Performance evaluation of large language models for the national nursing examination in Japan

Objectives Large language models (LLMs) are increasingly used in healthcare, with the potential for various applications. However, the performance of different LLMs on nursing license exams and their tendencies to make errors remain unclear. This study aimed to evaluate the accuracy of LLMs on basic...

Full description

Saved in:
Bibliographic Details
Main Authors: Tomoki Kuribara, Kengo Hirayama, Kenji Hirata
Format: Article
Language:English
Published: SAGE Publishing 2025-05-01
Series:Digital Health
Online Access:https://doi.org/10.1177/20552076251346571
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849717747805585408
author Tomoki Kuribara
Kengo Hirayama
Kenji Hirata
author_facet Tomoki Kuribara
Kengo Hirayama
Kenji Hirata
author_sort Tomoki Kuribara
collection DOAJ
description Objectives Large language models (LLMs) are increasingly used in healthcare, with the potential for various applications. However, the performance of different LLMs on nursing license exams and their tendencies to make errors remain unclear. This study aimed to evaluate the accuracy of LLMs on basic nursing knowledge and identify trends in incorrect answers. Methods The dataset consisted of 692 questions from the Japanese national nursing examinations over the past 3 years (2021–2023) that were structured with 240 multiple-choice questions per year and a total score of 300 points. The LLMs tested were ChatGPT-3.5, ChatGPT-4, and Microsoft Copilot. Questions were manually entered into each LLM, and their answers were collected. Accuracy rates were calculated to assess whether the LLMs could pass the exam, and deductive content analysis and Chi-squared tests were conducted to identify the tendency of incorrect answers. Results For over 3 years, the mean total score and standard deviation (SD) using ChatGPT-3.5, ChatGPT-4, and Microsoft Copilot was 180.3 ± 22.2, 251.0 ± 13.1, and 256.7 ± 14.0, respectively. ChatGPT-4 and Microsoft Copilot showed sufficient accuracy rates to pass the examinations for all the years. All LLMs made more mistakes in the health support and social security system domains ( p  < 0.01). Conclusions ChatGPT-4 and Microsoft Copilot may perform better than Chat GPT-3.5, and LLMs could incorrectly answer questions about laws and demographic data specific to a particular country.
format Article
id doaj-art-8a1b27cce39740c9a0d3ca1649a36702
institution DOAJ
issn 2055-2076
language English
publishDate 2025-05-01
publisher SAGE Publishing
record_format Article
series Digital Health
spelling doaj-art-8a1b27cce39740c9a0d3ca1649a367022025-08-20T03:12:35ZengSAGE PublishingDigital Health2055-20762025-05-011110.1177/20552076251346571Performance evaluation of large language models for the national nursing examination in JapanTomoki Kuribara0Kengo Hirayama1Kenji Hirata2 Department of Biostatistics, Graduate School of Medicine, Sapporo, Japan School of Nursing, , Sapporo, Japan Department of Diagnostic Imaging, Faculty of Medicine, , Sapporo, JapanObjectives Large language models (LLMs) are increasingly used in healthcare, with the potential for various applications. However, the performance of different LLMs on nursing license exams and their tendencies to make errors remain unclear. This study aimed to evaluate the accuracy of LLMs on basic nursing knowledge and identify trends in incorrect answers. Methods The dataset consisted of 692 questions from the Japanese national nursing examinations over the past 3 years (2021–2023) that were structured with 240 multiple-choice questions per year and a total score of 300 points. The LLMs tested were ChatGPT-3.5, ChatGPT-4, and Microsoft Copilot. Questions were manually entered into each LLM, and their answers were collected. Accuracy rates were calculated to assess whether the LLMs could pass the exam, and deductive content analysis and Chi-squared tests were conducted to identify the tendency of incorrect answers. Results For over 3 years, the mean total score and standard deviation (SD) using ChatGPT-3.5, ChatGPT-4, and Microsoft Copilot was 180.3 ± 22.2, 251.0 ± 13.1, and 256.7 ± 14.0, respectively. ChatGPT-4 and Microsoft Copilot showed sufficient accuracy rates to pass the examinations for all the years. All LLMs made more mistakes in the health support and social security system domains ( p  < 0.01). Conclusions ChatGPT-4 and Microsoft Copilot may perform better than Chat GPT-3.5, and LLMs could incorrectly answer questions about laws and demographic data specific to a particular country.https://doi.org/10.1177/20552076251346571
spellingShingle Tomoki Kuribara
Kengo Hirayama
Kenji Hirata
Performance evaluation of large language models for the national nursing examination in Japan
Digital Health
title Performance evaluation of large language models for the national nursing examination in Japan
title_full Performance evaluation of large language models for the national nursing examination in Japan
title_fullStr Performance evaluation of large language models for the national nursing examination in Japan
title_full_unstemmed Performance evaluation of large language models for the national nursing examination in Japan
title_short Performance evaluation of large language models for the national nursing examination in Japan
title_sort performance evaluation of large language models for the national nursing examination in japan
url https://doi.org/10.1177/20552076251346571
work_keys_str_mv AT tomokikuribara performanceevaluationoflargelanguagemodelsforthenationalnursingexaminationinjapan
AT kengohirayama performanceevaluationoflargelanguagemodelsforthenationalnursingexaminationinjapan
AT kenjihirata performanceevaluationoflargelanguagemodelsforthenationalnursingexaminationinjapan