Assessment of Artificial Intelligence for Treatment Decision Recommendation of Adult Skeletal Class III Patients

NCT ID: NCT06002373

Last Updated: 2023-08-23

Basic Information

• Recruitment Status: UNKNOWN
• Total Enrollment: 150 participants
• Study Classification: OBSERVATIONAL
• Study Start Date: 2023-05-01
• Study Completion Date: 2024-02-29

Brief Summary

The study titled "Reliability Of Artificial Intelligence for Treatment Decision Recommendation of Adult Skeletal Class III Patients" aims to assess the accuracy and dependability of artificial intelligence (AI) in providing treatment decision recommendations for adult patients with skeletal Class III malocclusion. Skeletal Class III malocclusion is characterized by an underdeveloped upper jaw or an overdeveloped lower jaw, leading to facial and dental irregularities. The study focuses on evaluating whether AI-based recommendations can reliably guide orthodontic treatment planning for this specific patient group.

This diagnostic test accuracy study involves collecting a diverse dataset of adult patients diagnosed with skeletal Class III malocclusion. AI algorithms will be trained on this dataset using various clinical and radiographic parameters to learn patterns and make treatment recommendations. The study will then compare the AI-generated treatment recommendations to those provided by experienced orthodontists.

Key aspects of the study include:

AI Reliability: The primary objective is to assess how consistently and accurately the AI system can recommend appropriate treatment decisions for adult skeletal Class III patients.

Diagnostic Test Accuracy: The study will determine the sensitivity, specificity, positive predictive value, and negative predictive value of the AI-generated treatment recommendations. This analysis will highlight the AI's ability to correctly identify patients who require specific treatment interventions.

Clinical Validity: Researchers will investigate whether the AI recommendations align with the decisions made by experienced orthodontists. This assessment is crucial to establish the AI system's clinical applicability.

Potential Benefits: If the AI system proves reliable and accurate, it could offer a time-efficient and standardized method for treatment decision support, aiding orthodontists in providing personalized care to adult skeletal Class III patients.

By conducting this study, researchers aim to contribute to the advancement of AI-assisted medical decision-making within the field of orthodontics. Successful outcomes would have the potential to revolutionize treatment planning processes, improve patient outcomes, and provide a valuable tool for orthodontists to make informed treatment decisions for adult skeletal Class III patients

Conditions

Skeletal Dysplasia; Reverse Overjet

Study Design

• Observational Model Type: COHORT
• Study Time Perspective: RETROSPECTIVE

Eligibility Criteria

Inclusion Criteria

• Skeletally mature patients with CVMI 6.
• Skeletal class III patients
• No congenital deformity, syndrome, or cleft.
• No previous surgical intervention
• No mandibular transverse functional shift.
• Normal overjet, overbite after completion of treatment.
• Patients with well finished occlusion.
• Patients who have achieved adequate functional and aesthetic results at the end of their treatment.
• Good quality initial and final lateral cephalometric radiographs.
• No sex predilection.

Exclusion Criteria

• Adolescents and skeletally immature patients.
• Patients with pseudo class III.
• Syndromic patients.
• Patients with facial deformity at the naso-maxillary complex

• Minimum Eligible Age: 18 Years
• Eligible Sex: ALL
• Accepts Healthy Volunteers: Yes

Sponsors

Cairo University

OTHER

Sponsor Role: lead

Responsible Party

Maha Abd El-Monem Nasr

Principal Investigator

Responsibility Role: PRINCIPAL_INVESTIGATOR

Locations

Cairo University

Cairo, , Egypt

Site Status: RECRUITING

Countries

Egypt

Central Contacts

Maha AM Swelam, PhD

Role: CONTACT

maha.swelam@gmail.com

00201123344551

Facility Contacts

Abd El Rahim

Role: primary

Other Identifiers

8114

Identifier Type: -

Identifier Source: org_study_id