Next Article in Journal
Semi-Quantitative ΔCt Thresholds for Bacteriuria and Pre-Analytic Drivers of PCR-Culture Discordance in Complicated UTI: An Analysis of NCT06996301
Previous Article in Journal
Recurrence, Readmission, and Key Mortality Predictors in Patients with Carbapenem-Resistant Enterobacterales Infections
Previous Article in Special Issue
Artificial Intelligence in the Diagnosis and Management of Atrial Fibrillation
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Diagnostics
Volume 15
Issue 23
10.3390/diagnostics15232958
diagnostics-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Evaluation of the Performance of an Artificial Intelligence-Based Classification Model for Pediatric Maxillofacial Morphology †

by
Hiroki Sato
1,
Akane Ueda
1,
Camila Tussie
2,
Sophie Kim
3,
Yukinori Kuwajima
1,
Emiko Kikuchi
1,
Shigemi Nagai
4 and
Kazuro Satoh
1,*
1
Division of Orthodontics, Department of Developmental Oral Health Science, School of Dentistry, Iwate Medical University, 1-3-27 Chuo-dori, Morioka 020-8505, Japan
2
Division of Orthodontics, Department of Developmental Biology, Harvard School of Dental Medicine, 188 Longwood Avenue, Boston, MA 02115, USA
3
Division of Orthodontics, Department of Regenerative and Reconstructive Sciences, UCLA School of Dentistry, 714 Tiverton, Los Angeles, CA 90095, USA
4
Department of Restorative Dentistry and Biomaterials Sciences, Harvard School of Dental Medicine, 188 Longwood Avenue, Boston, MA 02115, USA
*
Author to whom correspondence should be addressed.
†
This manuscript is a revised and expanded version of the poster presentation entitled “Classification of Maxillofacial Morphology in Japanese Children Using Artificial Intelligence and Verification of Accuracy,” which was presented at the 84th Annual Meeting of the Japanese Orthodontic Society, held in Sapporo, Japan, on 29 September–1 October 2025.
Diagnostics 2025, 15(23), 2958; https://doi.org/10.3390/diagnostics15232958
Submission received: 17 October 2025 / Revised: 13 November 2025 / Accepted: 13 November 2025 / Published: 21 November 2025
(This article belongs to the Special Issue Advancing Clinical Diagnosis with Artificial Intelligence: Applications, Challenges, and Future Directions)
Versions Notes

Abstract

Background/Objectives: Accurate assessment of craniofacial morphology is essential for orthodontic diagnosis and treatment planning. The Sassoni classification provides a useful framework for categorizing craniofacial morphology into nine groups but lacks standardized clinical criteria. This study developed an AI model to classify pediatric craniofacial morphology based on the Sassoni classification using lateral cephalometric radiographs and evaluated its agreement with classifications made by orthodontists. Methods: Data from 300 pediatric patients aged 6 to 10 years were analyzed. Nine cephalometric measurements and patient gender were used as input features. Three orthodontists classified morphology based on the Sassoni classification. Random forest (RF), logistic regression (LR), and support vector classification (SVC) models were trained and evaluated using 10-fold cross-validation. Results: The Random Forest (RF) model demonstrated the highest accuracy (RF: 0.907 ± 0.051, LR: 0.837 ± 0.057, SVC: 0.770 ± 0.055). It also outperformed the other two models in terms of F1 score, sensitivity, and positive predictive value, showing the best overall classification performance. The most influential feature was the ANB angle, while gender had minimal impact. Conclusions: The RF-based AI model demonstrated high accuracy in pediatric maxillofacial classification. Performance may be further improved with larger datasets and more balanced case distributions.
Keywords: maxillofacial morphology; artificial intelligence; random forest; pediatrics maxillofacial morphology; artificial intelligence; random forest; pediatrics

Share and Cite

MDPI and ACS Style

Sato, H.; Ueda, A.; Tussie, C.; Kim, S.; Kuwajima, Y.; Kikuchi, E.; Nagai, S.; Satoh, K. Evaluation of the Performance of an Artificial Intelligence-Based Classification Model for Pediatric Maxillofacial Morphology. Diagnostics 2025, 15, 2958. https://doi.org/10.3390/diagnostics15232958

AMA Style

Sato H, Ueda A, Tussie C, Kim S, Kuwajima Y, Kikuchi E, Nagai S, Satoh K. Evaluation of the Performance of an Artificial Intelligence-Based Classification Model for Pediatric Maxillofacial Morphology. Diagnostics. 2025; 15(23):2958. https://doi.org/10.3390/diagnostics15232958

Chicago/Turabian Style

Sato, Hiroki, Akane Ueda, Camila Tussie, Sophie Kim, Yukinori Kuwajima, Emiko Kikuchi, Shigemi Nagai, and Kazuro Satoh. 2025. "Evaluation of the Performance of an Artificial Intelligence-Based Classification Model for Pediatric Maxillofacial Morphology" Diagnostics 15, no. 23: 2958. https://doi.org/10.3390/diagnostics15232958

APA Style

Sato, H., Ueda, A., Tussie, C., Kim, S., Kuwajima, Y., Kikuchi, E., Nagai, S., & Satoh, K. (2025). Evaluation of the Performance of an Artificial Intelligence-Based Classification Model for Pediatric Maxillofacial Morphology. Diagnostics, 15(23), 2958. https://doi.org/10.3390/diagnostics15232958

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.
Back to TopTop