Digital and artificial intelligence-assisted cephalometric training effectively enhanced students' landmarking...

Digital cephalometric analyses, including those assisted by artificial intelligence (AI), are widely used in clinical practice. Similarly, computer-assisted learning has demonstrated teaching outcomes comparable to those of traditional methods in orthodontic education. However, the potential application of digital and AI-assisted cephalometric training in the preclinical education of orthodontic students remains unexplored. Cephalometric analysis is a fundamental skill for orthodontic students and practitioners. Therefore, this study aimed to integrate digital and AI-assisted cephalometric training into preclinical orthodontic education and evaluate its educational effectiveness.

Forty undergraduate students were grouped into pairs to use digital cephalometric training software. The students' landmarking abilities were evaluated by comparing their total scores before and after training on the same two lateral radiographs using digital cephalometric training software. The effectiveness of the software in improving landmarking accuracy was assessed objectively. Lateral radiographs of eight common patient types were selected. Twenty-four clinical training students from different grades used an AI-assisted cephalometric platform to analyze skeletal, dental, and soft tissue indicators. The accuracy of the measurements was compared among students in different grades.

Digital cephalometric training, through real-time feedback and visual error-correction mechanisms, enabled students to quickly identify and correct errors in landmarking, significantly improving their accuracy. There was no significant difference in AI-assisted cephalometric analysis ability among students with varying levels of clinical experience.

Digital cephalometric training effectively enhances students' landmarking accuracy in preclinical orthodontic education. AI-assisted cephalometry has the potential to minimize performance disparities among students with varying levels of clinical experience. Owing to the real-time feedback and self-directed learning features of digital tools, these technologies serve as valuable supplements to instructor-led training, potentially reducing educators' workload and accelerating skill acquisition in novice orthodontic students. However, these preliminary findings require further multicenter validation and long-term educational assessments while also considering the ethical implications of these technologies.