Title

AI for diagnosing malocclusions from 3D dental models

Authors

Imad Mohammed^1,*, Subash Chandra Nayak², Vasim Akram Shaik³, Akshaya Raj⁴, Murshida Pulayakalathil⁴ & Sreejith Karattuparambil Karunakaran⁵

Affiliation

¹Department of Orthodontics, Cmai Medical Center, Uthman bin afan road, Al falah Riyadh, Saudi Arabia; ²Department of Hi- tech Dental College and Hospital, Odisha, India; ³Department of Orthodontist, Orthodontic Navodaya Dental College, Raichur, Karnataka, India; ⁴Department of Educare Institute of Dental Sciences, Malappuram, Kerala, India; ⁵Department of Prosthodontist, Divya Jyoti College of Dental Sciences and Research, Modinagar, Ghaziabad, Uttar Pradesh, India 201204; *Corresponding author

Email

Imad Mohammed - E-mail: enforces03@gmail.com; Phone: +91 9655855099
Subash Chandra Nayak - E-mail: drsubashn@gmail.com; Phone: +91 9040041220
Vasim Akram Shaik - E-mail: vasimortho@gmail.com; Phone: 0551385647
Akshaya Raj - E-mail: ashayababuraj@gmail.com; Phone: +91 9074852474
Murshida Pulayakalathil - E-mail: azimurshi@gmail.com; Phone: +91 9400040309
Sreejith Karattuparambil Karunakaran - E-mail: in.dcaredental@gmail.com; Phone: +91 9544461528

Article Type

Research Article

Date

Received October 1, 2025; Revised November 15, 2025; Accepted November 15, 2025, Published November 15, 2025

Abstract

Accurate diagnosis of dental malocclusions remains challenging due to interobserver variability among orthodontists. Therefore, it is of interest to evaluate the diagnostic reliability of artificial intelligence (AI) algorithms in classifying malocclusion types using 3D dental models compared with expert orthodontist assessments. A convolutional neural network (CNN) was trained and tested on digital impressions, and its performance was statistically analyzed against expert diagnoses. Results demonstrated strong agreement between AI predictions and orthodontist evaluations with clinically relevant consistency. These findings highlight the potential of AI-assisted diagnostics to enhance accuracy and reduce subjectivity in orthodontic assessment.

Keywords

Malocclusion, deep learning, orthodontic diagnosis, digital impressions, artificial intelligence

Citation

Mohammed et al. Bioinformation 21(11): 4194-4197 (2025)

Edited by

A Prashanth

ISSN

0973-2063

Publisher

Biomedical Informatics

License

This is an Open Access article which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly credited. This is distributed under the terms of the Creative Commons Attribution License.