Novel Machine Learning Algorithms for Prediction of Treatment Decisions in Adult Patients With Class III Malocclusion.

BACKGROUND

Management of Class III (Cl III) dentoskeletal phenotype is often expert-driven.

PURPOSE

The aim is to identify critical morphological features in postcircumpubertal Cl III treatment and appraise the predictive ability of innovative machine learning (ML) algorithms for adult Cl III malocclusion treatment planning.

STUDY DESIGN

The Orthodontics Department at the University of Illinois Chicago undertook a retrospective cross-sectional study analyzing Cl III malocclusion cases (2003-2020) through dental records and pretreatment lateral cephalograms.

PREDICTOR

Forty features were identified through a literature review and gathered from pretreatment records, serving as ML model inputs. Eight ML models were trained to predict the best treatment for adult Cl III malocclusion.

OUTCOME VARIABLE

Predictive accuracy, sensitivity, and specificity of the models, along with the highest-contributing features, were evaluated for performance assessment.

COVARIATES

Demographic covariates, including age, gender, race, and ethnicity, were assessed. Inclusion criteria targeted patients with cervical vertebral maturation stage 4 or above. Operative covariates such as tooth extraction and types of orthognathic surgical maneuvers were also analyzed.

ANALYSES

Demographic characteristics of the camouflage and surgical study groups were described statistically. Shapiro-Wilk Normality test was employed to check data distribution. Differences in means between groups were evaluated using parametric and nonparametric independent sample tests, with statistical significance set at <0.05.

RESULTS

The study involved 182 participants; 65 underwent camouflage mechanotherapy, and 117 received orthognathic surgery. No statistical differences were found in demographic characteristics between the two groups (P > .05). Extreme values of pretreatment parameters suggested a surgical approach. Artificial neural network algorithms predicted treatment approach with 91% accuracy, while the Extreme Gradient Boosting model achieved 93% accuracy after recursive feature elimination optimization. The Extreme Gradient Boosting model highlighted Wit's appraisal, anterior overjet, and Mx/Md ratio as key predictors.

CONCLUSIONS

The research identified significant cephalometric differences between Cl III adults requiring orthodontic camouflage or surgery. A 93% accurate artificial intelligence model was formulated based on these insights, highlighting the potential role of artificial intelligence and ML as adjunct tools in orthodontic diagnosis and treatment planning. This may assist in minimizing clinician subjectivity in borderline cases.