A theoretical analysis of longitudinal temporomandibular joint compressive stresses and mandibular growth

Comparison of individualized facial growth prediction models based on the partial least squares and artificial intelligence

OBJECTIVES

To compare facial growth prediction models based on the partial least squares and artificial intelligence (AI).

MATERIALS AND METHODS

Serial longitudinal lateral cephalograms from 410 patients who had not undergone orthodontic treatment but had taken serial cephalograms were collected from January 2002 to December 2022. On every image, 46 skeletal and 32 soft-tissue landmarks were identified manually. Growth prediction models were constructed using multivariate partial least squares regression (PLS) and a deep learning method based on the TabNet deep neural network incorporating 161 predictor, and 156 response, variables. The prediction accuracy between the two methods was compared.

RESULTS

On average, AI showed less prediction error by 2.11 mm than PLS. Among the 78 landmarks, AI was more accurate in 63 landmarks, whereas PLS was more accurate in nine landmarks, including cranial base landmarks. The remaining six landmarks showed no statistical difference between the two methods. Overall, soft-tissue landmarks, landmarks in the mandible, and growth in the vertical direction showed greater prediction errors than hard-tissue landmarks, landmarks in the maxilla, and growth changes in the horizontal direction, respectively.

CONCLUSIONS

PLS and AI methods seemed to be valuable tools for predicting growth. PLS accurately predicted landmarks with low variability in the cranial base. In general, however, AI outperformed, particularly for those landmarks in the maxilla and mandible. Applying AI for growth prediction might be more advantageous when uncertainty is considerable.

Orthognathic surgery effects on temporomandibular joint compressive stresses

INTRODUCTION

This study tested orthognathic surgery effects on temporomandibular joint (TMJ) compressive stresses.

METHODS

Pre- (T1) and post-surgery (T2) cone-beam computed tomography images were collected from consenting subjects aged ≥15 years. Anatomical data were used to measure surgical changes in anteroposterior mandibular position and occlusal plane angle (FH-OP), estimate condylar loading areas (mm2 ) and calculate T1 and T2 TMJ and jaw muscle forces (N) during canine biting via numerical modelling. Analysis of covariance tested for sex and biting angle differences in T2 - T1 TMJ compressive stresses (TMJ force/loading area, MPa). Principal component analyses identified jaw muscle forces that accounted for changes in T2 - T1 TMJ loads. Regression analyses tested the correlations between surgical changes in mandibular position, FH-OP, TMJ loads and muscle forces.

RESULTS

Of 148 cases screened, 28 females and 16 males provided complete records. Condylar loading areas were significantly smaller (P = .024) for females vs males (124 ± 5 vs 144 ± 7 mm2 ). T2 - T1 differences in TMJ compressive stresses varied by surgical change, biting angle and sex. Overall, the largest increases in TMJ compressive stresses post-surgery were for females with mandibular setbacks where FH-OP angle decreased. T2 - T1 changes in jaw muscle forces had moderate (ipsilateral, λ = 4.59; η2  = 0.071) to large (contralateral, λ = 1.49; η2  = 0.31) effects on TMJ loads.

CONCLUSIONS

T2 - T1 differences in TMJ compressive stresses during canine biting were affected by surgical changes in mandibular position and occlusal plane angle, biting angle and sex. Surgical changes altered jaw muscle forces for the same biting conditions and, thus, affected TMJ loads and compressive stresses.