EUVIMEDEUVIMED entdecken
Crossref

Predicting the Risk of Maxillary Canine Impaction Based on Maxillary Measurements Using Supervised Machine Learning

Cristiano Miranda de Araujo iD, Pedro Felipe de Jesus Freitas iD, Aline Xavier Ferraz iD, Patricia Kern Di Scala Andreis iD, Michelle Nascimento Meger iD, Flares Baratto-Filho iD, Cesar Augusto Rodenbusch Poletto iD, Erika Calvano Küchler iD, Elisa Souza Camargo iD, Angela Graciela Deliga Schroder iD

Orthodontics & Craniofacial Research · 2025-02 · 28 (1) · 207-215

DOI: 10.1111/ocr.12863 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Orthodontics & Craniofacial Research, online erschienen am 04.10.2024. Verfasst von Cristiano Miranda de Araujo und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Dentistry, Tuiuti University of Paraná, Curitiba, Paraná, Brazil. Hauptthemen laut MEDLINE: Cuspid, Maxilla, Tooth, Impacted, Supervised Machine Learning. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 22 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

To predict palatally impacted maxillary canines based on maxilla measurements through supervised machine learning techniques. Materials and Methods The maxilla images from 138 patients were analysed to investigate intermolar width, interpremolar width, interpterygoid width, maxillary length, maxillary width, nasal cavity width and nostril width, obtained through cone beam computed tomography scans. The predictive models were built using the following machine learning algorithms: Adaboost Classifier, Decision Tree, Gradient Boosting Classifier, K‐Nearest Neighbours (KNN), Logistic Regression, Multilayer Perceptron Classifier (MLP), Random Forest Classifier and Support Vector Machine (SVM). A 5‐fold cross‐validation approach was employed to validate each model. Metrics such as area under the curve (AUC), accuracy, recall, precision and F1 Score were calculated for each model, and ROC curves were constructed.

Results

The predictive model included four variables (two dental and two skeletal measurements). The interpterygoid width and nostril width showed the largest effect sizes. The Gradient Boosting Classifier algorithm exhibited the best metrics, with AUC values ranging from 0.91 [CI95% = 0.74–0.98] for test data to 0.89 [CI95% = 0.86–0.94] for crossvalidation. The nostril width variable demonstrated the highest importance across all tested algorithms.

Conclusion

The use of maxillary measurements, through supervised machine learning techniques, is a promising method for predicting palatally impacted maxillary canines. Among the models evaluated, both the Gradient Boosting Classifier and the Random Forest Classifier demonstrated the best performance metrics, with accuracy and AUC values exceeding 0.8, indicating strong predictive capability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CuspidMaxillaTooth, ImpactedSupervised Machine LearningCone-Beam Computed TomographyHumansMaleFemaleAdolescentChildAlgorithms

Stichwörter der Autor:innen

artificial intelligenceimpacted toothmachine learningmaxilla

Autor:innen und Institutionen

  • School of Dentistry, Tuiuti University of Paraná, Curitiba, Paraná, Brazil.
  • Postgraduate Program in Human Communication Health, Tuiuti University of Paraná, Curitiba, Paraná, Brazil.
  • Graduate Program in Dentistry, Department of Orthodontics, Pontifícia Universidade Católica Do Paraná, Curitiba, Brazil.
  • Graduate Program in Dentistry, Department of Dental Radiology, Centro Universitário Unifacvest, Curitiba, Brazil.
  • Department of Orthodontics, University Hospital Bonn, Medical Faculty, Bonn, Germany.
  • Graduate Program in Dentistry, Orthodontics, Pontifícia Universidade Católica Do Paraná, Curitiba, Brazil.

ORCID-Profile: Cristiano Miranda de Araujo, Pedro Felipe de Jesus Freitas, Aline Xavier Ferraz, Patricia Kern Di Scala Andreis, Michelle Nascimento Meger, Flares Baratto-Filho, Cesar Augusto Rodenbusch Poletto, Erika Calvano Küchler, Elisa Souza Camargo, Angela Graciela Deliga Schroder

Zitieren

APA

de Araujo, C. M., Freitas, P. F. J., Ferraz, A. X., Andreis, P. K. D. S., Meger, M. N., Baratto-Filho, F., Augusto Rodenbusch Poletto, C., Küchler, E. C., Camargo, E. S., & Schroder, A. G. D. (2025). Predicting the Risk of Maxillary Canine Impaction Based on Maxillary Measurements Using Supervised Machine Learning. Orthodontics & Craniofacial Research, 28(1), 207-215. https://doi.org/10.1111/ocr.12863

Vancouver

de Araujo CM, Freitas PFJ, Ferraz AX, Andreis PKDS, Meger MN, Baratto-Filho F, et al. Predicting the Risk of Maxillary Canine Impaction Based on Maxillary Measurements Using Supervised Machine Learning. Orthodontics & Craniofacial Research. 2025;28(1):207-215. doi:10.1111/ocr.12863

BibTeX
@article{deAraujo2025,
  author = {de Araujo, Cristiano Miranda and Freitas, Pedro Felipe de Jesus and Ferraz, Aline Xavier and Andreis, Patricia Kern Di Scala and Meger, Michelle Nascimento and Baratto-Filho, Flares and Augusto Rodenbusch Poletto, Cesar and Küchler, Erika Calvano and Camargo, Elisa Souza and Schroder, Angela Graciela Deliga},
  title = {Predicting the Risk of Maxillary Canine Impaction Based on Maxillary Measurements Using Supervised Machine Learning},
  journal = {Orthodontics & Craniofacial Research},
  year = {2025},
  volume = {28},
  number = {1},
  pages = {207--215},
  doi = {10.1111/ocr.12863}
}
Kostenlos starten →