Abstract
Objective: To synthesize the available evidence on the diagnostic performance of artificial intelligence for sagittal skeletal classification using lateral cephalometric radiographs and to identify methodological limitations affecting clinical translation. Methods: PubMed, Embase, Scopus, and Web of Science were searched up to July 13, 2025, following PRISMA guidelines. Eligible studies used artificial intelligence to classify skeletal Class I, II, and III relationships from lateral cephalograms and reported diagnostic perfor- mance metrics. Non-image-based models, landmarking- only studies, commercial software evaluations, and non- original reports were excluded. Risk of bias was assessed using QUADAS-2. Exploratory random-effects meta- analyses using restricted maximum likelihood were per- formed, with subgroup analyses by skeletal class. Because of the small number of eligible studies, heterogeneity, and multiple model-level results from shared data sets, pooled estimates were interpreted cautiously. Results: Ninety-one records were screened, 12 underwent full-text review, four met the inclusion criteria, and three were included in quantitative synthesis, comprising an effective test sample of 2,743 across nine model arms. One study was excluded from pooling because it used combined posteroanterior and lateral inputs with best- fold reporting, limiting comparability. The pooled mul- ticlass performance showed sensitivity of 87.0%, speci- ficity of 91.1%, accuracy of 85.3%, and area under the receiver operating characteristic curve of 0.94. DenseNet- based models generally showed the strongest perfor- mance, whereas the Swin-T transformer model showed the weakest performance. QUADAS-2 indicated low to moderate risk of bias, with major concerns related to single-center sampling and lack of external validation. Conclusions: Artificial intelligence shows promising diagnostic performance for sagittal skeletal classification from lateral cephalograms. However, the current evi- dence remains limited, heterogeneous, and mainly single center. Therefore, pooled estimates should be considered exploratory rather than definitive indicators of clinical performance.Keywords
Artificial intelligence; Cephalometry; Deep learning; Diagnosis; Orthodontics � 2026 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Full article
How to cite
Mahmood Dashti, Farshad Khosraviani, Sara Esmaeili, Niloofar Ghadimi, Kaan Orhan, Atieh Meyari, Zohaib Khurshid; Falk Schwendicke k a Dentofacial Deformities Research Center, Research Institute of Dental Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran. (2026). Artificial intelligence for skeletal classification in orthodontics: A systematic review and meta-analysis of lateral cephalometric studies. Journal of Taibah University Medical Sciences, Volume 21, Issue 4, 683–697. DOI: 10.1016/j.jtumed.2026.06.003.
Recommended articles
Iron deficiency in pregnancy: fetal Doppler changes before anaemia and ferric carboxymaltose versus iron sucrose in primary care
Gulnoza T. Djuraeva, Dilbar K. Najmutdinova, Bakhrom M. Mamatkulov, Iroda Kamilova, Mokhira Sidikkhodjaeva, Umida Sadullaeva
Journal of Taibah University Medical Sciences · November 2026
Urolithiasis in military personnel: diagnosis, endourological treatment and return to duty
Gulomiddin A. Odinayev
Journal of Taibah University Medical Sciences · October 2026
Vitamin D status, dose-differentiated cholecalciferol and the structural response of the skin in women with premature skin ageing: a prospective single-centre study
Gulnara S. Babakulova, Ulugbek Yu. Sabirov
Journal of Taibah University Medical Sciences · November 2026
Anogenital papillomavirus infection in military personnel: epidemiology, surgical treatment and follow-up
Akmal M. Fayziev
Journal of Taibah University Medical Sciences · October 2026

