Fukuda Hikaru, Morishita Masaki, Muraoka Kosuke, Yamaguchi Shino, Nakamura Taiji, Habu Manabu, Yoshioka Izumi, Awano Shuji, Ono Kentaro
Department of Science of Physical Functions, Division of Maxillofacial Surgery, Kyushu Dental University, Fukuoka, Japan.
Department of Oral Function, Division of Clinical Education Development and Research, Kyushu Dental University, Kitakyushu, Fukuoka, Japan.
Int Dent J. 2025 Jun 9;75(4):100847. doi: 10.1016/j.identj.2025.100847.
With advancements in artificial intelligence (AI), its role in education and examinations is expanding. This study aimed to evaluate the accuracy and response capability of ChatGPT-4o in solving questions from the Japanese National Dental Technician Examination (JNDTE). By analysing the AI's answers to a variety of questions, including both text-based items and those containing visual information across multiple domains, we examined the practicality of using AI as a supportive tool for learning and assessment in dental education.
A total of 400 JNDTE questions (2018-2022) were analysed using ChatGPT-4o. Standardized prompts were used, and statistical analysis was conducted using Fisher's exact test.
The AI demonstrated high accuracy in basic knowledge-based questions but lower accuracy in specialized topics requiring technical skills. Notably, accuracy decreased when visual elements (figures, tables, and photographs) were present. The highest accuracy was observed in 'Dental materials, laboratory equipment, and processing technology' (84.1%), while the lowest was in 'Orthodontic technology' (46.2%) and 'Pediatric dental technology' (50.0%). The AI particularly struggled with interpreting radiographic images and procedural workflows.
ChatGPT-4o demonstrated reasonable proficiency with JNDTE-related knowledge, suggesting its potential application as a supplementary tool in dental education. However, its limitations in processing visual and technical content highlight the need for advancements in AI-driven image recognition and simulation-based learning.
The findings of this study highlight the potential application of AI models like ChatGPT-4o as a supplementary tool in dental technician education and examination preparation. Enhancing AI-driven image recognition and simulation-based learning could improve its effectiveness in dental education and clinical training, ultimately contributing to better learning outcomes and skill development for future dental technicians.
随着人工智能(AI)的发展,其在教育和考试中的作用不断扩大。本研究旨在评估ChatGPT-4o在解答日本国家牙科技师考试(JNDTE)问题时的准确性和响应能力。通过分析人工智能对各种问题的回答,包括基于文本的题目以及跨多个领域包含视觉信息的题目,我们考察了将人工智能用作牙科教育学习和评估支持工具的实用性。
使用ChatGPT-4o分析了总共400道JNDTE问题(2018 - 2022年)。使用了标准化提示,并采用Fisher精确检验进行统计分析。
人工智能在基于基础知识的问题上表现出较高的准确性,但在需要技术技能的专业主题上准确性较低。值得注意的是,当存在视觉元素(图表、表格和照片)时,准确性会下降。在“牙科材料、实验室设备和加工技术”方面观察到最高准确率(84.1%),而在“正畸技术”(46.2%)和“儿童牙科技术”(50.0%)方面最低。人工智能在解读放射图像和程序工作流程方面尤其困难。
ChatGPT-4o在与JNDTE相关的知识方面表现出一定的熟练度,表明其在牙科教育中作为辅助工具的潜在应用。然而,其在处理视觉和技术内容方面的局限性凸显了人工智能驱动的图像识别和基于模拟的学习方面取得进展的必要性。
本研究结果凸显了ChatGPT-4o等人工智能模型在牙科技师教育和考试准备中作为辅助工具的潜在应用。加强人工智能驱动的图像识别和基于模拟的学习可以提高其在牙科教育和临床培训中的有效性,最终有助于未来牙科技师获得更好的学习成果和技能发展。