{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T17:56:39Z","timestamp":1793382999957,"version":"4.5.0"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Bioeng. Biotechnol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>The study aims to predict tooth extraction decision based on four machine learning methods and analyze the feature contribution, so as to shed light on the important basis for experts of tooth extraction planning, providing reference for orthodontic treatment planning.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study collected clinical information of 192 patients with malocclusion diagnosis and treatment plans. This study used four machine learning strategies, including decision tree, random forest, support vector machine (SVM) and multilayer perceptron (MLP) to predict orthodontic extraction decisions on clinical examination data acquired during initial consultant containing Angle classification, skeletal classification, maxillary and mandibular crowding, overjet, overbite, upper and lower incisor inclination, vertical growth pattern, lateral facial profile. Among them, 30% of the samples were randomly selected as testing sets. We used five-fold cross-validation to evaluate the generalization performance of the model and avoid over-fitting. The accuracy of the four models was calculated for the training set and cross-validation set. The confusion matrix was plotted for the testing set, and 6 indicators were calculated to evaluate the performance of the model. For the decision tree and random forest models, we observed the feature contribution.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The accuracy of the four models in the training set ranges from 82% to 90%, and in the cross-validation set, the decision tree and random forest had higher accuracy. In the confusion matrix analysis, decision tree tops the four models with highest accuracy, specificity, precision and F1-score and the other three models tended to classify too many samples as extraction cases. In the feature contribution analysis, crowding, lateral facial profile, and lower incisor inclination ranked at the top in the decision tree model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Among the machine learning models that only use clinical data for tooth extraction prediction, decision tree has the best overall performance. For tooth extraction decisions, specifically, crowding, lateral facial profile, and lower incisor inclination have the greatest contribution.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fbioe.2024.1483230","type":"journal-article","created":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:51:30Z","timestamp":1728867090000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Evaluation of four machine learning methods in predicting orthodontic extraction decision from clinical examination data and analysis of feature contribution"],"prefix":"10.3389","volume":"12","author":[{"given":"Jialiang","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ian-Tong","family":"Chan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhixian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyi","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Congchong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichen","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,10,14]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.isprsjprs.2016.01.011","article-title":"Random forest in remote sensing: a review of applications and future directions","volume":"114","author":"Belgiu","year":"2016","journal-title":"Isprs J. Photogramm."},{"key":"B2","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/s0889-5406(95)70127-3","article-title":"The morphologic basis for the extraction decision in Class II, division 1 malocclusions: a comparative study","volume":"107","author":"Bishara","year":"1995","journal-title":"Am. J. Orthod. Dentofac. Orthop."},{"key":"B3","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1016\/s0889-5406(03)00448-7","article-title":"Long-term stability of Class I premolar extraction treatment","volume":"124","author":"Boley","year":"2003","journal-title":"Am. J. Orthod. Dentofac. Orthop."},{"key":"B4","doi-asserted-by":"publisher","first-page":"e171","DOI":"10.1016\/j.ajodo.2011.03.022","article-title":"Smile esthetics from patients\u2019 perspectives for faces of varying attractiveness","volume":"140","author":"Chang","year":"2011","journal-title":"Am. J. Orthod. Dentofac. Orthop."},{"key":"B5","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1016\/j.neucom.2017.08.035","article-title":"A simple plug-in bagging ensemble based on threshold-moving for classifying binary and multiclass imbalanced data","volume":"275","author":"Collell","year":"2018","journal-title":"Neurocomputing"},{"key":"B6","doi-asserted-by":"publisher","first-page":"102","DOI":"10.4041\/kjod.2022.52.2.102","article-title":"Use of automated artificial intelligence to predict the need for orthodontic extractions","volume":"52","author":"Del Real","year":"2022","journal-title":"Korean J. Orthod."},{"key":"B7","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1111\/ocr.12502","article-title":"Machine learning from clinical data sets of a contemporary decision for orthodontic tooth extraction","volume":"24","author":"Etemad","year":"2021","journal-title":"Orthod. Craniofac Res."},{"key":"B8","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1186\/s40510-014-0044-y","article-title":"Morphological characteristics influencing the orthodontic extraction strategies for Angle\u2019s class II division 1 malocclusions","volume":"15","author":"Guo","year":"2014","journal-title":"Prog. Orthod."},{"key":"B9","doi-asserted-by":"publisher","first-page":"82","DOI":"10.5005\/jp-journals-10005-1242","article-title":"Estimation of tooth size discrepancies among different malocclusion groups","volume":"7","author":"Hasija","year":"2014","journal-title":"Int. J. Clin. Pediatr. Dent."},{"key":"B10","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1016\/j.ajodo.2016.08.021","article-title":"Extraction frequencies at a university orthodontic clinic in the 21st century: demographic and diagnostic factors affecting the likelihood of extraction","volume":"151","author":"Jackson","year":"2017","journal-title":"Am. J. Orthod. Dentofac. Orthop."},{"key":"B11","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1186\/s40510-014-0067-4","article-title":"Stability of class II subdivision malocclusion treatment with 3 and 4 premolar extractions","volume":"15","author":"Janson","year":"2014","journal-title":"Prog. Orthod."},{"key":"B12","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1016\/s0889-5406(03)00449-9","article-title":"Stability of anterior open bite nonextraction treatment in the permanent dentition","volume":"124","author":"Janson","year":"2003","journal-title":"Am. J. Orthod. Dentofac. Orthop."},{"key":"B13","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1023\/a:1008987426876","article-title":"On the use of cross-validation to assess performance in multivariate prediction","volume":"10","author":"Jonathan","year":"2000","journal-title":"Statistics and Comput."},{"key":"B14","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.ajodo.2015.07.030","article-title":"New approach for the diagnosis of extractions with neural network machine learning","volume":"149","author":"Jung","year":"2016","journal-title":"Am. J. Orthod. Dentofac. Orthop."},{"key":"B15","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1007\/978-3-662-44415-3_30","article-title":"On cross-validation for MLP model evaluation","author":"Karkkainen","year":"2014","journal-title":"Int. Workshop Stat. Tech. Pattern Recognit."},{"key":"B16","doi-asserted-by":"publisher","first-page":"1318","DOI":"10.14219\/jada.archive.2008.0043","article-title":"Esthetics and smile characteristics from the layperson's perspective: a computer-based survey study","volume":"139","author":"Ker","year":"2008","journal-title":"J. Am. Dent. Assoc."},{"key":"B17","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1016\/j.jds.2020.05.022","article-title":"Scope and performance of artificial intelligence technology in orthodontic diagnosis, treatment planning, and clinical decision-making - a systematic review","volume":"16","author":"Khanagar","year":"2021","journal-title":"J. Dent. Sci."},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1111\/ocr.12811","article-title":"Evaluation of different machine learning algorithms for extraction decision in orthodontic treatment","author":"K\u00f6kt\u00fcrk","year":"2024","journal-title":"Orthod. Craniofac Res."},{"key":"B19","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1186\/2196-1042-14-47","article-title":"Extraction decision and identification of treatment predictors in Class I malocclusions","volume":"14","author":"Konstantonis","year":"2013","journal-title":"Prog. Orthod."},{"key":"B20","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1111\/ocr.12641","article-title":"Can we predict orthodontic extraction patterns by using machine learning?","volume":"26","author":"Leavitt","year":"2023","journal-title":"Orthod. Craniofac Res."},{"key":"B21","doi-asserted-by":"publisher","first-page":"2037","DOI":"10.1038\/s41598-018-38439-w","article-title":"Orthodontic treatment planning based on artificial neural networks","volume":"9","author":"Li","year":"2019","journal-title":"Sci. Rep."},{"key":"B22","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.17219\/acem\/138702","article-title":"Machine learning in orthodontics: challenges and perspectives","volume":"30","author":"Liu","year":"2021","journal-title":"Adv. Clin. Exp. Med."},{"key":"B23","doi-asserted-by":"publisher","first-page":"115","DOI":"10.23804\/ejpd.2020.21.02.05","article-title":"Worldwide prevalence of malocclusion in the different stages of dentition: a systematic review and meta-analysis","volume":"21","author":"Lombardo","year":"2020","journal-title":"Eur. J. Paediatr. Dent."},{"key":"B24","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1590\/2176-9451.20.1.052-058.oar","article-title":"Severe root resorption resulting from orthodontic treatment: prevalence and risk factors","volume":"20","author":"Mau\u00e9s","year":"2015","journal-title":"Dent. Press J. Orthod."},{"key":"B25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/dj11010001","article-title":"Machine learning predictive model as clinical decision support system in orthodontic treatment planning","volume":"11","author":"Prasad","year":"2022","journal-title":"Dent. J. (Basel)"},{"key":"B26","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1043\/0003-3219(1994)064<0407:FROEFA>2.0.CO;2","article-title":"Forty-year review of extraction frequencies at a university orthodontic clinic","volume":"64","author":"Proffit","year":"1994","journal-title":"Angle Orthod."},{"key":"B27","doi-asserted-by":"publisher","first-page":"24","DOI":"10.3760\/cma.j.cn115797-20211112-22105","article-title":"Analysis of craniofacial features of patients with skeletal Class II average angle deepoverjet in three different tooth extraction modes","volume":"29","author":"Su","year":"2022","journal-title":"Chin. J. Orthod."},{"key":"B28","doi-asserted-by":"publisher","first-page":"55","DOI":"10.3390\/bioengineering7020055","article-title":"Machine learning for the diagnosis of orthodontic extractions: a computational analysis using ensemble learning","volume":"7","author":"Suhail","year":"2020","journal-title":"Bioengineering"},{"key":"B29","doi-asserted-by":"publisher","first-page":"262","DOI":"10.2319\/111608-588.1","article-title":"Artificial neural network modeling for deciding if extractions are necessary prior to orthodontic treatment","volume":"80","author":"Xie","year":"2010","journal-title":"Angle Orthod."},{"key":"B30","doi-asserted-by":"publisher","first-page":"14","DOI":"10.3760\/cma.j.issn.1674-5760.2002.02.004","article-title":"Interclinician agreement on the decision of extraction or non-extraction orthodontic treatment","volume":"9","author":"Xu","year":"2002","journal-title":"Chin. J. Orthod."},{"key":"B31","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/s41664-018-0068-2","article-title":"On splitting training and validation set: a comparative study of cross-validation, bootstrap and systematic sampling for estimating the generalization performance of supervised learning","volume":"2","author":"Xu","year":"2018","journal-title":"J. Anal. Test."},{"key":"B32","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1016\/j.ajodo.2014.01.021","article-title":"Differences in facial profile and dental esthetic perceptions between young adults and orthodontists","volume":"145","author":"Yin","year":"2014","journal-title":"Am. J. Orthod. Dentofac. Orthop."}],"container-title":["Frontiers in Bioengineering and Biotechnology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2024.1483230\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:51:34Z","timestamp":1728867094000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2024.1483230\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":32,"alternative-id":["10.3389\/fbioe.2024.1483230"],"URL":"https:\/\/doi.org\/10.3389\/fbioe.2024.1483230","relation":{},"ISSN":["2296-4185"],"issn-type":[{"value":"2296-4185","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,14]]},"article-number":"1483230"}}