Artificial Intelligence (AI) for Proximal Caries Detection and Its Impact on Treatment Threshold

NCT07648212 | Not Yet Recruiting

• 1 other identifier: HUM00276058
• Study Type: interventional
• Target: 60
• Locations: 1 country
• Sites: 1

Brief Summary

The purpose of this study is to assess the impact of artificial intelligence on proximal caries detection and subsequent treatment decisions of early learners and compare those with outcomes of experienced learners.

Conditions

Caries,Dental

Keywords

Artificial intelligence; Dental students (years 2-4); Dental resident or junior faculty

Outcome Measures

Primary Outcomes (7)

• Lesion severity

  Levels for this outcome will be sound, outer enamel, inner enamel/outer dentin, inner dentin.

  approximately 1 week (2 sessions)

• Diagnostic accuracy

  Approximately 1 week (2 sessions)

• Specificity

  Approximately 1 week (2 sessions)

• Overall sensitivity

  Approximately 1 week (2 sessions)

• Sensitivity for outer enamel

  Approximately 1 week (2 sessions)

• Sensitivity for inner enamel/outer dentin

  Approximately 1 week (2 sessions)

• Sensitivity for inner dentin

  Approximately 1 week (2 sessions)

Secondary Outcomes (1)

• Intervention

  approximately 1 week (2 sessions)

Study Arms (2)

Early Learners - Dental students

OTHER

Other: Review of Radiograph Images

Late Learners - Dental resident or junior faculty

OTHER

Other: Review of Radiograph Images

Interventions

Review of Radiograph Images OTHER

Participants will be asked to attend two visits and view a randomized series of dental radiographs (10 at each visit). Participants will answer a set of questions for each image reviewed. Some of the radiographs will have an Artificial Intelligence enhancement and some will not. Participants will be asked to return within about one week of the first visit to view the second set of x-rays and answer the survey questions.

Early Learners - Dental students; Late Learners - Dental resident or junior faculty

Eligibility Criteria

• Age: 18 Years - 99 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Provide informed consent
• Willing to comply with all study procedures and be available for the duration of the study
• Dental student in second, third, or fourth year of dental school at University of Michigan School of Dentistry
• Provide informed consent
• Willing to comply with all study procedures and be available for the duration of the study
• Dental resident or junior faculty having at least 2 years of clinical experience outside of a dental education setting

You may not qualify if:

• Dental students who do not have previous experience with caries detection (such as first year dental students)
• Residents that do not have frequent exposure to caries detection, such as orthodontic, periodontic, oral surgery graduate residents.

Sponsors & Collaborators

• University of Michigan: lead
• Delta Dental Plan of Michigan: collaborator

Study Sites (1)

University of Michigan

Ann Arbor, Michigan, 48109, United States

Location

MeSH Terms

Conditions

Dental Caries

Condition Hierarchy (Ancestors)

Tooth Demineralization; Tooth Diseases; Stomatognathic Diseases

Study Officials

• Margherita Fontana, DDS, PhD

  University of Michigan

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Carmen Boren, DDS, FAGD

CONTACT

701-240-8191; drcarmen@umich.edu

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: PARTICIPANT
• Masking Details: Radiographs will be selected from an ongoing longitudinal cohort study pool comprised of 1172 de-identified mixed dentition (up to the age of 12) images. Participants will view and diagnose a randomized set of x-rays in a clinical environment. There will be 30 early learners and 30 late learners enrolled.
• Purpose: OTHER
• Intervention Model: CROSSOVER
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Professor of Dentistry

Model Details: This proposed study is designed to compare a binary outcome (overall diagnostic accuracy, and surgical restorative intervention vs. non-surgical restorative/no intervention) between evaluations with AI and without AI. The comparisons are made separately for early learners and late learners.

Study Record Dates

• First Submitted: June 9, 2026
• First Posted: June 15, 2026
• Study Start: June 1, 2026
• Primary Completion (Estimated): May 1, 2027
• Study Completion (Estimated): May 1, 2027
• Last Updated: June 15, 2026

Record last verified: 2026-06

Data Sharing

• IPD Sharing: Will not share

Locations

US (1)