Forecasting craniofacial growth in individuals with class III malocclusion by computational modelling

Area of Science:

• Orthodontics and craniofacial biology.
• Computational biology and data analysis.

Background:

• Class III malocclusion presents complex craniofacial growth patterns.
• Accurate prediction of craniofacial growth is crucial for effective clinical management.

Purpose of the Study:

• To develop a robust mathematical model for predicting craniofacial growth in Class III subjects.
• To enable longitudinal verification and clinical application of growth predictions.

Main Methods:

• Applied fuzzy clustering and network analysis to cephalometric data from 429 untreated Class III female patients.
• Analyzed data across four distinct age groups (7-17 years).

Main Results:

• Network analysis visualized craniofacial growth dynamics and correlations.
• Fuzzy clustering identified distinct growth patterns and coherences in Class III malocclusion.
• Individual growth trajectory prediction depends on cluster membership, representing a specific growth strategy.
• Model validation through longitudinal forecasting of 28 Class III subjects demonstrated reliability.

Conclusions:

• Combined fuzzy clustering and network algorithms created a global model for craniofacial growth.
• The model effectively integrates multiple cephalometric features.
• Predicts individual risk for Class III facial pattern imbalance during growth.