{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T14:37:01Z","timestamp":1791211021904,"version":"4.1.0"},"reference-count":38,"publisher":"The Angle Orthodontist (EH Angle Education & Research Foundation)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To evaluate factors influencing the prediction error of artificial intelligence (AI) that predict craniofacial growth and to identify an optimal AI training condition to improve the predictive performance of the AI model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>Original growth data were collected from the Mathews longitudinal serial growth study. From the original data consisting of 1257 datasets from 33 growing children of northern European descent, 60 data subsets were generated using random resampling procedures to include 12, 18, and 24 subjects, with data sizes of 100, 200, 300, 400, and 500 datasets. The resampling procedures were repeated four times. Each subset was used to train and create a total of 60 AI models. The prediction accuracy of these models was evaluated using growth prediction errors at the lower lip landmark, labrale inferius, as a benchmark indicator. The prediction errors of the 60 AI models were analyzed according to the number of subjects and data sizes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Prediction error decreased as the data size increased. However, increasing the number of subjects within the growth data led to higher prediction errors. Notably, the increase in prediction error caused by adding more subjects was more substantial than the improvement achieved by increasing the data size.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The findings suggest that developing highly accurate AI-based craniofacial growth prediction models remains a significant challenge, even with extensive datasets.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2319\/031025-197.1","type":"journal-article","created":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:45:02Z","timestamp":1759106702000},"page":"106-113","source":"Crossref","is-referenced-by-count":2,"title":["Factors influencing the predictive performance of artificial intelligence for craniofacial growth"],"prefix":"10.2319","volume":"96","author":[{"given":"Naeun","family":"Kwon","sequence":"first","affiliation":[{"name":"Graduate Student (Ph.D.), Department of Orthodontics, Seoul National University, Seoul, Korea."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jong-Hak","family":"Kim","sequence":"additional","affiliation":[{"name":"Graduate Student (Ph.D.), Department of Orthodontics, Seoul National University, Seoul, Korea."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heeyeon","family":"Suh","sequence":"additional","affiliation":[{"name":"Assistant Professor, Department of Orthodontics, Arthur A. Dugoni School of Dentistry, University of the Pacific, San Francisco, CA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heesoo","family":"Oh","sequence":"additional","affiliation":[{"name":"Professor and Chair, Department of Orthodontics, Arthur A. Dugoni School of Dentistry, University of the Pacific, San Francisco, CA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shin-Jae","family":"Lee","sequence":"additional","affiliation":[{"name":"Professor, Department of Orthodontics; and Dental Research Institute, Seoul National University School of Dentistry, Seoul, Korea."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1164","reference":[{"key":"i1945-7103-96-1-106-b01","series-title":"Angle Orthod","first-page":"249","article-title":"Comparison of individualized facial growth prediction models using artificial intelligence and partial least squares based on the Mathews growth collection","volume":"95","author":"Roseth","year":"2025","unstructured":"Roseth J,\nKim JH,\nMoon JH, et al. Comparison of individualized facial growth prediction models using artificial intelligence and partial least squares based on the Mathews growth collection. Angle Orthod. 2025;95:249\u2013258."},{"key":"i1945-7103-96-1-106-b02","series-title":"Angle Orthod","first-page":"219","article-title":"Craniofacial growth prediction models based on cephalometric landmarks in Korean and American children","volume":"95","author":"Kim","year":"2025","unstructured":"Kim JH,\nMoon JH,\nRoseth J,\nSuh H,\nOh H,\nLee SJ. Craniofacial growth prediction models based on cephalometric landmarks in Korean and American children. Angle Orthod. 2025;95:219\u2013226."},{"key":"i1945-7103-96-1-106-b03","series-title":"Angle Orthod","first-page":"207","article-title":"Comparison of individualized facial growth prediction models based on the partial least squares and artificial intelligence","volume":"94","author":"Moon","year":"2024","unstructured":"Moon JH,\nShin HK,\nLee JM, et al. Comparison of individualized facial growth prediction models based on the partial least squares and artificial intelligence. Angle Orthod. 2024;94:207\u2013215."},{"key":"i1945-7103-96-1-106-b04","series-title":"Angle Orthod","first-page":"705","article-title":"Evaluation of an individualized facial growth prediction model based on the multivariate partial least squares method","volume":"92","author":"Moon","year":"2022","unstructured":"Moon JH,\nKim MG,\nHwang HW,\nCho SJ,\nDonatelli RE,\nLee SJ. Evaluation of an individualized facial growth prediction model based on the multivariate partial least squares method. Angle Orthod. 2022;92:705\u2013713."},{"key":"i1945-7103-96-1-106-b05","author":"AAOF craniofacial growth legacy collection","year":"2025","unstructured":"AAOF craniofacial growth legacy collection. 2025. https:\/\/www.aaoflegacycollection.org\/aaof_home.html. Accessed March, 2025."},{"key":"i1945-7103-96-1-106-b06","series-title":"Angle Orthod","first-page":"25","article-title":"The effect of vertical skeletal proportions on overbite changes in untreated adolescents: a longitudinal evaluation","volume":"94","author":"Ferrillo","year":"2024","unstructured":"Ferrillo M,\nPandis N,\nFleming PS. The effect of vertical skeletal proportions on overbite changes in untreated adolescents: a longitudinal evaluation. Angle Orthod. 2024;94:25\u201330."},{"issue":"Suppl 2","key":"i1945-7103-96-1-106-b07","series-title":"Orthod Craniofac Res","first-page":"6","article-title":"Factors influencing the development of artificial intelligence in orthodontics","volume":"27","author":"Lee","year":"2024","unstructured":"Lee JM,\nMoon JH,\nPark JA,\nKim JH,\nLee SJ. Factors influencing the development of artificial intelligence in orthodontics. Orthod Craniofac Res. 2024;27 Suppl 2:6\u201312."},{"key":"i1945-7103-96-1-106-b08","series-title":"Am J Orthod Dentofacial Orthop","first-page":"616","article-title":"Sample size calculation for an artificial intelligence study","volume":"167","author":"Kim","year":"2025","unstructured":"Kim JH,\nKwon N,\nPandis N,\nLee SJ. Sample size calculation for an artificial intelligence study. Am J Orthod Dentofacial Orthop. 2025;167:616\u2013620."},{"key":"i1945-7103-96-1-106-b09","series-title":"Angle Orthod","first-page":"823","article-title":"How much deep learning is enough for automatic identification to be reliable? A cephalometric example","volume":"90","author":"Moon","year":"2020","unstructured":"Moon JH,\nHwang HW,\nYu Y,\nKim MG,\nDonatelli RE,\nLee SJ. How much deep learning is enough for automatic identification to be reliable? A cephalometric example. Angle Orthod. 2020;90:823\u2013830."},{"key":"i1945-7103-96-1-106-b10","series-title":"J Korean Dent Sci","first-page":"12","article-title":"Sample size estimation for developing artificial intelligence to predict orthodontic treatment outcomes","volume":"18","author":"Kim","year":"2025","unstructured":"Kim JH,\nKwon N,\nLee SJ. Sample size estimation for developing artificial intelligence to predict orthodontic treatment outcomes. J Korean Dent Sci. 2025;18:12\u201319."},{"key":"i1945-7103-96-1-106-b11","series-title":"Angle Orthod","first-page":"467","article-title":"What amount of data is required to develop artificial intelligence that can accurately predict soft-tissue changes after orthognathic surgery","volume":"95","author":"Kim","year":"2025","unstructured":"Kim JH,\nKwon N,\nPark JA,\nYoun SB,\nSeo BM,\nLee SJ. What amount of data is required to develop artificial intelligence that can accurately predict soft-tissue changes after orthognathic surgery? Angle Orthod. 2025;95:467\u2013472."},{"key":"i1945-7103-96-1-106-b12","first-page":"6679","article-title":"TabNet: attentive interpretable tabular learning","volume":"35","author":"Arik","year":"2021","unstructured":"Arik S\u00d6,\nPfister T. TabNet: attentive interpretable tabular learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2021;35:6679\u20136687."},{"key":"i1945-7103-96-1-106-b13","series-title":"Am J Orthod Dentofacial Orthop","first-page":"272","article-title":"How to test validity in orthodontic research: a mixed dentition analysis example","volume":"147","author":"Donatelli","year":"2015","unstructured":"Donatelli RE,\nLee SJ. How to test validity in orthodontic research: a mixed dentition analysis example. Am J Orthod Dentofacial Orthop. 2015;147:272\u2013279."},{"key":"i1945-7103-96-1-106-b14","series-title":"Semin Orthod","first-page":"45","article-title":"Reliability statistics every orthodontist should know","volume":"30","author":"Moon","year":"2024","unstructured":"Moon JH,\nLee JM,\nPark JA,\nSuh H,\nLee SJ. Reliability statistics every orthodontist should know. Semin Orthod. 2024;30:45\u201349."},{"key":"i1945-7103-96-1-106-b15","series-title":"Orthod Craniofac Res","first-page":"38","article-title":"Growth patterns and overbite depth indicators of long and short faces in Korean adolescents: revisited through mixed-effects analysis","volume":"22","author":"Han","year":"2019","unstructured":"Han SH,\nPark YS. Growth patterns and overbite depth indicators of long and short faces in Korean adolescents: revisited through mixed-effects analysis. Orthod Craniofac Res. 2019;22:38\u201345."},{"key":"i1945-7103-96-1-106-b16","series-title":"IEEE Access","first-page":"36636","article-title":"Partial least squares regression trees for multivariate response data with multicollinear predictors","volume":"12","author":"Yu","year":"2024","unstructured":"Yu W,\nLee SJ,\nCho H. Partial least squares regression trees for multivariate response data with multicollinear predictors. IEEE Access. 2024;12:36636\u201336644."},{"key":"i1945-7103-96-1-106-b17","series-title":"Commun Stat Appl Methods","first-page":"65","article-title":"Modified partial least squares method implementing mixed-effect model","volume":"30","author":"Kim","year":"2023","unstructured":"Kim K,\nLee SJ,\nEo SH,\nCho SJ,\nLee JW. Modified partial least squares method implementing mixed-effect model. Commun Stat Appl Methods. 2023;30:65\u201373."},{"key":"i1945-7103-96-1-106-b18","series-title":"Angle Orthod","first-page":"549","article-title":"Does artificial intelligence predict orthognathic surgical outcomes better than conventional linear regression methods","volume":"94","author":"Park","year":"2024","unstructured":"Park JA,\nMoon JH,\nLee JM, et al. Does artificial intelligence predict orthognathic surgical outcomes better than conventional linear regression methods? Angle Orthod. 2024;94:549\u2013556."},{"key":"i1945-7103-96-1-106-b19","series-title":"Angle Orthod","first-page":"557","article-title":"Orthodontic treatment outcome predictive performance differences between artificial intelligence and conventional methods","volume":"94","author":"Cho","year":"2024","unstructured":"Cho SJ,\nMoon JH,\nKo DY, et al. Orthodontic treatment outcome predictive performance differences between artificial intelligence and conventional methods. Angle Orthod. 2024;94:557\u2013565."},{"key":"i1945-7103-96-1-106-b01","series-title":"Angle Orthod","first-page":"249","article-title":"Comparison of individualized facial growth prediction models using artificial intelligence and partial least squares based on the Mathews growth collection","volume":"95","author":"Roseth","year":"2025","unstructured":"Roseth J,\nKim JH,\nMoon JH, et al. Comparison of individualized facial growth prediction models using artificial intelligence and partial least squares based on the Mathews growth collection. Angle Orthod. 2025;95:249\u2013258."},{"key":"i1945-7103-96-1-106-b02","series-title":"Angle Orthod","first-page":"219","article-title":"Craniofacial growth prediction models based on cephalometric landmarks in Korean and American children","volume":"95","author":"Kim","year":"2025","unstructured":"Kim JH,\nMoon JH,\nRoseth J,\nSuh H,\nOh H,\nLee SJ. Craniofacial growth prediction models based on cephalometric landmarks in Korean and American children. Angle Orthod. 2025;95:219\u2013226."},{"key":"i1945-7103-96-1-106-b03","series-title":"Angle Orthod","first-page":"207","article-title":"Comparison of individualized facial growth prediction models based on the partial least squares and artificial intelligence","volume":"94","author":"Moon","year":"2024","unstructured":"Moon JH,\nShin HK,\nLee JM, et al. Comparison of individualized facial growth prediction models based on the partial least squares and artificial intelligence. Angle Orthod. 2024;94:207\u2013215."},{"key":"i1945-7103-96-1-106-b04","series-title":"Angle Orthod","first-page":"705","article-title":"Evaluation of an individualized facial growth prediction model based on the multivariate partial least squares method","volume":"92","author":"Moon","year":"2022","unstructured":"Moon JH,\nKim MG,\nHwang HW,\nCho SJ,\nDonatelli RE,\nLee SJ. Evaluation of an individualized facial growth prediction model based on the multivariate partial least squares method. Angle Orthod. 2022;92:705\u2013713."},{"key":"i1945-7103-96-1-106-b05","author":"AAOF craniofacial growth legacy collection","year":"2025","unstructured":"AAOF craniofacial growth legacy collection. 2025. https:\/\/www.aaoflegacycollection.org\/aaof_home.html. Accessed March, 2025."},{"key":"i1945-7103-96-1-106-b06","series-title":"Angle Orthod","first-page":"25","article-title":"The effect of vertical skeletal proportions on overbite changes in untreated adolescents: a longitudinal evaluation","volume":"94","author":"Ferrillo","year":"2024","unstructured":"Ferrillo M,\nPandis N,\nFleming PS. The effect of vertical skeletal proportions on overbite changes in untreated adolescents: a longitudinal evaluation. Angle Orthod. 2024;94:25\u201330."},{"issue":"Suppl 2","key":"i1945-7103-96-1-106-b07","series-title":"Orthod Craniofac Res","first-page":"6","article-title":"Factors influencing the development of artificial intelligence in orthodontics","volume":"27","author":"Lee","year":"2024","unstructured":"Lee JM,\nMoon JH,\nPark JA,\nKim JH,\nLee SJ. Factors influencing the development of artificial intelligence in orthodontics. Orthod Craniofac Res. 2024;27 Suppl 2:6\u201312."},{"key":"i1945-7103-96-1-106-b08","series-title":"Am J Orthod Dentofacial Orthop","first-page":"616","article-title":"Sample size calculation for an artificial intelligence study","volume":"167","author":"Kim","year":"2025","unstructured":"Kim JH,\nKwon N,\nPandis N,\nLee SJ. Sample size calculation for an artificial intelligence study. Am J Orthod Dentofacial Orthop. 2025;167:616\u2013620."},{"key":"i1945-7103-96-1-106-b09","series-title":"Angle Orthod","first-page":"823","article-title":"How much deep learning is enough for automatic identification to be reliable? A cephalometric example","volume":"90","author":"Moon","year":"2020","unstructured":"Moon JH,\nHwang HW,\nYu Y,\nKim MG,\nDonatelli RE,\nLee SJ. How much deep learning is enough for automatic identification to be reliable? A cephalometric example. Angle Orthod. 2020;90:823\u2013830."},{"key":"i1945-7103-96-1-106-b10","series-title":"J Korean Dent Sci","first-page":"12","article-title":"Sample size estimation for developing artificial intelligence to predict orthodontic treatment outcomes","volume":"18","author":"Kim","year":"2025","unstructured":"Kim JH,\nKwon N,\nLee SJ. Sample size estimation for developing artificial intelligence to predict orthodontic treatment outcomes. J Korean Dent Sci. 2025;18:12\u201319."},{"key":"i1945-7103-96-1-106-b11","series-title":"Angle Orthod","first-page":"467","article-title":"What amount of data is required to develop artificial intelligence that can accurately predict soft-tissue changes after orthognathic surgery","volume":"95","author":"Kim","year":"2025","unstructured":"Kim JH,\nKwon N,\nPark JA,\nYoun SB,\nSeo BM,\nLee SJ. What amount of data is required to develop artificial intelligence that can accurately predict soft-tissue changes after orthognathic surgery? Angle Orthod. 2025;95:467\u2013472."},{"key":"i1945-7103-96-1-106-b12","first-page":"6679","article-title":"TabNet: attentive interpretable tabular learning","volume":"35","author":"Arik","year":"2021","unstructured":"Arik S\u00d6,\nPfister T. TabNet: attentive interpretable tabular learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2021;35:6679\u20136687."},{"key":"i1945-7103-96-1-106-b13","series-title":"Am J Orthod Dentofacial Orthop","first-page":"272","article-title":"How to test validity in orthodontic research: a mixed dentition analysis example","volume":"147","author":"Donatelli","year":"2015","unstructured":"Donatelli RE,\nLee SJ. How to test validity in orthodontic research: a mixed dentition analysis example. Am J Orthod Dentofacial Orthop. 2015;147:272\u2013279."},{"key":"i1945-7103-96-1-106-b14","series-title":"Semin Orthod","first-page":"45","article-title":"Reliability statistics every orthodontist should know","volume":"30","author":"Moon","year":"2024","unstructured":"Moon JH,\nLee JM,\nPark JA,\nSuh H,\nLee SJ. Reliability statistics every orthodontist should know. Semin Orthod. 2024;30:45\u201349."},{"key":"i1945-7103-96-1-106-b15","series-title":"Orthod Craniofac Res","first-page":"38","article-title":"Growth patterns and overbite depth indicators of long and short faces in Korean adolescents: revisited through mixed-effects analysis","volume":"22","author":"Han","year":"2019","unstructured":"Han SH,\nPark YS. Growth patterns and overbite depth indicators of long and short faces in Korean adolescents: revisited through mixed-effects analysis. Orthod Craniofac Res. 2019;22:38\u201345."},{"key":"i1945-7103-96-1-106-b16","series-title":"IEEE Access","first-page":"36636","article-title":"Partial least squares regression trees for multivariate response data with multicollinear predictors","volume":"12","author":"Yu","year":"2024","unstructured":"Yu W,\nLee SJ,\nCho H. Partial least squares regression trees for multivariate response data with multicollinear predictors. IEEE Access. 2024;12:36636\u201336644."},{"key":"i1945-7103-96-1-106-b17","series-title":"Commun Stat Appl Methods","first-page":"65","article-title":"Modified partial least squares method implementing mixed-effect model","volume":"30","author":"Kim","year":"2023","unstructured":"Kim K,\nLee SJ,\nEo SH,\nCho SJ,\nLee JW. Modified partial least squares method implementing mixed-effect model. Commun Stat Appl Methods. 2023;30:65\u201373."},{"key":"i1945-7103-96-1-106-b18","series-title":"Angle Orthod","first-page":"549","article-title":"Does artificial intelligence predict orthognathic surgical outcomes better than conventional linear regression methods","volume":"94","author":"Park","year":"2024","unstructured":"Park JA,\nMoon JH,\nLee JM, et al. Does artificial intelligence predict orthognathic surgical outcomes better than conventional linear regression methods? Angle Orthod. 2024;94:549\u2013556."},{"key":"i1945-7103-96-1-106-b19","series-title":"Angle Orthod","first-page":"557","article-title":"Orthodontic treatment outcome predictive performance differences between artificial intelligence and conventional methods","volume":"94","author":"Cho","year":"2024","unstructured":"Cho SJ,\nMoon JH,\nKo DY, et al. Orthodontic treatment outcome predictive performance differences between artificial intelligence and conventional methods. Angle Orthod. 2024;94:557\u2013565."}],"container-title":["The Angle Orthodontist"],"original-title":[],"link":[{"URL":"https:\/\/angle-orthodontist.kglmeridian.com\/view\/journals\/angl\/96\/1\/article-p106.xml","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/angle-orthodontist.kglmeridian.com\/downloadpdf\/journals\/angl\/96\/1\/article-p106.xml","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/angle-orthodontist.kglmeridian.com\/downloadpdf\/journals\/angl\/96\/1\/article-p106.xml","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T14:14:42Z","timestamp":1780064082000},"score":1,"resource":{"primary":{"URL":"https:\/\/angle-orthodontist.kglmeridian.com\/view\/journals\/angl\/96\/1\/article-p106.xml"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":38,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.2319\/031025-197.1","relation":{},"ISSN":["1945-7103","0003-3219"],"issn-type":[{"value":"1945-7103","type":"electronic"},{"value":"0003-3219","type":"print"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}