Back to all papers

Mandiblemath: External validation of a predictive tool for mandibular reconstruction.

April 28, 2026pubmed logopapers

Authors

Niño-Sandoval TC,Vasconcelos BC

Affiliations (2)

  • Department of Oral and Maxillofacial Surgery, Universidade de Pernambuco - School of Dentistry (UPE/FOP), Recife, Brazil.
  • Department of Oral and Maxillofacial Surgery and Traumatology, Universidade de Pernambuco - School of Dentistry (UPE/FOP), Recife, Brazil. Electronic address: [email protected].

Abstract

Mandiblemath is an artificial intelligence-driven software for predictive mandibular reconstruction that infers three-dimensional mandibular morphology from two-dimensional craniofacial data. We developed and externally validated Mandiblemath using a modular Python implementation integrating scientific computing, 3D visualization, and supervised learning. Ninety-one computed tomography scans (46 female, 45 male) yielded 12 craniomaxillary angles per subject; partial least squares regression generated 12 patient-specific mandibular configurations (Y<sub>1</sub>-Y<sub>12</sub>). Sex-specific classifiers - random forest, XGBoost, linear SVM, RBF-SVM, and gradient boosting - were trained with 10-fold cross-validation. External validation used 18 independent scans (nine female, nine male). Geometric correspondence between predicted and real mandibles was quantified using standard surface-based metrics. The best internal classifiers were linear SVM for females (68% accuracy) and random forest for males (82.8%). External validation achieved 88.8% accuracy for group identification in both sexes and ranking accuracy (top-three suggestions) of 66.6% in females and 70.4% in males. Predicted models exhibited broad global congruence with reference mandibles, maintaining clinically acceptable discrepancies (RMSD 1.2-3.3 mm) and strong overlap ([email protected] mm ≥ 0.85; Surface [email protected] mm ≥ 0.80). Mandiblemath demonstrated technical feasibility and clinical potential as a decision-support tool, providing low-cost, reproducible predictions and printable meshes for reconstructive planning. The findings support future multicenter validation and integration into digital surgical workflows.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.