모바일 메뉴

KJO Korean Journal of Orthodontics

Open Access

pISSN 2234-7518
eISSN 2005-372X
QR Code QR Code

퀵메뉴 버튼

Article

home All Articles View
Split Viewer

Article In Press

Korean J Orthod

Published online October 14, 2021

Copyright © The Korean Association of Orthodontists.

USE OF AUTOMATED ARTIFICIAL INTELLIGENCE TO PREDICT THE ORTHODONTIC NEED OF EXTRACTIONS

Alberto Del Real1, Octavio Del Real2, Sebastian Sardina3, Rodrigo Oyonarte4

1 Former Resident, Graduate Orthodontic Program, Discipline of Orthodontics, Faculty of Odontology, Universidad de los Andes, Chile. Private Practice, Santiago, Chile. ajdelreal@miuandes.cl
2 Clinical Instructor, Graduate Orthodontic Program, Discipline of Orthodontics, Faculty of Odontology, Universidad de los Andes, Chile. Private Practice, Santiago, Chile. octavio@delreal.cl
3 Professor at School of Science (Computer Science), RMIT University, Australia. sebastian.sardina@rmit.edu.au
4 Full Professor and Chairman, Graduate Orthodontic Program, Discipline of Orthodontics, Faculty of Odontology, Universidad de los Andes, Chile. Private Practice, Santiago, Chile. royonarte@miuandes.cl

Correspondence to:Alberto Del Real
Discipline of Orthodontics, Faculty of Odontology, Universidad de los Andes, Mons. Alvaro del Portillo 12.455, Las Condes, Santiago, 7620086, Chile.
Phone: +56989032888
Email: ajdelreal@miuandes.cl

This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

Objective: To explore the capacity of an Automated Artificial Intelligence system for the prediction of the need of dental extractions in orthodontic treatments using gender, model variables and cephalometric records, and to develop extraction prediction models based on the aforementioned records.
Methods: Gender, model variables and radiographic records of 214 patients were obtained from an anonymized data bank containing 314 cases treated by two experienced orthodontists. The data was processed using an automated Machine Learning software (Auto-Weka) to predict the need of extractions based on gender, model and/or cephalometric records.
Results: By generating and comparing several extraction prediction models, an accuracy of 93.9% was achieved to determine whether or not a case requires extraction, based on model and radiographic data. When only model variables were used, an accuracy of 87.4% was attained, whereas 72.7% accuracy was achieved if only cephalometric information was used.
Conclusions: The use of an automated machine learning system allows the generation of orthodontic extraction prediction models. The accuracy of the optimal extraction prediction models increases as model and cephalometric data is provided for the analytical process.

Keywords: Extraction vs. nonextraction, Computer algorithm, Decision tree, Orthodontic Index.

Article

ahead

Korean J Orthod

Published online October 14, 2021

Copyright © The Korean Association of Orthodontists.

USE OF AUTOMATED ARTIFICIAL INTELLIGENCE TO PREDICT THE ORTHODONTIC NEED OF EXTRACTIONS

Alberto Del Real1, Octavio Del Real2, Sebastian Sardina3, Rodrigo Oyonarte4

1 Former Resident, Graduate Orthodontic Program, Discipline of Orthodontics, Faculty of Odontology, Universidad de los Andes, Chile. Private Practice, Santiago, Chile. ajdelreal@miuandes.cl
2 Clinical Instructor, Graduate Orthodontic Program, Discipline of Orthodontics, Faculty of Odontology, Universidad de los Andes, Chile. Private Practice, Santiago, Chile. octavio@delreal.cl
3 Professor at School of Science (Computer Science), RMIT University, Australia. sebastian.sardina@rmit.edu.au
4 Full Professor and Chairman, Graduate Orthodontic Program, Discipline of Orthodontics, Faculty of Odontology, Universidad de los Andes, Chile. Private Practice, Santiago, Chile. royonarte@miuandes.cl

Correspondence to:Alberto Del Real
Discipline of Orthodontics, Faculty of Odontology, Universidad de los Andes, Mons. Alvaro del Portillo 12.455, Las Condes, Santiago, 7620086, Chile.
Phone: +56989032888
Email: ajdelreal@miuandes.cl

This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

Objective: To explore the capacity of an Automated Artificial Intelligence system for the prediction of the need of dental extractions in orthodontic treatments using gender, model variables and cephalometric records, and to develop extraction prediction models based on the aforementioned records.
Methods: Gender, model variables and radiographic records of 214 patients were obtained from an anonymized data bank containing 314 cases treated by two experienced orthodontists. The data was processed using an automated Machine Learning software (Auto-Weka) to predict the need of extractions based on gender, model and/or cephalometric records.
Results: By generating and comparing several extraction prediction models, an accuracy of 93.9% was achieved to determine whether or not a case requires extraction, based on model and radiographic data. When only model variables were used, an accuracy of 87.4% was attained, whereas 72.7% accuracy was achieved if only cephalometric information was used.
Conclusions: The use of an automated machine learning system allows the generation of orthodontic extraction prediction models. The accuracy of the optimal extraction prediction models increases as model and cephalometric data is provided for the analytical process.

Keywords: Extraction vs. nonextraction, Computer algorithm, Decision tree, Orthodontic Index.