Machine Learning and Artificial Intelligence: A Web-Based Implant Failure and Peri-implantitis Prediction Model for...

Area of Science:

• Biomedical Engineering
• Data Science in Dentistry
• Oral and Maxillofacial Surgery

Background:

• Dental implant success rates are high, but complications like failure and peri-implantitis can occur.
• Predictive tools are needed to identify patients at risk and optimize treatment outcomes.

Purpose of the Study:

• To develop and validate a machine learning (ML) model for predicting dental implant failure.
• To develop and validate an ML model for predicting peri-implantitis.
• To enhance overall dental implant success rates through predictive analytics.

Main Methods:

• Retrospective analysis of 942 dental implants from 398 patients (2006-2013).
• Supervised learning models including logistic regression, random forest, support vector machines, and ensemble techniques were utilized.
• Model performance was evaluated using receiver operating characteristic area under the curves (ROC AUC).

Main Results:

• The random forest model achieved the highest predictive accuracy.
• ROC AUC for implant failure prediction was 0.872.
• ROC AUC for peri-implantitis prediction was 0.840.
• Top predictors for implant failure: local anesthetic amount, implant length/diameter, preoperative antibiotics, hygiene frequency.
• Top predictors for peri-implantitis: implant length/diameter, preoperative antibiotics, hygiene frequency, diabetes mellitus.

Conclusions:

• Machine learning models can effectively predict dental implant failure and peri-implantitis.
• Demographics, medical history, and surgical factors significantly influence implant outcomes.
• The developed ML model can serve as a valuable clinical resource for improving dental implant treatment planning and success.