{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T13:11:59Z","timestamp":1789564319826,"version":"build-2803163510"},"reference-count":16,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"1","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>BACKGROUND:<\/jats:title>\n                    <jats:p>Treatment duration is a major factor influencing patient motivation, acceptance, and clinical workflow in orthodontics. Accurately estimating treatment length and identifying cases likely to finish very early or require extended time can significantly enhance treatment planning and patient communication. This study aimed to develop and compare machine learning (ML) models for predicting continuous orthodontic treatment duration and for classifying short-duration (\u226412 months) and long-duration (\u226530 months) treatments using a large, diverse clinical dataset.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>METHODS:<\/jats:title>\n                    <jats:p>\n                      A total of 10,553 completed orthodontic cases were extracted from 120,000 records in the FMBO database. Seventy percent of the data was used for training and 30% for testing. Seven regression algorithms (Linear Regression, OLS, Bagging, Random Forest, Gradient Boost, AdaBoost, XGBoost) were evaluated. Classification models (Logistic Regression, Random Forest, Gradient Boost, XGBoost, AdaBoost, Bagging) were developed to identify short and long treatments. Class imbalance was addressed using class weighting and optimized probability thresholds (0.24 for short, 0.16 for long). Model performance was assessed using MSE,\n                      <jats:italic toggle=\"yes\">R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      , precision, recall, F1-score, confusion matrices, and AUC. Explainability tools (feature importance, permutation importance, LIME) were applied to identify key predictors.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>RESULTS:<\/jats:title>\n                    <jats:p>\n                      The Gradient Boost Regression model demonstrated the strongest performance for continuous duration prediction (\n                      <jats:italic toggle=\"yes\">R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      = 0.387; MSE = 23.0). The most influential predictors across regression models were age at treatment start, extraction plan, facial convexity, skeletal pattern, overjet, and overbite. For short-duration classification, the Gradient Boost Classifier achieved an AUC of 0.867 (test set) with a recall of 0.630, a precision of 0.463, and F1 = 0.534 at the optimized threshold (0.24). Age at T1, upper incisor position (A1toAPoP), and molar position (A6toPTV) were the strongest contributors. For long-duration classification, the Random Forest Classifier achieved a test-set AUC of 0.793 with precision 0.437, recall 0.438, and F1 = 0.438 at the optimized threshold (0.16). Permutation importance identified lower incisor AP position (B1toAPoP), upper incisor AP position (A1toAPoP), overbite (IOB), and age at T1 as the most influential predictors.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>CONCLUSIONS:<\/jats:title>\n                    <jats:p>ML models demonstrated effective performance in predicting orthodontic treatment duration and in identifying fast- and slow-finishing cases. Key demographic, dental, and skeletal features\u2014particularly age, extraction plan, incisor AP position, and vertical\/incisal characteristics\u2014were consistently strong predictors. The integration of big data and ML provides a scalable approach to enhance orthodontic diagnosis, optimize scheduling, improve communication of expectations, and support individualized treatment planning. Future studies incorporating compliance, biomechanics, and 3D imaging may further strengthen prediction accuracy.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.4103\/jos.jos_186_25","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T13:01:23Z","timestamp":1789563683000},"update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":0,"title":["Artificial intelligence-powered prediction of orthodontic treatment duration: Identifying short and prolonged cases from a dataset of more than 10,000 patients"],"prefix":"10.4103","volume":"15","author":[{"given":"Mohammed H.","family":"Elnagar","sequence":"first","affiliation":[{"name":"Department of Orthodontics, College of Dentistry, University of Illinois Chicago, Chicago, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Allen Y.","family":"Pan","sequence":"additional","affiliation":[{"name":"Midwestern University, Downers Grove, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aryo","family":"Handono","sequence":"additional","affiliation":[{"name":"Telkom University, Bandung, West Java, Indonesia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Flavio","family":"Sanchez","sequence":"additional","affiliation":[{"name":"Department of Orthodontics, College of Dentistry, University of Illinois Chicago, Chicago, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sameh","family":"Talaat","sequence":"additional","affiliation":[{"name":"Department of Orthodontics, Faculty of Dental Medicine, Future University in Egypt, Cairo, Egypt"},{"name":"Department of Oral Technology, University of Bonn, Bonn, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christoph","family":"Bourauel","sequence":"additional","affiliation":[{"name":"Department of Oral Technology, University of Bonn, Bonn, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed","family":"Kaboudan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Shorouk Academy, El Shorouk, Egypt"},{"name":"DigiBrain4 Inc, Chicago, IL, USA"},{"name":"Foundation For Modern {BIO} Progressive Orthodontics, Colorado, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Budi","family":"Kusnoto","sequence":"additional","affiliation":[{"name":"Department of Orthodontics, College of Dentistry, University of Illinois Chicago, Chicago, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2026,9]]},"reference":[{"key":"R1-20260916","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/0889-5406(92)70013-Z","article-title":"The duration of orthodontic treatment","volume":"102","author":"Fink","year":"1992","journal-title":"Am J Orthod Dentofacial Orthop"},{"key":"R2-20260916","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1093\/ejo\/cjn018","article-title":"Factors affecting the duration of orthodontic treatment: A systematic review","volume":"30","author":"Mavreas","year":"2008","journal-title":"Eur J Orthod"},{"key":"R3-20260916","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1016\/j.ajodo.2015.09.020","article-title":"How long does treatment with fixed orthodontic appliances last? A systematic review","volume":"149","author":"Tsichlaki","year":"2016","journal-title":"Am J Orthod Dentofacial Orthop"},{"key":"R4-20260916","doi-asserted-by":"crossref","first-page":"57","DOI":"10.3126\/ojn.v9i2.28416","article-title":"Comparison of orthodontic treatment duration among extraction versus non extraction therapies","volume":"9","author":"Kafle","year":"2019","journal-title":"Orthod J Nepal"},{"key":"R5-20260916","doi-asserted-by":"crossref","first-page":"647","DOI":"10.5005\/jp-journals-10024-2313","article-title":"Effectiveness of the American board of orthodontics discrepancy index in predicting treatment time","volume":"19","author":"Aljehani","year":"2018","journal-title":"J Contemp Dent Pract"},{"key":"R6-20260916","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1016\/j.ajodo.2017.09.017","article-title":"Factors affecting treatment duration of labial inversely impacted maxillary central incisors","volume":"153","author":"Bhikoo","year":"2018","journal-title":"Am J Orthod Dentofacial Orthop"},{"key":"R7-20260916","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1186\/s40510-020-00334-4","article-title":"Duration of orthodontic treatment with fixed appliances in adolescents and adults: A systematic review with meta-analysis","volume":"21","author":"Abbing","year":"2020","journal-title":"Prog Orthod"},{"key":"R8-20260916","doi-asserted-by":"crossref","first-page":"1303","DOI":"10.3390\/jcm9051303","article-title":"Shortening of overall orthodontic treatment duration with low-intensity pulsed ultrasound (LIPUS)","volume":"9","author":"Kaur","year":"2020","journal-title":"J Clin Med"},{"key":"R9-20260916","doi-asserted-by":"crossref","first-page":"794","DOI":"10.2319\/012220-42.1","article-title":"Is there a relationship between mandibular cortical bone thickness and orthodontic treatment time?","volume":"90","author":"Landin-Ramos","year":"2020","journal-title":"Angle Orthod"},{"key":"R10-20260916","doi-asserted-by":"crossref","first-page":"783","DOI":"10.2319\/012020-39.1","article-title":"Evaluating the effects of functional orthodontic treatment on mandibular osseous structure using fractal dimension analysis of dental panoramic radiographs","volume":"90","author":"Cesur","year":"2020","journal-title":"Angle Orthod"},{"key":"R11-20260916","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1136\/svn-2017-000101","article-title":"Artificial intelligence in healthcare: Past, present and future","volume":"2","author":"Jiang","year":"2017","journal-title":"Stroke Vasc Neurol"},{"key":"R12-20260916","first-page":"p. 131","article-title":"Assessment of outcomes by using machine learning","author":"Venugopalan","year":"2021","journal-title":"Machine Learning in Dentistry. Springer International Publishing"},{"key":"R13-20260916","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1053\/j.sodo.2021.05.012","article-title":"The validity of an artificial intelligence application for assessment of orthodontic treatment need from clinical images","volume":"27","author":"Talaat","year":"2021","journal-title":"Semin Orthod"},{"issue":"1","key":"R15-20260916","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.acra.2019.07.030","article-title":"Machine Learning Principles for Radiology Investigators","volume":"27","author":"Borstelmann","year":"2020","journal-title":"Acad Radiol"},{"key":"R16-20260916","first-page":"163","article-title":"Does patient age affect duration or success of orthodontic treatment?","volume":"74","author":"Vayda","year":"1995","journal-title":"J Dent Res"},{"key":"R17-20260916","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1016\/0889-5406(91)70092-B","article-title":"Age effects on orthodontic treatment: Adolescents contrasted with adults","volume":"100","author":"Dyer","year":"1991","journal-title":"Am J Orthod Dentofacial Orthop"}],"container-title":["Journal of Orthodontic Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.4103\/jos.jos_186_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T13:01:25Z","timestamp":1789563685000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.4103\/jos.jos_186_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":16,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.4103\/jos.jos_186_25","relation":{},"ISSN":["2278-1897","2278-0203"],"issn-type":[{"value":"2278-1897","type":"print"},{"value":"2278-0203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"2025-12-03","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-05","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}