# AI for diagnosing malocclusions from 3D dental models

## TL;DR

This paper shows that AI can reliably diagnose dental malocclusions using 3D models, matching the accuracy of orthodontists.

## Contribution

The study introduces a CNN-based AI system for classifying malocclusions with high diagnostic consistency.

## Key findings

- AI predictions showed strong agreement with orthodontist evaluations.
- The AI system demonstrated clinically relevant consistency in diagnosing malocclusions.

## 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.