The emergence of artificial intelligence (AI) and specifically deep learning (DL) have shown great potentials in finding radiographic features and treatment planning in the field of cariology and endodontics . A growing body of literature suggests that DL models might assist dental practitioners in detecting radiographical features such as carious lesions, periapical lesions, as well as predicting the risk of pulp exposure when doing caries excavation therapy. Although, current literature lacks sufficient research on the effect of sufficient training of dental practitioners for using AI-based platforms. This prospective randomized controlled trial aims to assess the performance of students when using an AI-based platform for pulp exposure prediction with and without sufficient preprocedural training. The hypothesis is that participants performance at group with sufficient training is similar to the group without sufficient training.
Study Type
INTERVENTIONAL
Allocation
RANDOMIZED
Purpose
OTHER
Masking
DOUBLE
Enrollment
20
The students at the experimental group will receive a one-hour hands-on training session before logging in to the online platform. The session will be presented by a dentist with AI experience and this session will present basic aspects of AI in radiology, deep learning (DL) applications for cariology and endodontics, as well as basics of excavation therapy and pulp exposure. the theoretical part will be followed by a hands on session on which each participant will check 11 cases of teeth with deep caries and will find the closest line between caries and pulp. their performance will be supervised by the training session presenter and the correct line will be shown them in case of making wrong line.
University of Copenhagen Department of Odontology Cariology and Endodontics Section for Clinical Oral Microbiology
Copenhagen, Denmark
Performance of students at pulp exposure prediction in the AI-based platform with and without training session based on their accuracy
The accuracy of students at both group (with and without training session) will be measured and compared together. The accuracy measurement for each student will be calculated by the number of correct predictions of pulp exposure occurrence divided by the total predictions.
Time frame: 30 days
Performance of students at pulp exposure prediction in the AI-based platform with and without training session based on their sensitivity
The sensitivity of students at both group (with and without training session) will be measured and compared together. It will be based on the proportion of actual pulp exposure cases that got predicted as pulp exposure (true positive).
Time frame: 30 days
Performance of students at pulp exposure prediction in the AI-based platform with and without training session based on their specificity
The specificity of students at both group (with and without training session) will be measured and compared together. It will be based on the proportion of actual 'no pulp exposure' cases correctly predicted as cases without pulp exposure (true negative).
Time frame: 30 days
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.