In Vitro Simulation of Airway Volume Changes Following Rapid Maxillary Expansion: A 3D CBCT and Machine Learning Analysis

Abstract

Background: Rapid Maxillary Expansion (RME) is a prevalent orthodontic procedure designed to widen the maxillary arch to enhance occlusion and airway function. While prior research has shown varied effects of RME on airway volume, a comprehensive analysis utilizing advanced imaging and analytical methods remains limited. This study aims to address this gap by employing 3D Cone-Beam Computed Tomography (CBCT) and machine learning algorithms to thoroughly assess airway volume changes following RME.

Objective: To evaluate the impact of RME on airway volume through detailed in vitro simulations using 3D CBCT imaging and to apply machine learning techniques for an in-depth analysis of these changes.

Methods: This study involved 30 pre-treatment and post-treatment CBCT scans of patients who underwent RME. The scans were processed using DentAnalyser (Version 3.2) for volumetric analysis and machine learning models, including Convolutional Neural Networks (CNN) and AIForecast (Version 2.1), were employed to predict airway volume changes. Statistical analysis was performed using paired t-tests and analysis of variance (ANOVA) to determine the significance of the changes observed.

Results: The average airway volume increased significantly from 15.3 cm³ (± 2.5 cm³) before RME to 18.7 cm³ (± 2.7 cm³) after RME, reflecting a mean increase of 22.3% (p < 0.001). Machine learning models exhibited high predictive accuracy, with CNN achieving 95.8% and AIForecast achieving 92.3%. These findings were consistent across different patient demographics and treatment conditions.

Conclusion: The study confirms that RME significantly enhances airway volume, as shown by 3D CBCT imaging and machine learning analysis. The use of advanced analytical techniques provides a reliable method for assessing airway changes and offers valuable insights into the clinical benefits of RME. These results underscore the effectiveness of RME in improving airway dimensions, with implications for optimizing orthodontic treatment planning and patient management.