Integrating machine learning for treatment decisions in anterior open bite orthodontic cases: A retrospective study.

Abstract

Introduction: This article explores the integration of machine learning (ML) algorithms to aid in treatment planning and extraction decisions for anterior open bite cases, leveraging demographic, clinical, and radiographic data to predict treatment outcomes and informed decision-making.

Materials and methods: A retrospective study was conducted using patient data from the University of Illinois Chicago Department of Orthodontics. Data included demographic, clinical, and radiographic information from 115 anterior open bite patients who successfully completed their treatment. ML algorithms, including random forest, support vector machine, k-nearest neighbor, and convolutional neural networks (CNN), were trained on a subset of the data to predict treatment outcomes.

Results: Significant differences were observed in the percentages of males and females between the extraction and nonextraction groups and cephalometric variables between the two groups, which include maxillary depth, maxillary height, SN-palatal plane, facial angle, facial axis-Ricketts, FMA, total facial height, lower facial height, SNA, SNB, and SN-MP e ML algorithms examined consisted of CNN2, CNN1, and Random Forest, which demonstrated the highest accuracy rates (∼83%), while k-Nearest Neighbor had the lowest (∼73%). Key features influencing accuracy included crowding, SN-palatal plane, SNA, FMA, molar relation, and facial height measurements.

Conclusions: The study's evaluation of AI algorithms showed that CNN2, CNN1, and random forest had an accuracy of approximately 83% in classifying extraction versus nonextraction cases. Notably, features such as U-crowding, L-crowding, SN-palatal plane, SNA, FMA, molar relation, total facial height, lower facial height, and facial axis-Ricketts were most influential in achieving accuracy rates comparable to traditional methods.