Prediction of mandibular growth rotation: assessment of the Skieller, Björk, and Linde-Hansen method

Validation of Machine Learning Models for Craniofacial Growth Prediction

This study identified the most accurate model for predicting longitudinal craniofacial growth in a Japanese population using statistical methods and machine learning. Longitudinal lateral cephalometric radiographs were collected from 59 children (27 boys and 32 girls) with no history of orthodontic treatment. Multiple regression analysis, least absolute shrinkage and selection operator, radial basis function network, multilayer perceptron, and gradient-boosted decision tree were used. The independent variables included 26 coordinated values of skeletal landmarks, 13 linear skeletal parameters, and 17 angular skeletal parameters in children ages 6 to 12 years. The dependent variables were the values of the 26 coordinated skeletal landmarks, 13 skeletal linear parameters, and 17 skeletal angular parameters at 13 years of age. The difference between the predicted and actual measured values was calculated using the root-mean-square error. The prediction model for craniofacial growth using the least absolute shrinkage and selection operator had the smallest average error for all values of skeletal landmarks, linear parameters, and angular parameters. The highest prediction accuracies when predicting skeletal linear and angular parameters for 13-year-olds were 97.87% and 94.45%, respectively. This model incorporates several independent variables and is useful for future orthodontic treatment because it can predict individual growth.

Short- and Long-Term Prediction of the Post-Pubertal Mandibular Length and Y-Axis in Females Utilizing Machine Learning

The aim of this study was to create a novel machine learning (ML) algorithm for predicting the post-pubertal mandibular length and Y-axis in females. Cephalometric data from 176 females with Angle Class I occlusion were used to train and test seven ML algorithms. For all ML methods tested, the mean absolute errors (MAEs) for the 2-year prediction ranged from 2.78 to 5.40 mm and 0.88 to 1.48 degrees, respectively. For the 4-year prediction, MAEs of mandibular length and Y-axis ranged from 3.21 to 4.00 mm and 1.19 to 5.12 degrees, respectively. The most predictive factors for post-pubertal mandibular length were mandibular length at previous timepoints, age, sagittal positions of the maxillary and mandibular skeletal bases, mandibular plane angle, and anterior and posterior face heights. The most predictive factors for post-pubertal Y-axis were Y-axis at previous timepoints, mandibular plane angle, and sagittal positions of the maxillary and mandibular skeletal bases. ML methods were identified as capable of predicting mandibular length within 3 mm and Y-axis within 1 degree. Compared to each other, all of the ML algorithms were similarly accurate, with the exception of multilayer perceptron regressor.

Prediction of Pubertal Mandibular Growth in Males with Class II Malocclusion by Utilizing Machine Learning

The goal of this study was to create a novel machine learning (ML) model that can predict the magnitude and direction of pubertal mandibular growth in males with Class II malocclusion. Lateral cephalometric radiographs of 123 males at three time points (T1: 12; T2: 14; T3: 16 years old) were collected from an online database of longitudinal growth studies. Each radiograph was traced, and seven different ML models were trained using 38 data points obtained from 92 subjects. Thirty-one subjects were used as the test group to predict the post-pubertal mandibular length and y-axis, using input data from T1 and T2 combined (2 year prediction), and T1 alone (4 year prediction). Mean absolute errors (MAEs) were used to evaluate the accuracy of each model. For all ML methods tested using the 2 year prediction, the MAEs for post-pubertal mandibular length ranged from 2.11-6.07 mm to 0.85-2.74° for the y-axis. For all ML methods tested with 4 year prediction, the MAEs for post-pubertal mandibular length ranged from 2.32-5.28 mm to 1.25-1.72° for the y-axis. Besides its initial length, the most predictive factors for mandibular length were found to be chronological age, upper and lower face heights, upper and lower incisor positions, and inclinations. For the y-axis, the most predictive factors were found to be y-axis at earlier time points, SN-MP, SN-Pog, SNB, and SNA. Although the potential of ML techniques to accurately forecast future mandibular growth in Class II cases is promising, a requirement for more substantial sample sizes exists to further enhance the precision of these predictions.

Prediction of the Post-Pubertal Mandibular Length and Y Axis of Growth by Using Various Machine Learning Techniques: A Retrospective Longitudinal Study

The aim was to predict the post-pubertal mandibular length and Y axis of growth in males by using various machine learning (ML) techniques. Cephalometric data obtained from 163 males with Class I Angle malocclusion, were used to train various ML algorithms. Analysis of variances (ANOVA) was used to compare the differences between predicted and actual measurements among methods and between time points. All the algorithms revealed an accuracy range from 95.80% to 97.64% while predicting post-pubertal mandibular length. When predicting the Y axis of growth, accuracies ranged from 96.60% to 98.34%. There was no significant interaction between methods and time points used for predicting the mandibular length (p = 0.235) and Y axis of growth (p = 0.549). All tested ML algorithms accurately predicted the post-pubertal mandibular length and Y axis of growth. The best predictors for the mandibular length were mandibular and maxillary lengths, and lower face height, while they were Y axis of growth, lower face height, and mandibular plane angle for the post-pubertal Y axis of growth. No significant difference was found among the accuracies of the techniques, except the least squares method had a significantly larger error than all others in predicting the Y axis of growth.

Craniofacial shape from pre- to post-adolescence

AIM

Craniofacial growth demonstrates significant variation and is difficult to predict. The aim of the present investigation was twofold: (1) to assess the association (covariation) between craniofacial shape at pre- and post-adolescence and (2) to evaluate if pre-adolescent craniofacial shape is related (covaries) with growth magnitude and direction.

SUBJECTS AND METHODS

One hundred fifty subjects (86 males and 64 females) untreated orthodontically were selected from AAOF Craniofacial Growth Legacy Collection. Each subject had cephalograms taken before 9 (pre-adolescent stage) and after 15 years of age (post-adolescent). Fourteen curves comprising 123 points (10 fixed and 113 sliding semilandmarks) comprehensively covering the craniofacial skeleton were digitally traced on each cephalogram. Procrustes alignment, principal component analysis, 2-block partial least squares (2B-PLS) analysis, and regression analysis were done after sliding the semilandmarks to minimize bending energy.

RESULTS

The first 16 principal components (PCs) were non-trivial and explained 85.2% of total shape variability in the sample. PC1 depicted mainly variability in the vertical direction, PC2 represented mostly variability in the saddle angle and in the antero-posterior position of the mandible, and PC3 depicted primarily variability of the mandibular shape (steep versus flat mandibular plane). The covariation between pre- and post-adolescent facial shape was statistically significant, both in the pooled sample (RV coefficient = 0.604) and in boys (RV = 0.639) and girls (RV = 0.629). The pre-adolescent shape was weakly associated with the magnitude of facial change-2-block PLS analysis demonstrated that blocks 1 and 2 were independent (P = 0.118, RV = 0.035).

CONCLUSIONS

The pre-adolescent shape of the craniofacial complex explained approximately 60% of the post-adolescent shape of the craniofacial complex; however, the relationship between pre-adolescent shape of the craniofacial complex and magnitude of its change was weak.

Mesiodistal angulation of posterior teeth in orthodontic patients with different facial growth patterns

Background. Mesiodistal and buccolingual angulations of teeth are variable in different malocclusion classes. This study aimed to assess the mesiodistal angulation of posterior teeth in orthodontic patients with vertical, normal, and horizontal facial growth patterns. Methods. This descriptive, cross-sectional study evaluated 150 lateral cephalograms of orthodontic patients. According to cephalometric analysis, facial growth patterns were divided into three groups of normal, horizontal, and vertical (n=50). The angulation of maxillary and mandibular posterior teeth was then measured. Data were analyzed using SPSS 22. Results. The results showed an increase in the mean angle of maxillary and mandibular posterior teeth relative to palatal and mandibular planes in patients with a vertical facial growth pattern. Conversely, their angulation decreased relative to the bisected occlusal plane (BOP). The angulation of posterior teeth decreased relative to palatal and mandibular planes and increased relative to the occlusal plane with an increase in overbite. The mean angle of all maxillary teeth relative to the palatal plane was significantly greater in open bite patients compared to normal and deep bite patients. This value in patients with normal bite was significantly greater than that in deep bite patients (P<0.05). Conclusion. The current results revealed that in patients with a vertical growth pattern, all the posterior teeth had a forward inclination. Conversely, in patients with a horizontal growth pattern, the teeth had a backward inclination.

The use of Bjork's indications of growth for evaluation of extremes of skeletal morphology

BACKROUND

Morphological indicators within the cranium for prediction of mandibular growth patterns as reported by Bjork are: (1) inclination of the condylar head (ICH), (2) curvature of mandibular canal (CMC), (3) shape of the lower border of the mandible and specifically depth of the antegonial notch (AN), (4) inclination of the symphysis (ISY), (5) interincisal angle (IIA), (6) intermolar angle (IMA), and (7) lower anterior face height (LAFH). The purpose of this study was to examine the association of these indicators as they relate to extreme skeletal patterns observed in skeletally mature subjects.

MATERIALS

The pre-treatment lateral cephalometric radiographs of 395 post-growth subjects were randomly selected from the archives of a university orthodontic department. These were divided in three groups according to their MP-SN angle [normal: 28-36degrees (G1), hypodivergent: ≤26degrees (G2), hyperdivergent: ≥38degrees (G3)].

RESULTS

It was found that only LAFH was correlated to age across all groups. However, within G1, G2, and G3, and between genders, it was found that there were statistically significant differences for all indicators in relation to age, except IMA (P > 0.05). In addition, ISY and IMA had a predictive value lower than the chance level (0.5).

CONCLUSION

Bjork's implant studies have contributed much to understanding facial-skeletal growth; however, this study suggests that their utilization as a tool in classifying extreme skeletal patterns requires careful evaluation of all the parameters involved.

Correlation between symphyseal morphology and mandibular growth

Background:

This study sought to assess symphyseal morphology in adolescents with different mandibular growth patterns (MGPs) in order to see if a relation exists.

Materials and Methods:

In this study the symphyseal parameters (height, depth, and ratio) of normal subjects were compared with four groups with malocclusion (cl III vertical, cl II vertical, cl III horizontal, and cl II horizontal). These groups (15 samples each) were matched (for sex and cervical maturation stage [CVMS]) based on their cephalograms and patient charts. Growth patterns were differentiated by seven vertical parameters and the Wylie analysis. After confirmation of normality of the groups and similarity of their variances the two-way analysis of variance (ANOVA) was used for analysis of data assessed by adjusted chi-square (P < 0.001). The comparison of cases with the normal group was performed by the Dunnett method. Intraclass Correlation Coefficient (ICC) was used for evaluation of intraobserver reliability.

Results:

We found the symphyseal ratio to have a significant correlation with the MGP (P < 0.001). The symphyseal ratio (Height/Depth) was small in a mandible with vertical growth pattern Cl II or Cl III. Conversely, a horizontal growth pattern of a Cl II or Cl III mandible was associated with a larger ratio of the symphysis in comparison with the normal group. The symphyseal ratio was also found to be greater in females.

Conclusion:

The symphyseal ratio was found to be strongly associated with the MGP.

The inclination of mandibular incisors revisited

OBJECTIVE

To reassess the inclination of lower incisors and evaluate possible associations with gender, age, symphyseal parameters, and skeletal pattern.

MATERIALS AND METHODS

Twelve hundred and seventy-two (605 females, 667 males) cephalograms of untreated subjects of a craniofacial growth study (age: 8-16 years) were evaluated. Correlations between the angulation of the lower incisors and age, symphyseal distances (height, width, and depth), symphyseal ratios (height-width, height-depth), and skeletal angles (divergence of the jaws and gonial angle) were investigated for all ages separately and for both sexes independently.

RESULTS

The inclination of lower incisors increased over age (8 years: girls = 93.9° [95% CI, 92.3°-95.7°], boys = 93.3° [95% CI, 91.8°-94.9°]; 16 years: girls = 96.1° [95% CI, 94.1°-98.2°], boys = 97.1° [95% CI, 95.6°-98.6°]). Inclination of lower incisors correlated with the divergence of the jaws for all ages significantly or highly significantly, except for boys and girls 9 years of age and girls 11 and 12 years of age, for which only a tendency was observed. Similarly, a strong correlation to gonial angle could be observed. No correlation could be found between the inclination of lower incisors and any symphyseal parameters (absolute measurements and ratios), except for symphyseal depth.

CONCLUSION

Lower incisor inclination is linked to the subject's sex, age, and skeletal pattern. It is not associated with symphyseal dimensions, except symphyseal depth. Factors related to natural inclination of lower incisors should be respected when establishing a treatment plan.

Cervical vertebrae maturation method morphologic criteria: poor reproducibility

INTRODUCTION

The cervical vertebrae maturation (CVM) method has been advocated as a predictor of peak mandibular growth. A careful review of the literature showed potential methodologic errors that might influence the high reported reproducibility of the CVM method, and we recently established that the reproducibility of the CVM method was poor when these potential errors were eliminated. The purpose of this study was to further investigate the reproducibility of the individual vertebral patterns. In other words, the purpose was to determine which of the individual CVM vertebral patterns could be classified reliably and which could not.

METHODS

Ten practicing orthodontists, trained in the CVM method, evaluated the morphology of cervical vertebrae C2 through C4 from 30 cephalometric radiographs using questions based on the CVM method. The Fleiss kappa statistic was used to assess interobserver agreement when evaluating each cervical vertebrae morphology question for each subject. The Kendall coefficient of concordance was used to assess the level of interobserver agreement when determining a "derived CVM stage" for each subject.

RESULTS

Interobserver agreement was high for assessment of the lower borders of C2, C3, and C4 that were either flat or curved in the CVM method, but interobserver agreement was low for assessment of the vertebral bodies of C3 and C4 when they were either trapezoidal, rectangular horizontal, square, or rectangular vertical; this led to the overall poor reproducibility of the CVM method. These findings were reflected in the Fleiss kappa statistic. Furthermore, nearly 30% of the time, individual morphologic criteria could not be combined to generate a final CVM stage because of incompatible responses to the 5 questions. Intraobserver agreement in this study was only 62%, on average, when the inconclusive stagings were excluded as disagreements. Intraobserver agreement was worse (44%) when the inconclusive stagings were included as disagreements. For the group of subjects that could be assigned a CVM stage, the level of interobserver agreement as measured by the Kendall coefficient of concordance was only 0.45, indicating moderate agreement.

CONCLUSIONS

The weakness of the CVM method results, in part, from difficulty in classifying the vertebral bodies of C3 and C4 as trapezoidal, rectangular horizontal, square, or rectangular vertical. This led to the overall poor reproducibility of the CVM method and our inability to support its use as a strict clinical guideline for the timing of orthodontic treatment.

Mandibular growth rotation effects on postretention stability of mandibular incisor alignment

OBJECTIVE

To test the hypotheses that pronounced forward and backward mandibular growth rotation may be risk factors for postretention relapse of mandibular incisor alignment, and that morphologic parameters at adolescence may be predictive of the remaining type of mandibular growth.

MATERIALS AND METHODS

Cephalograms and study models were made before (T1) and after (T2) active treatment and at a minimum of 10 years postretention (T3) of three groups of orthodontic patients with acceptable occlusion at the time of appliance removal. The groups were short facial height (n = 46), angle between the sella-nasion line and the mandibular plane (SN/MP) <or= 28 degrees; normal facial height (n = 42), SN/MP 29 degrees through 37 degrees ; and long facial height (n = 35), SN/MP >or= 38 degrees at T2.

RESULTS

The groups were similar regarding age at T2, gender ratio, incisor irregularity (IRI), intercanine (3-3) width at T1, change of 3-3 width from T1 to T2, and time from T2 to T3 (P > .05). IRI increased in all groups from T2 to T3 (P < .05), but there were not any intergroup differences in this increase (P > .05). Minor differences were detected among the groups in mandibular growth rotation from T2 to T3. Males experienced more forward rotation than females (P < .001) and more increase in IRI from T2 to T3 (P < .01). Male gender, T1-T2 increase in 3-3 width, and T2-T3 reduction in 3-3 width were included in the model explaining T2-T3 increase in IRI.

CONCLUSION

High-angled and low-angled facial patterns at time of appliance removal are not associated with increased risk of postretention relapse of mandibular incisor malalignment, and in adolescent orthodontic patients are poor predictors of type of posttreatment growth.

Distribution of orthodontic services and fees in an insured population in Washington

Previous attempts to quantify the amount and type of orthodontic therapy provided by nonorthodontists in the United States have relied on survey data. Although there are advantages to surveys, such as control over survey recipients and inclusion of specific questions, they also have limitations, such as low response rates, response bias, and recall bias. This study used insurance claims data from a large dental benefits provider in Washington to assess the distribution of orthodontic services and fees among various dental providers. All orthodontic claims allowed by Washington Dental Service in 2001 were retrieved, along with treatment codes, fees, and demographic information for both patients and providers. A total of 102,984 orthodontic claims were included in the study. General dentists submitted 7.0% of these claims, orthodontists submitted 90.9%, and pedodontists submitted 1.9%. Orthodontists submitted higher average fees for space maintainers, first payments, and records. The percentage of orthodontic treatment preformed by general dentists and pedodontists in this claims-based study was substantially less than what has been previously reported in survey-based studies. Additionally, a smaller percentage of general dentists and pedodontists in this study performed comprehensive treatment, compared with previous studies. This study illustrates the value of insurance claims data to assess the provision of orthodontic care.

Clinical outcomes of Fränkel appliance therapy assessed with a counterpart analysis

To evaluate whether the Fränkel Regulator-II (FR-II) induced mandibular growth rotations relative to the nasomaxilla and the middle cranial fossae, cephalometric changes in 28 treated Brazilian children were compared with changes in 28 untreated Class II children and in 28 children with normal occlusion. According to Enlow's counterpart analysis, the 3 groups were not significantly different initially in ramus alignment or relative ramus vertical dimension. These jaw relationships were maintained in both untreated groups. In the treated group, all children had overjet reduction, with correction of the dental arch relationship in 26 of the 28, and there was a significant trend toward a more forward ramus alignment (P =.002) and increased ramus relative vertical dimension (P =.0002). These treatment-induced changes showed a negative correlation with ramus alignment; ie, greater improvement was more likely in children who had backward ramus alignment before treatment and whose Class II malocclusion had not already been intrinsically compensated. Changes in the treated children were similar to but greater than those in the normal children, and different from those in the untreated Class II group. The data suggest that studies of skeletal variations with counterpart analysis can show ramus remodeling compensations from treatment that are missed with conventional cephalometrics.

Evaluation of antegonial notch depth for growth prediction

In recent years, some researchers have proposed that the depth of the mandibular antegonial notch can be used as a predictor of facial growth. However, the data for those studies were derived from populations with extreme morphologic characteristics. The purpose of this investigation was to test the hypothesis that the antegonial notch depth is a useful predictor of facial growth in a longitudinal sample of untreated growing patients selected at random. Lateral cephalometric radiographs were obtained from 20 males and 20 females at 3 times, approximating prepubescence (8.5 years), adolescence (12 years), and adulthood (> or = 17 years). These 40 subjects were randomly chosen from a longitudinal sample of untreated growing patients. Prepubescent and adolescent antegonial notch depths were correlated with vertical and horizontal growth changes of the jaws from the age of 8.5 years to adulthood. Correlation analysis revealed a statistically (but not clinically) significant negative relationship (0.40 < or = r < or = 0.47; P < or =.05) between adolescent antegonial notch depth and horizontal growth of the maxilla and the mandible from adolescence to adulthood. Previous investigators have proposed that antegonial notch depth, when extreme in magnitude, might be used to predict facial growth. We concluded that antegonial notch depth fails to provide sufficient indication of future facial growth to warrant its application as a growth predictor in a nonextreme population.