Comparison of Artificial Intelligence and Clinicians With Different Experience Levels in Assessing Gingival Phenotype

NCT07570290 | Not Yet Recruiting

• 1 other identifier: OMUKAEK NO:225/335
• Study Type: observational
• Target: 40
• Locations: 0 countries
• Sites: N/A

Brief Summary

The goal of this observational study is to compare the performance of clinicians with different experience levels and a deep learning-based artificial intelligence (AI) model in assessing gingival phenotype using two diagnostic methods: the periodontal probe transparency method and visual assessment from standardized clinical photographs. The main questions it aims to answer are: Can AI achieve comparable accuracy to human examiners in both probe transparency and visual assessment methods? Does examiner experience level influence diagnostic performance and agreement with the reference standard in these methods? Researchers will compare AI, dental students, and periodontology residents to determine accuracy, sensitivity, specificity, and agreement with the gold standard for each method. Participants will: Undergo standardized intraoral photography of maxillary anterior teeth, with and without a periodontal probe in place, following a validated protocol. Have gingival phenotype determined by a reference periodontologist using the probe transparency method as the gold standard. Have their photographs evaluated by AI, dental students, and residents for phenotype classification using both methods.

Conditions

Gingival Phenotype Assessment

Keywords

gingiva; Gingival phenotype; Deep Learning; Transparency Method

Outcome Measures

Primary Outcomes (1)

• Diagnostic Accuracy of Each Examiner Group and AI Model in the Periodontal Probe Transparency Method

  Accuracy in determining probe visibility (visible vs. not visible) compared to the gold standard classification by an experienced periodontologist. Measure Type: Proportion (%). Analysis: Accuracy, sensitivity, specificity, and Cohen's kappa coefficient will be calculated.

  At the time of image evaluation (single session).

Secondary Outcomes (3)

• Diagnostic Accuracy of Each Examiner Group and AI Model in Visual Assessment Method

  At the time of image evaluation (single session).

• Agreement Between Examiner Groups and AI Model

  At the time of image evaluation and at 2-week retest (for a random subset of evaluators).

• Effect of Examiner Experience Level on Diagnostic Performance

  At the time of image evaluation (single session).

Study Arms (3)

Periodontology Research Assistant

Research assistants in periodontology will assess standardized intraoral photographs using both the periodontal probe transparency method and visual assessment to classify gingival phenotype.

Diagnostic Test: Periodontal Probe Transparency Method; Diagnostic Test: Visual Assessment Method

Dental Students

Fourth- and fifth-year dental intern students will assess standardized intraoral photographs using both the periodontal probe transparency method and visual assessment to classify gingival phenotype.

Diagnostic Test: Periodontal Probe Transparency Method; Diagnostic Test: Visual Assessment Method

Artificial Intelligence Model

A deep learning-based image classification model will analyze standardized intraoral photographs, detecting probe visibility and classifying gingival phenotype according to the periodontal probe transparency method and visual assessment criteria.

Diagnostic Test: Periodontal Probe Transparency Method; Diagnostic Test: Visual Assessment Method; Other: Deep Learning-Based Artificial Intelligence Model

Interventions

Periodontal Probe Transparency Method DIAGNOSTIC_TEST

Standardized intraoral photography of the maxillary anterior teeth with a periodontal probe placed according to the transparency method protocol to determine probe visibility status.

Artificial Intelligence Model; Dental Students; Periodontology Research Assistant

Visual Assessment Method DIAGNOSTIC_TEST

Standardized intraoral photography of the maxillary anterior teeth without a periodontal probe, evaluated for gingival phenotype classification based on morphological features.

Artificial Intelligence Model; Dental Students; Periodontology Research Assistant

Deep Learning-Based Artificial Intelligence Model OTHER

A deep learning image classification algorithm trained to assess probe visibility and gingival phenotype from standardized intraoral photographs.

Artificial Intelligence Model

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population will consist of systemically and periodontally healthy adults attending the Department of Periodontology at Ondokuz Mayıs University, Faculty of Dentistry, for routine dental care or check-up. Eligible participants will have natural maxillary anterior incisors and meet all inclusion criteria. Additionally, the examiner population will include: Periodontology research assistants currently working in the department. Fourth- and fifth-year dental intern students who have completed the periodontology clinical rotation.

You may qualify if:

• Systemically healthy individuals with periodontal health.
• Presence of natural maxillary anterior incisors.

You may not qualify if:

• Presence of fixed crowns or cervical restorations on the evaluated teeth.
• Pregnant or breastfeeding women.
• Signs of gingival inflammation or periodontal disease with attachment loss.
• Presence of buccal gingival recession.
• Use of medications known to cause gingival enlargement.
• Presence of congenital anomalies or dental structural defects.
• Research assitant: Must be currently working in the Department of Periodontology.
• Dental Intern Students: Fourth- or fifth-year students who have completed periodontology clinical rotation.
• Those who are confirmed to be color blind by the Ishihara test

Sponsors & Collaborators

• Ondokuz Mayıs University: lead

Related Links

• Ondokuz Mayis University Clinical Research Ethics Committee

Central Study Contacts

Sude Yıldırım Bolat, DDS

CONTACT

+905378947645; sugde.sude@gmail.com

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: CROSS SECTIONAL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: research assistant

Study Record Dates

• First Submitted: April 29, 2026
• First Posted: May 6, 2026
• Study Start (Estimated): May 15, 2026
• Primary Completion (Estimated): August 15, 2026
• Study Completion (Estimated): October 15, 2026
• Last Updated: May 6, 2026

Record last verified: 2026-04

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL, SAP, ICF
• Time Frame: De-identified IPD and supporting documents will be available within 12 months after publication of the main results and will remain available for at least 5 years.
• Access Criteria: https://www.icmje.org/recommendations/browse/publishing-and-editorial-issues/clinical-trial-registration.html