Accuracy of Artificial Intelligence-Assisted Staging and Grading for Diagnosis of Periodontitis.

NCT07113327 | Completed

• 1 other identifier: FDASU-REC IM012413
• Study Type: observational
• Target: 47
• Locations: 1 country
• Sites: 1

Brief Summary

This observational study aims to develop and assess the accuracy, specificity, and sensitivity of a deep learning model for the classification of periodontitis using panoramic radiographs and clinical data inputs. A total of 341 panoramic images will be retrospectively collected and labeled by experienced periodontists to train and test the model. The model will be evaluated for its ability to determine the stage and grade of periodontitis based on the 2017 classification guidelines set by the American Academy of Periodontology. The results will be compared to those of clinical experts to validate the AI-assisted diagnostic system. This study is conducted at the Faculty of Dentistry, Ain Shams University, in fulfillment of a Master's degree in Periodontology.

Conditions

Periodontitis

Keywords

Periodontitis; Artificial Intelligence; Deep Learning

Outcome Measures

Primary Outcomes (1)

• Establishment of an AI model for calculating periodontal bone loss (%) and assigning stage and grade of periodontitis using 2017 classification

  Development of a machine learning model using retrospectively collected panoramic radiographs to calculate the percentage of periodontal bone loss (PBL) for each tooth and assign a stage (I-IV) and grade (A-C) of periodontitis according to the 2017 World Workshop classification of Periodontal and Peri-implant Diseases. The outcome will be reported as the accuracy percentage in which the model successfully provides both a PBL calculation and a corresponding stage and grade classification without processing errors.

  10 months

Secondary Outcomes (1)

• Diagnostic performance of the AI model compared to specialist diagnosis (accuracy, sensitivity, specificity)

  3 months

Study Arms (1)

Periodontitis Patients: Model's Testing Set

This cohort includes 47 patients diagnosed with different stages and grades of periodontitis. Each participant underwent clinical examination and panoramic radiography. Their images and clinical data were used to validate the performance of a deep learning model developed to classify periodontal staging and grading according to the 2017 classification by the American Academy of Periodontology. No intervention was administered; the study is observational and retrospective in design.

Diagnostic Test: Artificial Intelligence-Assisted Staging and Grading for Diagnosis of Periodontitis

Interventions

Artificial Intelligence-Assisted Staging and Grading for Diagnosis of Periodontitis DIAGNOSTIC_TEST

A deep learning diagnostic model (using DenseNet and VGG16 architectures) was applied to panoramic radiographs of 47 patients to classify the stage and grade of periodontitis. The model was trained on an external dataset and validated against expert-labeled outcomes. The purpose was to assess the accuracy of AI in replicating clinician-level diagnosis based on the 2017 classification system of periodontitis.

Periodontitis Patients: Model's Testing Set

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

A total of 47 adult patients diagnosed with periodontitis based on clinical and radiographic criteria were included. All participants were recruited from the outpatient clinics of the Periodontology Department at Ain Shams University. The population consisted of individuals with different stages and grades of periodontitis, providing a diverse testing sample for AI diagnostic validation.

You may qualify if:

• patients with periodontitis causing radiographic bone loss

You may not qualify if:

• x-ray images with
• Mixed dentition
• Orthodontic brackets
• Images with artifacts and distortion

Sponsors & Collaborators

• Ain Shams University: lead

Study Sites (1)

Ain Shams University

Cairo, Egypt

Location

MeSH Terms

Conditions

Periodontitis

Condition Hierarchy (Ancestors)

Periodontal Diseases; Mouth Diseases; Stomatognathic Diseases

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: CROSS SECTIONAL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Master's Degree Candidate at the Department of Oral Medicine, Periodontology, and Oral Diagnosis

Study Record Dates

• First Submitted: August 1, 2025
• First Posted: August 8, 2025
• Study Start: July 1, 2024
• Primary Completion: May 30, 2025
• Study Completion: June 1, 2025
• Last Updated: August 14, 2025

Record last verified: 2025-08

Locations

EG (1)