Reliability of Artificial Intelligence for Treatment Decision for Adult Skeletal Open Bite Patients

NCT06992908 | Completed

• 2 other identifiers: Adult skeletal open bite casesSelf-funded by me.
• Study Type: observational
• Target: 53
• Locations: 1 country
• Sites: 1

Brief Summary

This study evaluated a specially designed AI model developed by a programmer using x-ray readings and corresponding treatment decisions from 70% of the cases (either orthodontic treatment only or orthodontic treatment with surgery). For the evaluation, we will use the remaining 30% of cases. "Subsequently, to assess its performance, the model was tested on the remaining 30% of cases. The programmer provided only the X-ray readings as input. The AI model was then tasked with classifying.

Conditions

Openbite; Artifical Intelligence

Outcome Measures

Primary Outcomes (1)

• accuracy of diagnostic test

  In this study, the investigators have only one outcome, which is the accuracy of a diagnostic test. This test is based on the comparison of the results of machine learning decisions with a conventional method, which is an expert orthodontist's decision. Accuracy = (true positives + true negatives) / (total) A true positive will be the correct prediction of camouflage. A true negative will be the correct prediction of orthognathic surgery. Total means the total test set cases. All cases are randomly distributed. The investigators use the skeletal and dental cephalometrical parameters , some of which are angles measured by degrees, and others are linear measurements measured by millimeters. SNA SNB ANB SN/PP SN/MP Maxillary-mandibular plane angle Anterior facial height Posterior facial height Jarabak ratio Gonial angle Lower anterior facial height Open bite Maxillary anterior teeth inclination Mandibular anterior teeth inclination

  through study completion, an average of 1 year".

Study Arms (2)

Group 1: MLG acts as learning group.

Cephalometric readings parameters of cases with their decisions will be used in this group for training the machine to be able to make a decision.

Group 2: TG acts as a test group

The programmer will put parameters as input and then ask the AI model to decide on an output of the model, either camouflage or surgery.

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

Adult anterior skeletal open bite patients with at least 3mm opening.

You may qualify if:

• Moderate to severe Adult patients with anterior skeletal open bite (at least 3mm opening)
• Completed their treatment successfully.
• Well-documented cases with comprehensive preoperative and postoperative lateral cephalometric x-rays were considered.

You may not qualify if:

• Patient below 18 years.
• Improperly finished orthodontic treatment.
• Incomplete documentation.
• cleft lip and palate patient, patient with syndromes.
• Dental open bite.

Sponsors & Collaborators

• Cairo University: lead

Study Sites (1)

Faculty of Dentistry, Cairo University

Cairo, 11251, Egypt

Location

MeSH Terms

Conditions

Open Bite

Condition Hierarchy (Ancestors)

Malocclusion; Tooth Diseases; Stomatognathic Diseases

Study Officials

• Dina Osman, Associate Professor

  supervisor

  STUDY DIRECTOR

• Mostafa El-Dawlatly, Associate Professor

  supervisor

  STUDY DIRECTOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Master's student.

Study Record Dates

• First Submitted: April 24, 2025
• First Posted: May 28, 2025
• Study Start: May 12, 2024
• Primary Completion: January 15, 2025
• Study Completion: March 15, 2025
• Last Updated: May 28, 2025

Record last verified: 2025-05

Data Sharing

• IPD Sharing: Will not share

Locations

EG (1)