Validation of AI-Based Cephalometric Analysis in Orthodontics

NCT07315152 | Not Yet Recruiting

• 1 other identifier: AI-CEPH-VAL-01
• Study Type: observational
• Target: 55
• Locations: 1 country
• Sites: 1

Brief Summary

This study is designed to evaluate whether artificial intelligence can analyze cephalometric images in orthodontics as a reliable tool for diagnosis and treatment planning. The study will include orthodontic patients who need cephalometric evaluation. Participants will have their X-ray images analyzed using both the AI system and traditional manual methods. The study will compare the results to see how closely the AI measurements match the standard measurements. This information may help patients, families, and health care providers understand how AI can support orthodontic diagnosis and treatment planning.

Conditions

Malocclusion

Keywords

Treatment planing Orthodontics cephalometric analysis

Outcome Measures

Primary Outcomes (1)

• Accuracy of AI-driven cephalometric analysis

  Comparison of cephalometric measurements obtained using AI software with manual tracings to evaluate the accuracy and reliability of AI-driven analysis in orthodontic diagnosis.

  Day 1

Study Arms (1)

Patients

Patients undergoing routine cephalometric analysis, used to validate AI-driven measurements against manual tracings.

Diagnostic Test: Artificial Intelligence-Driven Cephalometric Analysis

Interventions

Artificial Intelligence-Driven Cephalometric Analysis DIAGNOSTIC_TEST

Cephalometric analysis performed using AI software, compared with manual tracings for validation of accuracy in orthodontic diagnosis and treatment planning.

Patients

Eligibility Criteria

• Age: 12 Years - 30 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Child (0-17), Adult (18-64)
• Sampling Method: Non-Probability Sample

Study Population

consists of orthodontic patients aged 12 to 40 years who require orthodontic diagnosis and treatment planning. Participants will have good-quality lateral cephalometric radiographs taken using standardized imaging protocols. The study includes both male and female patients with no previous orthodontic treatment.

You may qualify if:

• No systemic disease.
• Not receiving medical treatment that could interfere with bone metabolism.
• Good level of oral hygiene.
• No periodontal disease or radiographic evidence of bone loss.

You may not qualify if:

• Periodontally compromised patients.
• Presence of systemic diseases.
• Drug dependencies.
• Uncooperative patients.

Sponsors & Collaborators

• Al-Azhar University: lead

Study Sites (1)

Faculty of Dentistry, Al-Azhar University

Asyut, Asyut Governorate, 71524, Egypt

Location

Related Publications (1)

• Kunz F, Stellzig-Eisenhauer A, Zeman F, Boldt J. Artificial intelligence in orthodontics : Evaluation of a fully automated cephalometric analysis using a customized convolutional neural network. J Orofac Orthop. 2020 Jan;81(1):52-68. doi: 10.1007/s00056-019-00203-8. Epub 2019 Dec 18.

  PMID: 31853586 BACKGROUND

Related Links

• Scientific and biomedical literature related to orthodontics and artificial intelligence.

MeSH Terms

Conditions

Malocclusion

Condition Hierarchy (Ancestors)

Tooth Diseases; Stomatognathic Diseases

Study Officials

• Mohammed A Mohammed, DDs,phD

  Al-Azhar University

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Hamdi K Khalaf, BDs

CONTACT

201025135711; hamdikhalaf5@gmail.com

Noha S Mohammed, BDs

CONTACT

201148294667; nohaelkhateeb32@gmail.com

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: CROSS SECTIONAL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Principal Investigator (Master's Degree Researcher)

Study Record Dates

• First Submitted: December 18, 2025
• First Posted: January 2, 2026
• Study Start: May 1, 2026
• Primary Completion (Estimated): June 1, 2027
• Study Completion (Estimated): June 1, 2028
• Last Updated: January 7, 2026

Record last verified: 2025-12

Locations

EG (1)