{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,9]],"date-time":"2026-11-09T17:11:50Z","timestamp":1794244310572,"version":"4.9.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,4,13]],"date-time":"2025-04-13T00:00:00Z","timestamp":1744502400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,4,13]],"date-time":"2025-04-13T00:00:00Z","timestamp":1744502400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100005626","name":"Universit\u00e4t Regensburg","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005626","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>The precise and efficient diagnosis of an individual\u2019s skeletal class is necessary in orthodontics to ensure correct and stable treatment planning. However, it is difficult to efficiently determine the true skeletal class due to several correlations between various anatomic structures. The primary outcome of this prospective cross-sectional study was developing a machine learning model for classifying patients as skeletal class I and III. Furthermore, the investigation intended to compare cephalometric variables between skeletal class I and III as well as between age and sex-specific subgroups to analyse correlations between cephalometric parameters and to perform Principal Component Analysis (PCA) to identify the most important variables contributing to skeletal class I and III variances. This study was based on the pre-treatment lateral cephalograms of 509 German orthodontic patients diagnosed as skeletal class I (n\u2009=\u2009341) or III (n\u2009=\u2009168) according to the individualised ANB of Panagiotidis and Witt, following descriptive analyses of cephalometric parameters, correlation analyses followed by Principal Component Analysis (PCA) to identify key cephalometric variables. Machine learning models, including Random Forest (RF), Classification and Regression Trees (CART), k-nearest Neighbors (KNN), Linear Discriminant Analysis (LDA), Support Vector Machines (SVM), and Generalized Linear Model (GLM), were evaluated for accuracy. Within the same skeletal class, age influenced cephalometric parameters: in skeletal class I, adolescents presented a more horizontal pattern (PFH\/AFH, Gonial angle, NL-ML) and prominent mandible (SNB, SN-Pg) than children. In skeletal class III, the degree of sagittal discrepancy between jaw bases was most notable in adults (ANB: III_Age\u2009&gt;\u200921-III _14\u2009&lt;\u2009Age\u2009&lt;\u200920 \u2212\u00a01.78\u00b0). Comparing skeletal class I and III, the latter had more prognathic mandibles (SNB) and compensated incisors\u2019 inclination (proclination of the upper (+\u20091\/NA: 9.01\u00b0), retroinclination of the lower incisors (\u2212\u00a01\/ML: 8.99\u00b0). Among others, a correlation was found between the sagittal (degree of prognathism, SNB) and vertical (inclination, ML-NSL) orientation of the mandible (skeletal class I: p\u2009&lt;\u20090.001, \u03c1\u2009=\u2009\u2212\u00a00.742; skeletal class III: p\u2009&lt;\u20090.001, \u03c1\u2009=\u2009\u2212\u00a00.665). PCA revealed that the first four principal components explain 93% of the variance in skeletal class I\/III diagnosis and that these parameters had the most influence loading score on the first component-PFH\/AFH ratio (0.35), SNB angle (0.35), SN-Pg (0.37), and ML-NSL (\u2212\u00a00.35). Evaluating machine learning models, the general model, including all cephalometric parameters, age, and sex, resulted in perfect (1.00) accuracy and kappa scores compared to the gold standard Calculated_ANB with the model\u2019s RF and CART. In model 2 the amount of input variables was reduced (Wits, SNB only), but the accuracy (0.88), and kappa (0.73) were still good in the KNN model. In the last section of this study, we applied different machine learning classification models. We examined the ability of the parameters\u2014SNA, SNB, and ML-NSL angles to predict the classification as skeletal class I or III. The results demonstrated that the GLM model gained an accuracy of 0.99 (Accuracy\u2009=\u20090.99, Kappa\u2009=\u20090.97). The precise diagnosis of skeletal class I\/III can be simplified by applying the machine learning model GLM with the input variables SNA, SNB, and ML-NSL only. This stresses the importance of their correct identification. However, considering all skeletal classes, a larger population is needed to validate and generalize this approach.<\/jats:p>","DOI":"10.1038\/s41598-025-97717-6","type":"journal-article","created":{"date-parts":[[2025,4,13]],"date-time":"2025-04-13T16:01:01Z","timestamp":1744560061000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Machine learning models for improving the diagnosing efficiency of skeletal class I and III in German orthodontic patients"],"prefix":"10.1038","volume":"15","author":[{"given":"Eva","family":"Paddenberg-Schubert","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kareem","family":"Midlej","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Krohn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Agnes","family":"Schr\u00f6der","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Obaida","family":"Awadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samir","family":"Masarwa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Iqbal M.","family":"Lone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Osayd","family":"Zohud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Kirschneck","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nezar","family":"Watted","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Proff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fuad A.","family":"Iraqi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,13]]},"reference":[{"key":"97717_CR1","first-page":"115","volume":"21","author":"G Lombardo","year":"2020","unstructured":"Lombardo, G. et al. Worldwide prevalence of malocclusion in the different stages of dentition: A systematic review and meta-analysis. Eur. J. Paediatr. Dent. 21, 115\u2013122 (2020).","journal-title":"Eur. J. Paediatr. Dent."},{"key":"97717_CR2","doi-asserted-by":"publisher","first-page":"75","DOI":"10.4236\/ojepi.2012.24012","volume":"02","author":"DK Hardy","year":"2012","unstructured":"Hardy, D. K., Cubas, Y. P. & Orellana, M. F. Prevalence of angle class III malocclusion: A systematic review and meta-analysis. Open J. Epidemiol. 02, 75\u201382 (2012).","journal-title":"Open J. Epidemiol."},{"key":"97717_CR3","unstructured":"Riedel, R. A. The relation of maxillary structures to cranium in malocclusion and in normal occlusion. The Angle Orthodontist (1952)."},{"key":"97717_CR4","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1016\/0002-9416(84)90162-3","volume":"85","author":"W Hussels","year":"1984","unstructured":"Hussels, W. & Nanda, R. S. Analysis of factors affecting angle ANB. Am. J. Orthod. 85, 411\u2013423 (1984).","journal-title":"Am. J. Orthod."},{"key":"97717_CR5","doi-asserted-by":"crossref","unstructured":"Enlow, D. H., Moyers, R. E., Hunter, W. S. & Jr, J. M. A procedure for the analysis of intrinsic facial form and growth An equivalent-balance concept (1969).","DOI":"10.1016\/0002-9416(69)90254-1"},{"key":"97717_CR6","unstructured":"Solow, B. The patterns of craniofacial association. A morphological and methodological correlation factor analysis study on young male adults. Acta Odontol Scand (1966)."},{"key":"97717_CR7","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1007\/BF02163219","volume":"38","author":"G Panagiotidis","year":"1977","unstructured":"Panagiotidis, G. & Witt, E. Der individualisierte ANB-Winkel. Fortschr. Kieferorthop. 38, 408\u2013416 (1977).","journal-title":"Fortschr. Kieferorthop."},{"key":"97717_CR8","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1016\/0889-5406(88)90134-5","volume":"94","author":"S J\u00e4rvinen","year":"1988","unstructured":"J\u00e4rvinen, S. Relation of the Wits appraisal to the ANB angle: A statistical appraisal. Am. J. Orthod. Dentofacial Orthop. 94, 432\u2013435 (1988).","journal-title":"Am. J. Orthod. Dentofacial Orthop."},{"key":"97717_CR9","first-page":"165","volume":"50","author":"A Hasund","year":"1980","unstructured":"Hasund, A. & B\u00f6e, O. E. Floating norms as guidance for the position of the lower incisors. Angle Orthod. 50, 165\u2013168 (1980).","journal-title":"Angle Orthod."},{"key":"97717_CR10","unstructured":"Franchi, L. & Baccetti, T. Cephalometric floating norms for North American adults. The Angle \u2026 (1998)."},{"key":"97717_CR11","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1093\/oxfordjournals.ejo.a035988","volume":"11","author":"D Segner","year":"1989","unstructured":"Segner, D. Floating norms as a means to describe individual skeletal patterns. Eur. J. Orthod. 11, 214\u2013220 (1989).","journal-title":"Eur. J. Orthod."},{"key":"97717_CR12","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1093\/ejo\/16.5.401","volume":"16","author":"I Tollaro","year":"1994","unstructured":"Tollaro, I., Baccetti, T., Bassarelli, V. & Franchi, L. Class III malocclusion in the deciduous dentition: a morphological and correlation study. EORTHO 16, 401\u2013408 (1994).","journal-title":"EORTHO"},{"key":"97717_CR13","doi-asserted-by":"crossref","unstructured":"Pearson, K. On lines and planes of closest fit to systems of points in space. Phil Mag. 559\u201372 (1901).","DOI":"10.1080\/14786440109462720"},{"key":"97717_CR14","doi-asserted-by":"crossref","unstructured":"El-Dawlatly, M., Attia, K. H., Abdelghaffar, A. Y., Mostafa, Y. A. & Abd El-Ghafour, M. Preciseness of artificial intelligence for lateral cephalometric measurements. J. Orofac. Orthop. 85, 27\u201333 (2024).","DOI":"10.1007\/s00056-023-00459-1"},{"key":"97717_CR15","doi-asserted-by":"crossref","unstructured":"Dipalma, G. et al. Artificial intelligence and its clinical applications in orthodontics: A systematic review. Diagnostics (Basel) 13, (2023).","DOI":"10.3390\/diagnostics13243677"},{"key":"97717_CR16","doi-asserted-by":"publisher","first-page":"903","DOI":"10.2319\/022019-127.1","volume":"89","author":"J-H Park","year":"2019","unstructured":"Park, J.-H. et al. Automated identification of cephalometric landmarks: Part 1-Comparisons between the latest deep-learning methods YOLOV3 and SSD. Angle Orthod. 89, 903\u2013909 (2019).","journal-title":"Angle Orthod."},{"key":"97717_CR17","doi-asserted-by":"crossref","unstructured":"Zhao, L. et al. Machine learning algorithms for the diagnosis of class III malocclusions in children. Children (Basel) 11, (2024).","DOI":"10.3390\/children11070762"},{"key":"97717_CR18","doi-asserted-by":"crossref","unstructured":"Nan, L. et al. Automated sagittal skeletal classification of children based on deep learning. Diagnostics (Basel) 13, (2023).","DOI":"10.3390\/diagnostics13101719"},{"key":"97717_CR19","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1007\/s00784-024-05900-2","volume":"28","author":"K Midlej","year":"2024","unstructured":"Midlej, K. et al. Lateral cephalometric parameters among Arab skeletal classes II and III patients and applying machine learning models. Clin. Oral Investig. 28, 511 (2024).","journal-title":"Clin. Oral Investig."},{"key":"97717_CR20","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1038\/nmeth.4370","volume":"14","author":"M Krzywinski","year":"2017","unstructured":"Krzywinski, M. & Altman, N. Classification and regression trees. Nat. Methods 14, 757\u2013758 (2017).","journal-title":"Nat. Methods"},{"key":"97717_CR21","doi-asserted-by":"publisher","unstructured":"Hox, J. J. & Maas, C. J. M. Multilevel Analysis. In Encyclopedia of social measurement 785\u2013793 (Elsevier, 2005). https:\/\/doi.org\/10.1016\/B0-12-369398-5\/00560-0.","DOI":"10.1016\/B0-12-369398-5\/00560-0"},{"key":"97717_CR22","unstructured":"International Encyclopedia of Education. (Elsevier Science, 2010)."},{"key":"97717_CR23","doi-asserted-by":"publisher","first-page":"144","DOI":"10.4097\/kjae.2017.70.2.144","volume":"70","author":"SG Kwak","year":"2017","unstructured":"Kwak, S. G. & Kim, J. H. Central limit theorem: The cornerstone of modern statistics. Kor. J. Anesthes. 70, 144\u2013156 (2017).","journal-title":"Kor. J. Anesthes."},{"key":"97717_CR24","unstructured":"Kuhn, M. The caret package. (2011)."},{"key":"97717_CR25","unstructured":"Kuhn, M., Wing, J., Weston, S. & Williams, A. Package \u2018caret\u2019. The R  (2020)."},{"key":"97717_CR26","doi-asserted-by":"publisher","unstructured":"Cohen, J. Statistical power analysis for the behavioral sciences. 79\u201381 (Lawrence Erlbaum Associates, 1988). https:\/\/doi.org\/10.4324\/9780203771587.","DOI":"10.4324\/9780203771587"},{"key":"97717_CR27","doi-asserted-by":"publisher","first-page":"2839","DOI":"10.1016\/j.patcog.2015.03.009","volume":"48","author":"T-T Wong","year":"2015","unstructured":"Wong, T.-T. Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation. Pattern Recogn. 48, 2839\u20132846 (2015).","journal-title":"Pattern Recogn."},{"key":"97717_CR28","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1016\/0002-9416(84)90063-0","volume":"85","author":"SE Bishara","year":"1984","unstructured":"Bishara, S. E., Peterson, L. C. & Bishara, E. C. Changes in facial dimensions and relationships between the ages of 5 and 25 years. Am. J. Orthod. 85, 238\u2013252 (1984).","journal-title":"Am. J. Orthod."},{"key":"97717_CR29","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1016\/j.ajodo.2014.10.023","volume":"147","author":"SS Yoon","year":"2015","unstructured":"Yoon, S. S. & Chung, C.-H. Comparison of craniofacial growth of untreated Class I and Class II girls from ages 9 to 18 years: A longitudinal study. Am. J. Orthod. Dentofacial Orthop. 147, 190\u2013196 (2015).","journal-title":"Am. J. Orthod. Dentofacial Orthop."},{"key":"97717_CR30","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.ajodo.2003.03.008","volume":"125","author":"BK Ochoa","year":"2004","unstructured":"Ochoa, B. K. & Nanda, R. S. Comparison of maxillary and mandibular growth. Am. J. Orthod. Dentofacial Orthop. 125, 148\u2013159 (2004).","journal-title":"Am. J. Orthod. Dentofacial Orthop."},{"key":"97717_CR31","unstructured":"Alexander, A. E. Z., Jr, J. M. & Franchi, L. Semilongitudinal cephalometric study of craniofacial growth in untreated Class III malocclusion. Am J. (2009)."},{"key":"97717_CR32","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1053\/j.sodo.2007.05.006","volume":"13","author":"T Baccetti","year":"2007","unstructured":"Baccetti, T., Franchi, L. & McNamara, J. A. Growth in the untreated class III subject. Semin. Orthod. 13, 130\u2013142 (2007).","journal-title":"Semin. Orthod."},{"key":"97717_CR33","unstructured":"Baccetti, T., Reyes, B. C. & McNamara, J. A. Gender Differences in Class III Malocclusion. Angle Orthodontist (2005)."},{"key":"97717_CR34","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1016\/S0889-5406(05)81329-0","volume":"104","author":"H Mitani","year":"1993","unstructured":"Mitani, H., Sato, K. & Sugawara, J. Growth of mandibular prognathism after pubertal growth peak. Am. J. Orthod. Dentofacial Orthop. 104, 330\u2013336 (1993).","journal-title":"Am. J. Orthod. Dentofacial Orthop."},{"key":"97717_CR35","first-page":"446","volume":"48","author":"AS Aristide","year":"2022","unstructured":"Aristide, A. S., Dragomirescu, A.-O., Bencze, M.-A., B\u0103lut\u0103, A. & Ionescu, E. Vertical cephalometric characteristics in class III malocclusions. Curr. Health Sci. J. 48, 446\u2013453 (2022).","journal-title":"Curr. Health Sci. J."},{"key":"97717_CR36","doi-asserted-by":"crossref","unstructured":"Zawawi, K. H., Alsulaimani, F. F. & Al-Dharrab, A. A. Morphological features of Class I, II and III malocclusions of Saudi adolescents. Saudi J. (2021).","DOI":"10.1016\/j.sjbs.2021.03.026"},{"key":"97717_CR37","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1007\/s00056-021-00322-1","volume":"84","author":"E Paddenberg","year":"2023","unstructured":"Paddenberg, E., Proff, P. & Kirschneck, C. Floating norms for individualising the ANB angle and the WITS appraisal in orthodontic cephalometric analysis based on guiding variables. J. Orofac. Orthop. 84, 10\u201318 (2023).","journal-title":"J. Orofac. Orthop."},{"key":"97717_CR38","doi-asserted-by":"publisher","first-page":"792","DOI":"10.3390\/jcm14030792","volume":"14","author":"K Midlej","year":"2025","unstructured":"Midlej, K. et al. Clustering and machine learning models of skeletal class I and II parameters of Arab orthodontic patients. JCM 14, 792 (2025).","journal-title":"JCM"},{"key":"97717_CR39","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-023-02919-7","author":"Y Zhou","year":"2023","unstructured":"Zhou, Y. et al. Orthodontic craniofacial pattern diagnosis: Cephalometric geometry and machine learning. Med. Biol. Eng. Comput. https:\/\/doi.org\/10.1007\/s11517-023-02919-7 (2023).","journal-title":"Med. Biol. Eng. Comput."},{"key":"97717_CR40","doi-asserted-by":"crossref","unstructured":"Ni\u00f1o-Sandoval, T. C., Guevara Perez, S. V., Gonz\u00e1lez, F. A., Jaque, R. A. & Infante-Contreras, C. An automatic method for skeletal patterns classification using craniomaxillary variables on a Colombian population. Forensic Sci. Int. 261, 159e1\u2013159e6 (2016).","DOI":"10.1016\/j.forsciint.2015.12.025"},{"key":"97717_CR41","volume":"15","author":"S Rauniyar","year":"2023","unstructured":"Rauniyar, S., Jena, S., Sahoo, N., Mohanty, P. & Dash, B. P. Artificial intelligence and machine learning for automated cephalometric landmark identification: A meta-analysis previewed by a systematic review. Cureus 15, e40934 (2023).","journal-title":"Cureus"},{"key":"97717_CR42","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/s40510-021-00361-9","volume":"22","author":"YM Bichu","year":"2021","unstructured":"Bichu, Y. M. et al. Applications of artificial intelligence and machine learning in orthodontics: A scoping review. Prog. Orthod. 22, 18 (2021).","journal-title":"Prog. Orthod."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-97717-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-97717-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-97717-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,13]],"date-time":"2025-04-13T16:01:09Z","timestamp":1744560069000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-97717-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,13]]},"references-count":42,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["97717"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-97717-6","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,13]]},"assertion":[{"value":"3 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Informed consent was obtained from all subjects involved in the study, as shown in supplement # 2.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"All methods were carried out in accordance with relevant guidelines and regulations. According to current guidelines and following the Ethics Committee of the University of Regensburg ethics and regulations, the committee reviewed and approved this research project and study design with approval number 19-1596-101 (dated 13\/11\/2019).","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Institutional review board statement"}}],"article-number":"12738"}}