Photograph-Based Skeletal Malocclusion Screening with Geometric Machine Learning: External Validation Across Turkish and Non-European Cohorts
- 1Department of Orthodontics, Bezmialem Vakif University, Istanbul, Turkey, Kedi Mobil Uygulama Anonim Sirketi, Istanbul, Turkey
Abstract
A photograph based screening classifier for skeletal malocclusion maps 100 engineered geometric feature vectors, derived from a side-profile smartphone photograph, to orthodontic class labels, enabling non-invasive triage without radiographic imaging. This study reports external validation across two independent cohorts that contributed no cases to training. Two binary tasks were evaluated; Class III against non-Class III, and Class I against Class II; each with its own development set and model, applied without modification at the default threshold. One external cohort was Turkish, drawn from an institution not represented in the development set; the other was a non-European cohort from a Belgian private orthodontic clinic. Sensitivity, specificity and the area under the receiver operating characteristic curve (AUC) were pre-specified as primary outcome measures, since none depends on outcome prevalence. In the Class III task, sensitivity was similar across all three evaluation sets (0.801, 0.836, 0.848; all adjusted p>0.7), while specificity fell from 0.766 in the Turkish external cohort to 0.697 in the non-European cohort. AUC was 0.902 and 0.835 respectively (difference 0.066; p=0.029). In the Class I and Class II task the corresponding values were 0.875 and 0.723 (difference 0.152; p<0.001). A subgroup analysis showed lower sensitivity in children than adults across both cohorts (0.71 to 0.80 versus 0.89 to 0.90). AUC was lower in the non-European cohort for all three models in both tasks. The observed performance differences are consistent with a population-specific generalizability effect rather than model-specific failure and support mandatory external validation on target populations before clinical deployment.
Related
- Mandibular incisor alveolar housing and incisor-alveolar axis relationship in untreated skeletal Class III malocclusion: A cross-sectional CBCT study
- AI-Driven opportunistic osteoporosis screening: the skeletal failure paradigm for trustworthy vertebral fracture triage
- Construction and validation of a frailty screening model for older adults with cataract: a cross-sectional study
- Federated learning for privacy-preserving opportunistic screening of lumbar-spine DXA-defined osteoporotic-level bone mineral density using chest radiographs: A multi-center independent validation study
- Population‐Based Prediction Equations for Appendicular Skeletal Muscle Mass: A Three‐Phase Validation Study in 13 582 Asian Adults
BibTeX
@misc{davut2026photographbased,
title = {{Photograph-Based Skeletal Malocclusion Screening with Geometric Machine Learning: External Validation Across Turkish and Non-European Cohorts}},
author = {A. Eker Davut and M. C. Sakman and A. Yagci and B. Cakmak and E. Dumu and Y. E. Ucaker and C. A. Akcan and O. Kilic and T. Onal-Suzek and B. Kilic},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.28.26366413},
url = {https://www.medrxiv.org/content/10.64898/2026.10.28.26366413v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Photograph-Based Skeletal Malocclusion Screening with Geometric Machine Learning: External Validation Across Turkish and Non-European Cohorts
AU - A. Eker Davut
AU - M. C. Sakman
AU - A. Yagci
AU - B. Cakmak
AU - E. Dumu
AU - Y. E. Ucaker
AU - C. A. Akcan
AU - O. Kilic
AU - T. Onal-Suzek
AU - B. Kilic
PY - 2026
DA - 2026/10/28
PB - medRxiv
DO - 10.64898/2026.10.28.26366413
UR - https://www.medrxiv.org/content/10.64898/2026.10.28.26366413v1
AB - A photograph based screening classifier for skeletal malocclusion maps 100 engineered geometric feature vectors, derived from a side-profile smartphone photograph, to orthodontic class labels, enabling non-invasive triage without radiographic imaging. This study reports external validation across two independent cohorts that contributed no cases to training. Two binary tasks were evaluated; Class III against non-Class III, and Class I against Class II; each with its own development set and model, applied without modification at the default threshold. One external cohort was Turkish, drawn from an institution not represented in the development set; the other was a non-European cohort from a Belgian private orthodontic clinic. Sensitivity, specificity and the area under the receiver operating characteristic curve (AUC) were pre-specified as primary outcome measures, since none depends on outcome prevalence. In the Class III task, sensitivity was similar across all three evaluation sets (0.801, 0.836, 0.848; all adjusted p>0.7), while specificity fell from 0.766 in the Turkish external cohort to 0.697 in the non-European cohort. AUC was 0.902 and 0.835 respectively (difference 0.066; p=0.029). In the Class I and Class II task the corresponding values were 0.875 and 0.723 (difference 0.152; p<0.001). A subgroup analysis showed lower sensitivity in children than adults across both cohorts (0.71 to 0.80 versus 0.89 to 0.90). AUC was lower in the non-European cohort for all three models in both tasks. The observed performance differences are consistent with a population-specific generalizability effect rather than model-specific failure and support mandatory external validation on target populations before clinical deployment.
ER -