Evaluation of different machine learning algorithms for extraction decision in orthodontic treatment
Authors:
Open Access
- 20 May 2024
- journal article
- research article
- Published by Wiley in Orthodontics & Craniofacial Research
- Vol. 27 (S2) , 13-24
Abstract
Introduction: The extraction decision significantly affects the treatment process and outcome. Therefore, it is crucial to make this decision with a more objective and standardized method. The objectives of this study were (1) to identify the best‐performing model among seven machine learning (ML) models, which will standardize the extraction decision and serve as a guide for inexperienced clinicians, and (2) to determine the important variables for the extraction decision.Methods: This study included 1000 patients who received orthodontic treatment with or without extraction (500 extraction and 500 non‐extraction). The success criteria of the study were the decisions made by the four experienced orthodontists. Seven ML models were trained using 36 variables; including demographic information, cephalometric and model measurements. First, the extraction decision was performed, and then the extraction type was identified. Accuracy and area under the curve (AUC) of the receiver operating characteristics (ROC) curve were used to measure the success of ML models.Results: The Stacking Classifier model, which consists of Gradient Boosted Trees, Support Vector Machine, and Random Forest models, showed the highest performance in extraction decision with 91.2% AUC. The most important features determining extraction decision were maxillary and mandibular arch length discrepancy, Wits Appraisal, and ANS‐Me length. Likewise, the Stacking Classifier showed the highest performance with 76.3% accuracy in extraction type decisions. The most important variables for the extraction type decision were mandibular arch length discrepancy, Class I molar relationship, cephalometric overbite, Wits Appraisal, and L1‐NB distance.Conclusion: The Stacking Classifier model exhibited the best performance for the extraction decision. While ML models showed a high performance in extraction decision, they could not able to achieve the same level of performance in extraction type decision.Keywords
Funding Information
- Baskent Üniversitesi
This publication has 39 references indexed in Scilit:
- Machine learning and orthodontics, current trends and the future opportunities: A scoping reviewAmerican Journal of Orthodontics and Dentofacial Orthopedics, 2021
- Auto-WEKA: Automatic Model Selection and Hyperparameter Optimization in WEKA2019
- Arch-width changes in extraction vs nonextraction treatments in matched Class I borderline malocclusionsAmerican Journal of Orthodontics and Dentofacial Orthopedics, 2017
- Extraction frequencies at a university orthodontic clinic in the 21st century: Demographic and diagnostic factors affecting the likelihood of extractionAmerican Journal of Orthodontics and Dentofacial Orthopedics, 2017
- Esthetic perception of changes in facial profile resulting from orthodontic treatment with extraction of premolarsThe Journal of the American Dental Association, 2017
- Artificial intelligence expert systems with neural network machine learning may assist decision-making for extractions in orthodontic treatment planningJournal of Evidence-Based Dental Practice, 2016
- New approach for the diagnosis of extractions with neural network machine learningAmerican Journal of Orthodontics and Dentofacial Orthopedics, 2016
- Short-term effects of systematic premolar extraction on lip profile, vertical dimension and cephalometric parameters in borderline patients for extraction therapy—a retrospective cohort studyClinical Oral Investigations, 2015
- Arch-width and perimeter changes in patients with borderline Class I malocclusion treated with extractions or without extractions with air-rotor strippingAmerican Journal of Orthodontics and Dentofacial Orthopedics, 2010
- Profile changes of patients treated with and without premolar extractionsAmerican Journal of Orthodontics and Dentofacial Orthopedics, 2007