Direkt zum Inhalt

Paddenberg-Schubert, Eva ; Midlej, Kareem ; Krohn, Sebastian ; Kuchler, Erika ; Watted, Nezar ; Proff, Peter ; Iraqi, Fuad A.

Automated classification of skeletal malocclusion in German orthodontic patients

Paddenberg-Schubert, Eva, Midlej, Kareem, Krohn, Sebastian, Kuchler, Erika, Watted, Nezar, Proff, Peter und Iraqi, Fuad A. (2025) Automated classification of skeletal malocclusion in German orthodontic patients. Clinical Oral Investigations 29, S. 396.

Veröffentlichungsdatum dieses Volltextes: 06 Aug 2025 08:15
Artikel
DOI zum Zitieren dieses Dokuments: 10.5283/epub.77516


Zusammenfassung

Objectives: Precisely diagnosing skeletal class is mandatory for correct orthodontic treatment. Artificial intelligence (AI) could increase efficiency during diagnostics and contribute to automated workflows. So far, no AI-driven process can differentiate between skeletal classes I, II, and III in German orthodontic patients. This prospective cross-sectional study aimed to develop machine- and ...

Objectives:
Precisely diagnosing skeletal class is mandatory for correct orthodontic treatment. Artificial intelligence (AI) could increase efficiency during diagnostics and contribute to automated workflows. So far, no AI-driven process can differentiate between skeletal classes I, II, and III in German orthodontic patients. This prospective cross-sectional study aimed to develop machine- and deep-learning models for diagnosing their skeletal class based on the gold-standard individualised ANB of Panagiotidis and Witt.

Materials and methods:
Orthodontic patients treated in Germany contributed to the study population. Pre-treatment cephalometric parameters, sex, and age served as input variables. Machine-learning models performed were linear discriminant analysis (LDA), random forest (RF), decision tree (DT), K-nearest neighbours (KNN), support vector machine (SVM), Gaussian naïve Bayes (NB), and multi class logistic regression (MCLR). Furthermore, an artificial neural network (ANN) was conducted.

Results:
1277 German patients presented skeletal class I (48.79%), II (27.56%) and III (23.64%). The best machine-learning model, which considered all input parameters, was RF with 100% accuracy, with Calculated_ANB being the most important (0.429). The model with Calculated_ANB only achieved 100% accuracy (KNN), but ANB alone was inappropriate (71–76% accuracy). The ANN with all parameters and Calculated_ANB achieved 95.31% and 100% validation-accuracy, respectively.

Conclusions:
Machine- and deep-learning methods can correctly determine an individual’s skeletal class. Calculated_ANB was the most important among all input parameters, which, therefore, requires precise determination.

Clinical relevance:
The AI methods introduced may help to establish digital and automated workflows in cephalometric diagnostics, which could contribute to the relief of the orthodontic practitioner.



Beteiligte Einrichtungen


Details

DokumentenartArtikel
Titel eines Journals oder einer ZeitschriftClinical Oral Investigations
Verlag:Springer Nature Link
Band:29
Seitenbereich:S. 396
Datum5 August 2025
InstitutionenMedizin > Lehrstuhl für Kieferorthopädie
Identifikationsnummer
WertTyp
10.1007/s00784-025-06485-0DOI
Stichwörter / KeywordsSkeletal malocclusion · Artificial intelligence · Orthodontic diagnostics · Cephalometric analysis ·Individualized ANB · Orthodontic treatment planning
Dewey-Dezimal-Klassifikation600 Technik, Medizin, angewandte Wissenschaften > 610 Medizin
StatusVeröffentlicht
BegutachtetJa, diese Version wurde begutachtet
An der Universität Regensburg entstandenZum Teil
URN der UB Regensburgurn:nbn:de:bvb:355-epub-775162
Dokumenten-ID77516

Bibliographische Daten exportieren

Nur für Besitzer und Autoren: Kontrollseite des Eintrags

nach oben