{"title":"Performance of ChatGPT and Bard in self-assessment questions for nephrology board renewal.","authors":"Ryunosuke Noda, Yuto Izaki, Fumiya Kitano, Jun Komatsu, Daisuke Ichikawa, Yugo Shibagaki","doi":"10.1007/s10157-023-02451-w","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Large language models (LLMs) have impacted advances in artificial intelligence. While LLMs have demonstrated high performance in general medical examinations, their performance in specialized areas such as nephrology is unclear. This study aimed to evaluate ChatGPT and Bard in their potential nephrology applications.</p><p><strong>Methods: </strong>Ninety-nine questions from the Self-Assessment Questions for Nephrology Board Renewal from 2018 to 2022 were presented to two versions of ChatGPT (GPT-3.5 and GPT-4) and Bard. We calculated the correct answer rates for the five years, each year, and question categories and checked whether they exceeded the pass criterion. The correct answer rates were compared with those of the nephrology residents.</p><p><strong>Results: </strong>The overall correct answer rates for GPT-3.5, GPT-4, and Bard were 31.3% (31/99), 54.5% (54/99), and 32.3% (32/99), respectively, thus GPT-4 significantly outperformed GPT-3.5 (p < 0.01) and Bard (p < 0.01). GPT-4 passed in three years, barely meeting the minimum threshold in two. GPT-4 demonstrated significantly higher performance in problem-solving, clinical, and non-image questions than GPT-3.5 and Bard. GPT-4's performance was between third- and fourth-year nephrology residents.</p><p><strong>Conclusions: </strong>GPT-4 outperformed GPT-3.5 and Bard and met the Nephrology Board renewal standards in specific years, albeit marginally. These results highlight LLMs' potential and limitations in nephrology. As LLMs advance, nephrologists should understand their performance for future applications.</p>","PeriodicalId":10349,"journal":{"name":"Clinical and Experimental Nephrology","volume":null,"pages":null},"PeriodicalIF":2.2000,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical and Experimental Nephrology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s10157-023-02451-w","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/2/14 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"UROLOGY & NEPHROLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Background: Large language models (LLMs) have impacted advances in artificial intelligence. While LLMs have demonstrated high performance in general medical examinations, their performance in specialized areas such as nephrology is unclear. This study aimed to evaluate ChatGPT and Bard in their potential nephrology applications.
Methods: Ninety-nine questions from the Self-Assessment Questions for Nephrology Board Renewal from 2018 to 2022 were presented to two versions of ChatGPT (GPT-3.5 and GPT-4) and Bard. We calculated the correct answer rates for the five years, each year, and question categories and checked whether they exceeded the pass criterion. The correct answer rates were compared with those of the nephrology residents.
Results: The overall correct answer rates for GPT-3.5, GPT-4, and Bard were 31.3% (31/99), 54.5% (54/99), and 32.3% (32/99), respectively, thus GPT-4 significantly outperformed GPT-3.5 (p < 0.01) and Bard (p < 0.01). GPT-4 passed in three years, barely meeting the minimum threshold in two. GPT-4 demonstrated significantly higher performance in problem-solving, clinical, and non-image questions than GPT-3.5 and Bard. GPT-4's performance was between third- and fourth-year nephrology residents.
Conclusions: GPT-4 outperformed GPT-3.5 and Bard and met the Nephrology Board renewal standards in specific years, albeit marginally. These results highlight LLMs' potential and limitations in nephrology. As LLMs advance, nephrologists should understand their performance for future applications.
期刊介绍:
Clinical and Experimental Nephrology is a peer-reviewed monthly journal, officially published by the Japanese Society of Nephrology (JSN) to provide an international forum for the discussion of research and issues relating to the study of nephrology. Out of respect for the founders of the JSN, the title of this journal uses the term “nephrology,” a word created and brought into use with the establishment of the JSN (Japanese Journal of Nephrology, Vol. 2, No. 1, 1960). The journal publishes articles on all aspects of nephrology, including basic, experimental, and clinical research, so as to share the latest research findings and ideas not only with members of the JSN, but with all researchers who wish to contribute to a better understanding of recent advances in nephrology. The journal is unique in that it introduces to an international readership original reports from Japan and also the clinical standards discussed and agreed by JSN.