Journal of dental education · 2025
Artificial Intelligence in Dental Education: A Pilot Study of Caries Detection Accuracy and Instructor Agreement.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Ji Somyung, Daly Ladan, Shah Kumar, Bhoopathi Vinodh, Mallya Sanjay M
Аннотация
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.
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.