Impact of Training Dental Students for an AI-Based Platform

Not Applicable

Completed

• Conditions: Artificial Intelligence; Education

• Registration Number: NCT05912361
• Lead Sponsor: University of Copenhagen

Brief Summary

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.

Detailed Description

Not available

Study Timeline

• Study First Submitted: 2023-05-24
• Study First Submitted QC: 2023-06-12
• Study First Posted: 2023-06-22
• Study Start: 2023-08-20
• Primary Completion: 2023-12-20
• Status Verified: 2024-01
• Study Completion: 2024-01-01
• Last Update Submitted: 2024-01-05
• Last Update Posted: 2024-01-08

Recruitment & Eligibility

• Status: COMPLETED
• Sex: All
• Target Recruitment: 20

Inclusion Criteria

• perhaps 4th year and 5th year dental students at the university of Copenhagen who are willing to participate voluntarily and have signed the consent letter.
• Limited or no previous knowledge and experience about AI

Exclusion Criteria

• None

Study & Design

• Study Type: INTERVENTIONAL
• Study Design: PARALLEL

Primary Outcome Measures

Name	Time	Method
Performance of students at pulp exposure prediction in the AI-based platform with and without training session based on their sensitivity	30 days	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).
Performance of students at pulp exposure prediction in the AI-based platform with and without training session based on their accuracy	30 days	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.
Performance of students at pulp exposure prediction in the AI-based platform with and without training session based on their specificity	30 days	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).

Trial Locations

Locations (1)

University of Copenhagen Department of Odontology Cariology and Endodontics Section for Clinical Oral Microbiology; 🇩🇰 Copenhagen, Denmark