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

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 the study 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 research assistants 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 research assistants for phenotype classification using both methods.

Study Overview

• Status: Not yet recruiting
• Conditions: Gingival Phenotype Assessment
• Intervention / Treatment: Diagnostic test: Periodontal Probe Transparency Method; Diagnostic test: Visual Assessment Method; Other: Deep Learning-Based Artificial Intelligence Model

Detailed Description

Gingival phenotype, representing the thickness and morphological characteristics of the gingival soft tissues, plays a critical role in periodontal health, treatment planning, and the long-term stability of clinical outcomes. A thin phenotype is associated with increased risk of gingival recession, papilla loss, and inflammatory complications, while a thick phenotype offers better soft tissue stability but may mask inflammation. Accurate and reproducible assessment of gingival phenotype is therefore essential in clinical dentistry.

The periodontal probe transparency method is considered the gold standard for phenotype assessment due to its simplicity and non-invasiveness. In this method, a periodontal probe is inserted into the sulcus from the buccal aspect, and if the probe is visible through the gingival tissue, the phenotype is classified as thin; if not visible, it is classified as thick. However, the method is susceptible to variability depending on examiner experience, lighting conditions, and subjective interpretation.

Visual assessment, which relies solely on the inspection of gingival and tooth morphology in photographs without a probe, offers a non-contact alternative but is similarly subject to examiner-related variability. These limitations highlight the need for standardized and objective approaches to phenotype determination.

Artificial intelligence (AI), particularly deep learning-based image analysis, has shown promising results in dental diagnostics, enabling automated classification of clinical images with high accuracy and reproducibility. In periodontal research, AI has been applied for lesion detection and radiographic interpretation, but its application in gingival phenotype assessment-especially using the probe transparency method and visual assessment-remains unexplored.

This observational study aims to compare the diagnostic performance of a deep learning-based AI model with human examiners of different experience levels (periodontology residents vs. dental students) in assessing gingival phenotype from standardized intraoral photographs using both the periodontal probe transparency method and visual assessment. The reference standard will be the classification provided by an experienced periodontologist using the probe transparency method in a clinical setting.

The study will evaluate and compare accuracy, sensitivity, specificity, and inter-/intra-examiner agreement across examiner groups and the AI model. The findings are expected to provide insights into the potential of AI as a standardizing tool, reducing inter-examiner variability and supporting clinical decision-making, particularly for less experienced clinicians. Additionally, the study may inform the integration of AI-assisted diagnostic tools in dental education and practice, improving training efficiency and clinical outcomes.

• Study Type: Observational
• Enrollment (Estimated): 40

Contacts and Locations

• Study Contact: Name: Sude Yıldırım Bolat, DDS; Phone Number: +905378947645; Email: sugde.sude@gmail.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

• 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.

Description

Inclusion Criteria for Volunteer Participants Who Will Participate in Transparency and Visual Assessment:

• Systemically and periodontally healthy individuals.
• Presence of natural maxillary anterior incisors.

Exclusion Criteria:

• 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.

Inclusion Criteria for Clinicians:

• Research assistants: Must be currently working in the Department of Periodontology.
• Dental Intern Students: Fourth- or fifth-year students who have completed periodontology clinical rotation.

Exclusion Criteria for Clinicians:

• Those who are confirmed to be color blind by the Ishihara test

Study Plan

How is the study designed?

Number of groups / cohorts

3

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
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; Standardized intraoral photography of the maxillary anterior teeth with a periodontal probe placed according to the transparency method protocol to determine probe visibility status.; Diagnostic test: Visual Assessment Method; Standardized intraoral photography of the maxillary anterior teeth without a periodontal probe, evaluated for gingival phenotype classification based on morphological features.
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; Standardized intraoral photography of the maxillary anterior teeth with a periodontal probe placed according to the transparency method protocol to determine probe visibility status.; Diagnostic test: Visual Assessment Method; Standardized intraoral photography of the maxillary anterior teeth without a periodontal probe, evaluated for gingival phenotype classification based on morphological features.; Other: Deep Learning-Based Artificial Intelligence Model; A deep learning image classification algorithm trained to assess probe visibility and gingival phenotype from standardized intraoral photographs.
Periodontology Research Assistants; 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; Standardized intraoral photography of the maxillary anterior teeth with a periodontal probe placed according to the transparency method protocol to determine probe visibility status.; Diagnostic test: Visual Assessment Method; Standardized intraoral photography of the maxillary anterior teeth without a periodontal probe, evaluated for gingival phenotype classification based on morphological features.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
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 Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic Accuracy of Each Examiner Group and AI Model in Visual Assessment Method	Accuracy in classifying gingival phenotype (thin vs. thick) without probe, compared to the gold standard classification. Measure Type: Proportion (%).	At the time of image evaluation (single session).
Agreement Between Examiner Groups and AI Model	Inter-examiner and intra-examiner agreement for each method, evaluated using Cohen's kappa coefficient and intraclass correlation coefficient (ICC).	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	Comparison of accuracy and agreement between research assistants and dental intern students for each method. Proportion (%), agreement statistic.	At the time of image evaluation (single session).

Collaborators and Investigators

• Sponsor: Ondokuz Mayıs University

Publications and helpful links

Helpful Links

• Ondokuz Mayis University Clinical Research Ethics Committee

Study record dates

Study Major Dates

• Study Start (Estimated): May 15, 2026
• Primary Completion (Estimated): August 15, 2026
• Study Completion (Estimated): October 15, 2026

Study Registration Dates

• First Submitted: April 29, 2026
• First Submitted That Met QC Criteria: April 29, 2026
• First Posted (Actual): May 6, 2026

Study Record Updates

• Last Update Posted (Actual): May 11, 2026
• Last Update Submitted That Met QC Criteria: May 6, 2026
• Last Verified: May 1, 2026

More Information

Terms related to this study

• Keywords: Deep Learning; Gingival phenotype; gingiva; Transparency Method
• Other Study ID Numbers: OMUKAEK NO:225/335

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Plan Description: De-identified individual participant data (IPD), including demographic characteristics, periodontal measurements, and standardized intraoral photographs, may be shared upon reasonable request for academic purposes. Access will require a data use agreement and approval by the principal investigator.
• IPD Sharing 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.
• IPD Sharing Access Criteria: https://www.icmje.org/recommendations/browse/publishing-and-editorial-issues/clinical-trial-registration.html
• IPD Sharing Supporting Information Type: STUDY_PROTOCOL; SAP; ICF

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No