Artificial Intelligence in Dental Education: A Pilot Study of Caries Detection Accuracy and Instructor Agreement
Journal of Dental Education · 2026-09 · 90 (9) · 1342-1349
DOI: 10.1002/jdd.70126 ↗Abstract
ABSTRACT Purpose This pilot study evaluated the use of Second Opinion , an artificial intelligence (AI)‐based radiographic evaluation tool, to support instruction in radiographic caries detection by examining its impact on instructor diagnostic performance and inter‐instructor agreement, as well as its potential to improve instructional consistency. Methods This study used data from faculty calibration and examination development for a second‐year predoctoral dental student instructional module on radiographic caries detection. Instructor diagnostic performance—including sensitivity, specificity, accuracy, precision, and F1 score—was evaluated with and without AI‐assisted interpretation across varying carious lesion depths. Results Instructors demonstrated high baseline diagnostic performance, with group average metrics exceeding 91% across all parameters. There was strong agreement between Second Opinion and instructor assessments, and AI‐assisted interpretation led to modest, non‐significant improvements in diagnostic performance. Notably, AI use increased the rate of unanimous agreement, particularly for sound surfaces (E0) and early‐to‐moderate dentinal caries (D1/D2). Conclusions Second Opinion demonstrated diagnostic performance comparable to that of the instructor group in radiographic caries detection and contributed to improved inter‐instructor agreement. These findings support its use in instructor calibration and case selection, highlighting the potential of AI‐assisted interpretation to enhance instructional consistency and strengthen assessment reliability in dental radiographic education.
EUVIMED