Journal of dental sciences · 2023
Evaluating GPT-4V's performance in the Japanese national dental examination: A challenge explored.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Morishita Masaki, Fukuda Hikaru, Muraoka Kosuke, Nakamura Taiji, Hayashi Masanari, Yoshioka Izumi, Ono Kentaro, Awano Shuji
Аннотация
BACKGROUND/PURPOSE: Rapid advancements in AI technology have led to significant interest in its application across various fields, including medicine and dentistry. This study aimed to assess the capabilities of ChatGPT-4V with image recognition in answering image-based questions from the Japanese National Dental Examination (JNDE) to explore its potential as an educational support tool for dental students.
MATERIALS AND METHODS: The dataset used questions from the JNDE, which was conducted in January 2023, with a focus on image-related queries. ChatGPT-4V was utilized, and standardized prompts, question texts, and images were input. Data and statistical analyses were conducted using Qlik Sense® and GraphPad Prism.
RESULTS: The overall correct response rate of ChatGPT-4V for image-based JNDE questions was 35.0 %. The correct response rates were 57.1 % for compulsory questions, 43.6 % for general questions, and 28.6 % for clinical practical questions. In specialties like Dental Anesthesiology and Endodontics, ChatGPT-4V achieved correct response rates above 70 %, while response rates for Orthodontics and Oral Surgery were lower. A higher number of images in questions was correlated with lower accuracy, suggesting an impact of the number of images on correct and incorrect responses.
CONCLUSION: While innovative, ChatGPT-4V's image recognition feature exhibited limitations, especially in handling image-intensive and complex clinical practical questions, and is not yet fully suitable as an educational support tool for dental students at its current stage. Further technological refinement and re-evaluation with a broader dataset are recommended.
MATERIALS AND METHODS: The dataset used questions from the JNDE, which was conducted in January 2023, with a focus on image-related queries. ChatGPT-4V was utilized, and standardized prompts, question texts, and images were input. Data and statistical analyses were conducted using Qlik Sense® and GraphPad Prism.
RESULTS: The overall correct response rate of ChatGPT-4V for image-based JNDE questions was 35.0 %. The correct response rates were 57.1 % for compulsory questions, 43.6 % for general questions, and 28.6 % for clinical practical questions. In specialties like Dental Anesthesiology and Endodontics, ChatGPT-4V achieved correct response rates above 70 %, while response rates for Orthodontics and Oral Surgery were lower. A higher number of images in questions was correlated with lower accuracy, suggesting an impact of the number of images on correct and incorrect responses.
CONCLUSION: While innovative, ChatGPT-4V's image recognition feature exhibited limitations, especially in handling image-intensive and complex clinical practical questions, and is not yet fully suitable as an educational support tool for dental students at its current stage. Further technological refinement and re-evaluation with a broader dataset are recommended.