Leveraging ChatGPT to support terminology learning in oral anatomy: a mixed-methods study among linguistically diverse dental students

利用 ChatGPT 辅助口腔解剖学术语学习:一项针对不同语言背景牙科学生的混合方法研究

阅读:1

Abstract

BACKGROUND: English-medium instruction (EMI) in health professional education presents linguistic barriers for non-native English-speaking students, particularly in terminology-dense subjects like dental anatomy. While artificial intelligence (AI) has shown promise in educational contexts, its application to support terminology learning among multilingual learners remains underexplored. This study evaluated the impact of ChatGPT-assisted learning on terminology comprehension and student engagement among international dental students in Malaysia. METHODS: A convergent mixed-methods pilot study was conducted with 35 Chinese international Year 1 and Year 2 dental students enrolled in an oral anatomy course at SEGi University. Students completed pre- and post-intervention comprehension tests and engagement surveys. Over an eight-week period, students used ChatGPT to clarify terminology and explore anatomical content. ChatGPT usage logs were analyzed, and post-intervention focus group discussions were conducted. Quantitative data were analyzed using paired t-tests and Wilcoxon Signed-Rank Tests; qualitative data underwent thematic analysis. RESULTS: Comprehension scores improved significantly post-intervention (mean increase = 5.7 points, p< 0.001; Cohen’s d = 1.91). Engagement scores also increased significantly (p < 0.001), reflecting enhanced autonomy and motivation. ChatGPT was used primarily for term clarification (45%), function explanation (32%), and structural comparisons (23%). Thematic analysis revealed four key themes: (1) Clarity and Confidence, (2) Self-Directed Learning, (3) Concerns About Accuracy and Overreliance, and (4) Ethical and Privacy Awareness. CONCLUSIONS: AI-assisted terminology learning significantly improved comprehension and engagement among linguistically diverse dental students, aligning with principles from Cognitive Load Theory (CLT) and Self-Determination Theory (SDT). However, ethical concerns—particularly around data privacy and unchecked reliance—highlight the importance of faculty guidance and institutional oversight. These findings underscore the value of hybrid AI-human approaches that are pedagogically sound, ethically responsible, and culturally adaptive. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1186/s12909-025-07968-0.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。