Accurate identification of intraoral radiographic landmarks is essential for diagnosis; however, complex jaw anatomy presents learning challenges for undergraduate dental students. The educational potential of AI-assisted tools and drawing-based learning for intraoral radiographic anatomy remains unexplored. This study evaluated the effectiveness of ChatGPT-5.0-assisted learning and drawing-based learning as supplementary tools to enhance students’ understanding of intraoral radiographic anatomy. This comparative study included third-year Bachelor of Dental Surgery students. After a standardized lecture, students were randomly assigned to three groups: ChatGPT, self-directed learning, and drawing (n = 26 each), and baseline knowledge was assessed. The ChatGPT group used structured prompts, the drawing-based learning group drew and labelled landmarks, and the self-directed learning group studied independently. A post-intervention assessment was conducted after 12 weeks. Intragroup changes were analysed using paired t-tests with Cohen’s d, and intergroup differences using one-way ANOVA with Eta-squared (η²). ChatGPT and drawing groups showed significantly greater improvement than the Self-directed learning group. The drawing group demonstrated the most consistent gains, with significant improvement in 12 landmarks and moderate-to-large effect sizes (Cohen’s d ≈ 0.45–0.77). The ChatGPT group showed significant improvements in several landmarks, particularly in the maxillary and mandibular anterior regions. Intergroup analysis showed higher post-instructional scores for the drawing group in 20 of 30 landmarks, with moderate-to-large η² values (≈ 0.08–0.25). ChatGPT and drawing-based learning are effective supplementary strategies for learning intraoral radiographic landmarks, outperforming self-directed learning alone. Their integration into dental radiology education may enhance anatomical understanding and long-term learning outcomes.
Veerabhadrappa et al. (2026) studied this question.