• Predicting treatment pathways...

*Result*: Predicting treatment pathways in Class II malocclusion patients using machine learning: A comparative study of four algorithms for classifying camouflage, growth modulation, and surgical decisions.

Title:
Predicting treatment pathways in Class II malocclusion patients using machine learning: A comparative study of four algorithms for classifying camouflage, growth modulation, and surgical decisions.
Authors:
Kumar M; Department of Orthodontics and Dentofacial Orthopaedics, Teerthanker Mahaveer Dental College & Research centre, Teerthanker Mahaveer University, Moradabad, Uttar Pradesh, India., Kumar S; Department of Orthodontics and Dentofacial Orthopaedics, Teerthanker Mahaveer Dental College & Research centre, Teerthanker Mahaveer University, Moradabad, Uttar Pradesh, India., Agarwal M; Department of Orthodontics and Dentofacial Orthopaedics, Teerthanker Mahaveer Dental College & Research centre, Teerthanker Mahaveer University, Moradabad, Uttar Pradesh, India. Electronic address: malvika.ortho@gmail.com., Yadav E; Department of Orthodontics and Dentofacial Orthopaedics, Teerthanker Mahaveer Dental College & Research centre, Teerthanker Mahaveer University, Moradabad, Uttar Pradesh, India., Gandi S; Department of Orthodontics and Dentofacial Orthopaedics, Teerthanker Mahaveer Dental College & Research centre, Teerthanker Mahaveer University, Moradabad, Uttar Pradesh, India. Electronic address: sougandhikagandi@gmail.com.
Source:
International orthodontics [Int Orthod] 2026 Mar; Vol. 24 (1), pp. 101070. Date of Electronic Publication: 2025 Oct 03.
Publication Type:
Journal Article; Comparative Study
Language:
English
Journal Info:
Publisher: Masson Country of Publication: France NLM ID: 101184882 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1879-680X (Electronic) Linking ISSN: 17617727 NLM ISO Abbreviation: Int Orthod Subsets: MEDLINE
Imprint Name(s):
Original Publication: Paris : Masson, c2003-
MeSH Terms:
Malocclusion, Angle Class II*/therapy , Malocclusion, Angle Class II*/surgery , Machine Learning* , Algorithms* , Clinical Decision-Making*, Humans ; Female ; Male ; Support Vector Machine ; Decision Trees ; Reproducibility of Results ; Child ; Adolescent ; Logistic Models
Contributed Indexing:
Keywords: Artificial intelligence; Class II malocclusion; Decision-making; Machine-learning algorithms; Treatment planning
Entry Date(s):
Date Created: 20251004 Date Completed: 20260221 Latest Revision: 20260221
Update Code:
20260222
DOI:
10.1016/j.ortho.2025.101070
PMID:
41045594
Database:
MEDLINE

*Further Information*

*Objectives: The aim of this study was to develop a machine-learning model to assist in treatment decision-making for surgery, camouflage, and growth modulation in Class II malocclusion patients and to evaluate its validity and reliability.
Material and Methods: A total of 506 Class II malocclusion patients were included in the study, with patients randomly assigned to a training set (405) and a test set (101). Four machine-learning (ML) models - logistic regression (LR), decision tree (DT), random forest (RF), and support vector machine (SVM) - were trained to predict the most suitable treatment approach: camouflage, growth modulation (GM), or surgery. The accuracy of treatment decisions was evaluated for each model, along with 95% confidence intervals (CIs). Additionally, the McNemar's test was used to assess the statistical significance of model performance.
Results: The AUC-PR values indicate that SVM and RF are the best-performing models, both achieving 1.00 for GM, 0.92 for camouflage, and 0.82 for surgery, demonstrating strong classification capabilities across all classes. LR performs well for GM (0.97) but struggles with camouflage and surgery (both 0.66), indicating inconsistencies. The DT has the lowest overall performance, with 0.62 for GM and camouflage, and 0.55 for surgery, suggesting weaker classification reliability. Given these results, SVM and RF emerge as the most effective models, offering the best balance of precision and recall across all classes.
Conclusions: Support vector machine and random forest demonstrate strong classification for growth modulation with high precision and recall, while camouflage remains stable until 80% recall before precision declines. Surgery involves greater trade-offs between precision and recall. This study further supports that ANB, Nasolabial angle, SNA, H angle, Age, Mandibular plane angle can be used as strong predictors in assessing patient's treatment needs.
(Copyright © 2025 CEO. Published by Elsevier Masson SAS. All rights reserved.)*

*Disclosure of interest The authors declare that they have no competing interest.*