Artificial Intelligence in Predicting Surgical Problems and Postoperative Morbidity in Mandibular Third Molar...

Area of Science:

• Oral Surgery
• Medical Imaging
• Artificial Intelligence

Background:

• Mandibular third molar (MTM) extractions are common oral surgeries with unpredictable outcomes.
• Surgical difficulty and postoperative complications can vary significantly.
• Artificial intelligence (AI) shows promise in improving preoperative planning for MTM extractions.

Purpose of the Study:

• To assess the effectiveness of AI in predicting surgical difficulty and postoperative morbidity associated with MTM extractions.
• To utilize cone-beam computed tomography (CBCT) data and patient variables for AI-driven predictions.
• To enhance preoperative planning for MTM extraction procedures.

Main Methods:

• A cross-sectional study involving 40 patients undergoing MTM extraction.
• Application of AI algorithms (random forest, convolutional neural networks) to analyze CBCT features and clinical data.
• Statistical analysis using SPSS version 26 to evaluate prediction accuracy.

Main Results:

• The AI model achieved 87.5% accuracy in predicting surgical difficulty.
• The AI model achieved 82.3% accuracy in predicting postoperative morbidity.
• Key predictors identified include root morphology, proximity to the inferior alveolar nerve, and patient age (P < 0.05).

Conclusions:

• AI-based predictive models are effective for assessing MTM extraction difficulty and postoperative morbidity.
• These AI models can significantly contribute to personalized treatment planning in oral surgery.
• Integrating AI with CBCT data offers a valuable tool for optimizing MTM extraction outcomes.