Effect of artificial intelligence-assisted personalized feedback on radiographic diagnostic performance of dental students: a controlled study
Büşra Yılmaz, Furkan Özbey, Birkan Eyup Yilmaz
Abstract
BACKGROUND: This study aimed to evaluate the impact of MeSH based personalized learning guides generated by ChatGPT-4o on the radiographic diagnostic performance of dental students and to compare it with the traditional correct/incorrect feedback method. METHODS: This randomized controlled study was conducted among fifth-year dental students at Afyonkarahisar Health Sciences University. A total of 110 students were randomly assigned to either the experimental or control group. The experimental group received personalized study guides targeting their learning gaps, generated by ChatGPT-4o based on Medical Subject Headings (MeSH). The control group received only a standard correct/incorrect feedback analysis. One month after the intervention, a post-test was administered to assess diagnostic accuracy and student satisfaction. RESULTS: The increase in test scores from pre- to post-test was significantly higher in the experimental group (3.6 ± 1.0) compared to the control group (1.3 ± 1.2; p < 0.001). Final test scores were also significantly higher in the experimental group (p < 0.001). Survey responses indicated that the experimental group rated the feedback as more understandable, beneficial, and motivating compared to the control group. CONCLUSIONS: ChatGPT-4o based personalized feedback proved to be an effective tool for enhancing diagnostic performance and supporting learning in dental education. The findings suggest that AI-driven individualized educational strategies hold significant potential in the future of dental training.