of ChatGPT (P = 0.009, Pearson's Chi-square test).

Conclusion: Although the currently released artificial intelligence chatbots can be used to access accurate information about lenses, cataracts, and refractive surgery, one should always be careful about the accuracy of the answers given.

Keywords: Bard; Bing; Chat Generative Pre-trained Transformer; cataract; refractive surgery.

PubMed Disclaimer

Conflict of interest statement

There are no conflicts of interest.

References

    1. Evans RS. Electronic health records: Then, now, and in the future. Yearb Med Inform 2016;Suppl. 1:S48–61. - PMC - PubMed
    1. Rahimy E. Deep learning applications in ophthalmology. Curr Opin Ophthalmol. 2018;29:254–60. - PubMed
    1. Patel VL, Shortliffe EH, Stefanelli M, Szolovits P, Berthold MR, Bellazzi R, et al. The coming of age of artificial intelligence in medicine. Artif Intell Med. 2009;46:5–17. - PMC - PubMed
    1. Mikolov T, Deoras A, Povey D, Burget L, Černocký J. Strategies for Training Large Scale Neural Network Language Models. 2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings. 2011:196–201.
    1. Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I. Language Models are Unsupervised Multitask Learners. Available from: https://github.com/codelucas/newspaper . [Last accessed on 2023 Jun 26]