Assessing the Competence of Artificial Intelligence Programs in Pediatric Ophthalmology and Strabismus and Comparing their Relative Advantages.

Romanian journal of ophthalmology Pub Date : 2023-10-01 DOI:10.22336/rjo.2023.61

Eyupcan Sensoy, Mehmet Citirik

{"title":"Assessing the Competence of Artificial Intelligence Programs in Pediatric Ophthalmology and Strabismus and Comparing their Relative Advantages.","authors":"Eyupcan Sensoy, Mehmet Citirik","doi":"10.22336/rjo.2023.61","DOIUrl":null,"url":null,"abstract":"Objective: The aim of the study was to determine the knowledge levels of ChatGPT, Bing, and Bard artificial intelligence programs produced by three different manufacturers regarding pediatric ophthalmology and strabismus and to compare their strengths and weaknesses. Methods: Forty-four questions testing the knowledge levels of pediatric ophthalmology and strabismus were asked in ChatGPT, Bing, and Bard artificial intelligence programs. Questions were grouped as correct or incorrect. The accuracy rates were statistically compared. Results: ChatGPT chatbot gave 59.1% correct answers, Bing chatbot gave 70.5% correct answers, and Bard chatbot gave 72.7% correct answers to the questions asked. No significant difference was observed between the rates of correct answers to the questions in all 3 artificial intelligence programs (p=0.343, Pearson's chi-square test). Conclusion: Although information about pediatric ophthalmology and strabismus can be accessed using current artificial intelligence programs, the answers given may not always be accurate. Care should always be taken when evaluating this information.","PeriodicalId":94355,"journal":{"name":"Romanian journal of ophthalmology","volume":"67 4","pages":"389-393"},"PeriodicalIF":0.0000,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10793362/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Romanian journal of ophthalmology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.22336/rjo.2023.61","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

Objective: The aim of the study was to determine the knowledge levels of ChatGPT, Bing, and Bard artificial intelligence programs produced by three different manufacturers regarding pediatric ophthalmology and strabismus and to compare their strengths and weaknesses. Methods: Forty-four questions testing the knowledge levels of pediatric ophthalmology and strabismus were asked in ChatGPT, Bing, and Bard artificial intelligence programs. Questions were grouped as correct or incorrect. The accuracy rates were statistically compared. Results: ChatGPT chatbot gave 59.1% correct answers, Bing chatbot gave 70.5% correct answers, and Bard chatbot gave 72.7% correct answers to the questions asked. No significant difference was observed between the rates of correct answers to the questions in all 3 artificial intelligence programs (p=0.343, Pearson's chi-square test). Conclusion: Although information about pediatric ophthalmology and strabismus can be accessed using current artificial intelligence programs, the answers given may not always be accurate. Care should always be taken when evaluating this information.

查看原文本刊更多论文

评估人工智能程序在小儿眼科和斜视方面的能力并比较其相对优势。

研究目的本研究旨在确定 ChatGPT、Bing 和 Bard 三家不同制造商生产的人工智能程序对小儿眼科和斜视的了解程度，并比较它们的优缺点。研究方法在 ChatGPT、Bing 和 Bard 人工智能程序中提出了 44 道测试小儿眼科和斜视知识水平的问题。问题分为正确和错误两组。对正确率进行统计比较。结果如下ChatGPT 聊天机器人回答问题的正确率为 59.1%，Bing 聊天机器人回答问题的正确率为 70.5%，Bard 聊天机器人回答问题的正确率为 72.7%。所有 3 个人工智能程序的问题正确率之间没有明显差异（P=0.343，皮尔逊卡方检验）。结论：虽然可以通过当前的人工智能程序获取有关小儿眼科和斜视的信息，但给出的答案不一定总是准确的。在评估这些信息时应始终小心谨慎。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Romanian journal of ophthalmology

自引率

0.00%

发文量