Objectives: Traditional fixed prosthodontic training evaluations are time-consuming and subjective. This study aimed to introduce and evaluate a novel 3D auto-evaluate tooth preparation with an augmented reality (3DAR) visualization algorithm to enhance dental education for students and improve the efficiency of fixed prosthodontic training evaluations.
Methods: Fifty maxillary central incisors and first molars prepared by 50 dental students on typodont models were scanned with a 3D scanner to capture STL files and evaluated using the 3DAR algorithm, which calculated Euclidean distances and root mean square error (RMSE) for accuracy assessment and assigned scores based on RMSE, using an augmented reality (AR) app for interactive evaluation and visualization. These scores were compared to manual scoring with computer assistance (MSCA method), which also used RMSE but required manual alignment and model scoring. Intrarater and interrater reliability of the 3DAR scoring method was assessed using intraclass correlation coefficients (ICC) and compared with the MSCA method. Additionally, the feasibility of 3DAR was evaluated based on evaluation time and user satisfaction.
Results: The 3DAR method demonstrated good-to-excellent interrater agreement (ICC = 0.75-0.95) and perfect intrarater reliability (ICC = 1), while the MSCA method showed moderate-to-good reliability (ICC = 0.74-0.89). 3DAR significantly reduced evaluation time (10.514 s vs. 2 h required for MSCA) and received high user satisfaction ratings (average score = 4.66±0.24).
Conclusions: The 3DAR algorithm offers a reliable and efficient assessment method for prosthodontic training. It showed strong agreement with traditional methods, significantly reduced evaluation time, and achieved high user satisfaction.
Clinical significance: The integration of a 3D augmented reality-based auto-evaluation algorithm into tooth preparation training enhances reliability and provides interactive, real-time feedback on performance, highlighting its potential to advance dental education practices.
Keywords: Augmented reality; Automated scoring; Dental education; Feasibility; Preclinical practice; Reliability; Tooth preparation.
Copyright © 2024 Elsevier Ltd. All rights reserved.