Dataset Information

Orthodontic Treatment Planning based on Artificial Neural Networks.

ABSTRACT: In this study, multilayer perceptron artificial neural networks are used to predict orthodontic treatment plans, including the determination of extraction-nonextraction, extraction patterns, and anchorage patterns. The neural network can output the feasibilities of several applicable treatment plans, offering orthodontists flexibility in making decisions. The neural network models show an accuracy of 94.0% for extraction-nonextraction prediction, with an area under the curve (AUC) of 0.982, a sensitivity of 94.6%, and a specificity of 93.8%. The accuracies of the extraction patterns and anchorage patterns are 84.2% and 92.8%, respectively. The most important features for prediction of the neural networks are "crowding, upper arch" "ANB" and "curve of Spee". For handling discrete input features with missing data, the average value method has a better complement performance than the k-nearest neighbors (k-NN) method; for handling continuous features with missing data, k-NN performs better than the other methods most of the time. These results indicate that the proposed method based on artificial neural networks can provide good guidance for orthodontic treatment planning for less-experienced orthodontists.

SUBMITTER: Li P

PROVIDER: S-EPMC6375961 | biostudies-literature | 2019 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Orthodontic Treatment Planning based on Artificial Neural Networks.

Li Peilin P Kong Deyu D Tang Tian T Su Di D Yang Pu P Wang Huixia H Zhao Zhihe Z Liu Yang Y

Scientific reports 20190214 1

In this study, multilayer perceptron artificial neural networks are used to predict orthodontic treatment plans, including the determination of extraction-nonextraction, extraction patterns, and anchorage patterns. The neural network can output the feasibilities of several applicable treatment plans, offering orthodontists flexibility in making decisions. The neural network models show an accuracy of 94.0% for extraction-nonextraction prediction, with an area under the curve (AUC) of 0.982, a se ...[more]

PMID: 30765756

Similar Datasets

Project description:BackgroundTraditionally, dental models, facial and intra-oral photographs and a set of two-dimensional radiographs are used for orthodontic diagnosis and treatment planning. As evidence is lacking, the discussion is ongoing which specific records are needed for the process of making an orthodontic treatment plan.ObjectiveTo estimate the contribution and importance of different diagnostic records for making an orthodontic diagnosis and treatment plan.Data sourcesAn electronic search in PubMed (1948-July 2012), EMBASE Excerpta Medica (1980-July 2012), CINAHL (1982-July 2012), Web of Science (1945-July 2012), Scopus (1996-July 2012), and Cochrane Library (1993-July 2012) was performed. Additionally, a hand search of the reference lists of included studies was performed to identify potentially eligible studies. There was no language restriction.Study selectionThe patient, intervention, comparator, outcome (pico) question formulated for this study was as follows: for patients who need orthodontic treatment (P), will the use of record set X (I) compared with record set Y (C) change the treatment plan (O)? Only primary publications were included.Data extractionIndependent extraction of data and quality assessment was performed by two observers.ResultsOf the 1041 publications retrieved, 17 met the inclusion criteria. Of these, 4 studies were of high quality. Because of the limited number of high quality studies and the differences in study designs, patient characteristics, and reference standard or index test, a meta-analysis was not possible.ConclusionCephalograms are not routinely needed for orthodontic treatment planning in Class II malocclusions, digital models can be used to replace plaster casts, and cone-beam computed tomography radiographs can be indicated for impacted canines. Based on the findings of this review, the minimum record set required for orthodontic diagnosis and treatment planning could not be defined.Systematic review registration numberCRD42012002365.

Dataset Information

Orthodontic Treatment Planning based on Artificial Neural Networks.

Publications

Orthodontic Treatment Planning based on Artificial Neural Networks.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets