Related Experiment Video
Updated: Jan 13, 2026
A Postoperative Evaluation Guideline for Computer-Assisted Reconstruction of the Mandible
Published on: January 28, 2020
Machine learning models for predicting postoperative complications following mandibular third molar surgery:
1Department of Oral and Maxillofacial Surgery, Geetanjali Dental and Research Institute, Geetanjali University, Eklingpura, 313001, Udaipur, Rajasthan, India; Department of Dental Research Cell, Dr. D. Y. Patil Dental College and Hospital, Dr. D. Y. Patil Vidyapeeth, Pimpri, 411018, Pune, Maharashtra, India; Department of Oral and Maxillofacial Surgery, Narsinhbhai Patel Dental College and Hospital, Sankalchand Patel University, Visnagar, 384315, Gujarat, India.
Machine learning models can predict complications from impacted mandibular third molar surgery. Factors like surgical duration and operator experience significantly influence outcomes, improving risk assessment.
Area of Science:
- Oral and Maxillofacial Surgery
- Artificial Intelligence in Medicine
- Predictive Analytics
Background:
- Surgical removal of impacted mandibular third molars is common but linked to significant postoperative morbidity.
- Current methods for assessing surgical difficulty primarily use radiographic and positional factors, neglecting intraoperative and operator influences.
Purpose of the Study:
- To develop and validate machine learning (ML) models for predicting postoperative complications following mandibular third molar extraction.
- To identify key predictors of complications using explainable AI.
Main Methods:
- A retrospective cohort study of 472 mandibular third molar extractions.
- Inclusion of demographic, radiographic, and intraoperative variables.
- Comparison of five ML algorithms, including Random Forest, XGBoost, and logistic regression, using AUC for performance evaluation.
Main Results:
- Random Forest (AUC 0.91) and XGBoost (AUC 0.89) showed superior predictive performance over logistic regression (AUC 0.74).
- Explainable AI (SHAP) identified surgical duration, impaction type, root morphology, operator experience, and bone guttering as significant predictors.
- The models effectively predicted outcomes such as pain, swelling, trismus, infection, and paraesthesia.
Conclusions:
- Machine learning, particularly with explainable AI, offers enhanced, individualized risk stratification for third molar surgery compared to traditional methods.
- These ML models can support clinical decision-making, patient counseling, and surgical training.
- Further prospective, multicenter validation is warranted to confirm generalizability.
