Predictive Model for Bone Availability in Patients With Unilateral Cleft Lip and Palate: A Machine Learning Approach

ObjectiveTo develop a predictive model for estimating cortical bone thickness at any maxillary location in patients with unilateral cleft lip and palate (UCLP).DesignRetrospective cross-sectional cohort study with machine learning.SettingUniversity hospital, Department of Oral and Maxillofacial Radiology.Patients, ParticipantsFifty patients with non-syndromic UCLP and 50 age- and gender-matched controls (total N = 100). Mean age: UCLP 14.8 ± 5.1 years; controls 16.5 ± 4.6 years. Age range: 8 to 27 years.InterventionsAll participants underwent CBCT (0.2 mm voxel, 14 × 16 cm FOV). Cortical bone thickness was measured at 4, 6, 8, 10, and 12 mm from the alveolar crest across six interradicular regions, yielding 4500 data points.Main Outcome Measure(s)Cortical bone thickness; model performance metrics (R², RMSE); feature importance; accuracy by region and depth.ResultsRandom Forest regression explained 75% of variance (patient-level cross-validation: R² = 0.75, RMSE = 0.102 mm). Anatomical region was the strongest predictor (0.38), followed by depth (0.27), age (0.18), cleft status (0.12), and side (0.05). Best accuracy in posterior regions (R² = 0.84) and at 12 mm depth (R² = 0.81); lowest in anterior regions (R² = 0.72) and at 4 mm depth (R² = 0.69). The model identified high-risk zones with 89% sensitivity (AUC = 0.94). External validation has not yet been performed; the author welcomes collaboration with other centers for independent testing.ConclusionsThis model provides accurate, patient-specific predictions of cortical bone thickness in UCLP patients, assisting in pretreatment risk assessment, surgical planning, and patient counseling.