Artificial Intelligence-Based Evaluation of Permanent First Molar Extraction Indications in Children Using Panoramic...

Area of Science:

• Dentistry
• Artificial Intelligence
• Medical Imaging

Background:

• Evaluating extraction indications for pediatric permanent first molars is crucial for orthodontic treatment planning.
• Panoramic radiography is a common diagnostic tool in pediatric dentistry.
• Observer variability can influence clinical decisions regarding tooth extraction.

Purpose of the Study:

• To develop an artificial intelligence (AI)-based decision support model for evaluating permanent first molar extraction indications in pediatric patients using panoramic radiographs.
• To assess the contribution of this AI model to clinical decision-making processes.

Main Methods:

• A retrospective study analyzed 176 panoramic radiographs from children aged 8-10 years, staged using the Demirjian system.
• Image features were extracted using Gabor filters and Histogram of Oriented Gradients (HOG).
• A Support Vector Machine (SVM) classifier with a radial basis function (RBF) kernel was employed for classification.

Main Results:

• The AI model achieved 77.78% accuracy and an Area Under the Curve (AUC) of 0.77.
• Sensitivity for the extraction-indicated group was 0.81, with an F1-score of 0.79.
• Sensitivity for the non-indicated group was 0.74, with an F1-score of 0.77.

Conclusions:

• AI analysis of panoramic radiographs offers an objective and reproducible method for evaluating extraction indications in pediatric first molars.
• The AI model serves as an adjunctive tool to reduce observer variability, not replace clinical judgment.
• Further validation through multicenter and multi-parametric studies is recommended to confirm clinical applicability.