Augmented teaching of the next-generation-dentists in diagnosis of common dental diseases with the overjet artificial intelligence (AI) module

Abstract

Objective

The objective of this study is to investigate the feasibility and effectiveness of integrating artificial intelligence (AI) technology into dental education, specifically in the field of oral & maxillofacial radiology. The aim is to assess whether an AI-augmented radiographic training module can assist students in consistently identifying common dental lesions and improving their radiographic diagnostic skills.

Study Design

In this pilot study, 10 intra-oral radiographs were selected for charting carious lesions, and 2 oral and maxillofacial radiologists independently charted and confirmed the presence of 42 proximal carious lesions. Fifty D3 University of Florida dental students participated in the study. They initially recorded dental caries after a traditional teaching module and then re-charted the carious lesions after receiving training through an Overjet training module.

Results

Using traditional methods of teaching, the D3 students could diagnose an average of 26 of the 42 proximal lesions. After learning from an AI training module, there was a 35% increase in the detection of carious lesions among the D3 students, with an average of 36 of the 42 proximal lesions being identified. The rate of false positives remained constant at 5%.

Conclusion

Our results indicate that AI-augmented radiographic training can effectively help dental students learn the radiographic diagnosis of proximal caries. The student engagement teaching method creates a learner-centered educational model that enhances the learning process. Therefore, incorporating AI in dental education holds great potential for advancing the field and improving the quality of education provided to dental students.