Expert Orthodontists Research Articles

Diagnostic accuracy of conventional orthodontic radiographic modalities and cone-beam computed tomography for localization of impacted maxillary canine teeth.

Orthodontic treatment planning for an impacted canine tooth requires accurate information about its position. The aim of this study was to compare the diagnostic accuracy of two conventional orthodontic radiographic modalities with cone-beam computed tomography (CBCT) for localization of impacted maxillary canine teeth. Panoramic radiographs, lateral cephalograms, and CBCT scans of 30 patients with unilaterally impacted maxillary canine teeth were retrieved from the archives. Eight expert orthodontists evaluated the parameters related to the location of impacted canine teeth by using panoramic radiographs and lateral cephalograms of patients. After 4 weeks, the same parameters were evaluated on CBCT scans of patients. The diagnostic accuracy of conventional modalities and CBCT was compared with each other and also with the gold standard. The conventional radiographic modalities and CBCT had similar accuracy for assessment of the overall inclination (p = 0.11), apex morphology (p = 0.18), and mesiodistal position of the apex (p = 0.12). CBCT had significantly higher accuracy for determination of incisal tip location (p = 0.001), labiopalatal (p = 0.001) and vertical (p = 0.01) position of the crown tip, minimum bone thickness covering the crown (p = 0.001), and root resorption of the adjacent tooth (p = 0.001). The combination of panoramic radiographs and lateral cephalograms was sufficiently accurate to assess some diagnostic parameters such as overall inclination, apex morphology, and mesiodistal apex location of impacted canine teeth.

Robotic Applications in Orthodontics: Overview of Existing Research

Malocclusion is the world's third most common oral ailment. The fixed orthodontic procedure is now the most successful treatment strategy for malocclusion. Archwire bending is an important part of orthodontic therapy. However, because to the great stiffness and exceptional flexibility of orthodontic wire, it is a very difficult task. The old method of obtaining the created archwire curve is dependent on manual operation, which would bring various errors induced by human causes. Customised archwires are required in clinics for lingual orthodontics treatment. Previously, only expert orthodontists could physically bend these archwires. This is a pattern demands specialised skill training, precision, and extensive chairside time, but cannot guarantee the accuracy of appliances. So, what are the most recent developments?

Facial profile evaluation and prediction of skeletal class II patients during camouflage extraction treatment: a pilot study

BackgroundThe evaluation of the facial profile of skeletal Class II patients with camouflage treatment is of great importance for patients and orthodontists. The aim of this study is to explore the key factors in evaluating the facial profile esthetics and to predict the posttreatment facial profile esthetics of skeletal Class II extraction patients.Methods124 skeletal Class II extraction patients were included. The pretreatment and posttreatment cephalograms were analyzed by a trained expert orthodontist. The facial profile esthetics of pretreatment and posttreatment lateral photographs were evaluated by 10 expert orthodontists using the visual analog scale (VAS). The correlation between subjective facial profile esthetics and objective cephalometric measurements was assessed. Three machine-learning methods were used to predict posttreatment facial profile esthetics.ResultsThe distances from lower and upper lip to the E plane and U1-APo showed the stronger correlation with profile esthetics. The changes in lower lip to the E plane and U1-APo during extraction exhibited the stronger correlation with changes in VAS score (r = − 0.551 and r = − 0.469). The random forest prediction model had the lowest mean absolute error and root mean square error, demonstrating a better prediction accuracy and fitting effect. In this model, pretreatment upper lip to E plane, pretreatment Pog-NB and the change of U1-GAll were the most important variables in predicting the posttreatment score of facial profile esthetics.ConclusionsThe maxillary incisor protrusion and lower lip protrusion are key objective indicators for evaluating and predicting facial profile esthetics of skeletal Class II extraction patients. An artificial intelligence prediction model could be a new method for predicting the posttreatment esthetics of facial profiles.

Orthodontic Practitioners’ Knowledge and Education Demand on Clear Aligner Therapy

ObjectivesClear aligner therapy (CAT) has been gaining popularity amongst the orthodontic community. No systematic course on CAT has been reported to date. The objectives of this study were to determine practitioners’ knowledge and to offer insights for future tailored courses on CAT. MethodsAn online questionnaire was distributed. The questionnaire comprised personal background information, predictability of tooth movement through CAT, and CAT knowledge that practitioners demanded to learn. Four senior expert orthodontists’ answers to the predictability of tooth movement through CAT were averaged to be a standard reference. Descriptive statistics, 1-way analysis of variance (ANOVA), principal component analysis, Student t test, and multivariate logistics regression analysis were performed with significance set at P < .05. ResultsIn total, 190 practitioners participated in this study. As compared to the standard reference, participants overestimated the predictability of difficult-to-be-achived tooth movements (eg, molar mesialisation; P < .0001). Strategy of managing troubleshooting cases and extraction cases ranked the highest CAT knowledge that participants requested to learn. Practice type, number of completed CAT cases, number of undergoing CAT cases, years of practice, education background, and time of using CAT were the influencing factors of the questions regarding the predictability of tooth movement through CAT and CAT knowledge that were demanded to be learned. ConclusionsThe predictability of difficult-to-be-achieved tooth movement through CAT is often overestimated by practitioners with limited clinical experience. Tailored education on CAT, especially managing troubleshooting cases and extraction cases, should be designed for all practitioners.

Decision-making patterns among expert and novice orthodontists and oral maxillofacial surgeons in the management of adults with Class III malocclusions and moderate degree of skeletal discrepancies.

To explore the decision-making patterns among expert and novice orthodontists and oral maxillofacial surgeons in the management of adults with Class III malocclusions and moderate skeletal discrepancies. Self-administered questionnaire survey. Faculty of Dentistry, National University of Singapore and the University Dental Cluster, National University Hospital, Singapore. A total of 55 clinicians, comprising 13 expert orthodontists, 20 novice orthodontists, 10 expert oral maxillofacial surgeons and 12 novice oral maxillofacial surgeons. Clinicians assessed six adults with a Class III malocclusion and moderate skeletal discrepancy. They were asked to decide who could be managed exclusively by orthodontic camouflage, who would require combined orthodontic-orthognathic surgery as the only viable treatment, or who could be offered both treatment options. The study found variable decision-making patterns among the clinicians in each case. Only 18.2%-40.0% of clinicians agreed that the cases selected were of moderate skeletal discrepancies and could be offered both treatment options whereas the rest were either more inclined to recommend orthodontic camouflage or orthognathic surgery. Intra-clinician agreement (n = 20) was only fair (Kappa value = 0.31). There was only slight inter-clinician agreement (n = 55) on their clinical decisions (Kappa value = 0.10). Clinical experience and dental specialty did not significantly influence clinicians' decisions. Oral and maxillofacial surgeons were 1.98 times more likely to indicate orthognathic surgery as the only viable treatment compared to the orthodontists (95% confidence interval = 1.15-3.42). Variability in the patterns of decision-making for adults with a Class III malocclusion and moderate skeletal discrepancy was observed among the clinicians with low repeatability and agreement.

Image preprocessing with contrast-limited adaptive histogram equalization improves the segmentation performance of deep learning for the articular disk of the temporomandibular joint on magnetic resonance images

The objective was to evaluate the robustness of deep learning (DL)-based encoder-decoder convolutional neural networks (ED-CNNs) for segmenting temporomandibular joint (TMJ) articular disks using data sets acquired from 2 different 3.0-T magnetic resonance imaging (MRI) scanners using original images and images subjected to contrast-limited adaptive histogram equalization (CLAHE). In total, 536 MR images from 49 individuals were examined. An expert orthodontist identified and manually segmented the disks in all images, which were then reviewed by another expert orthodontist and 2 expert oral and maxillofacial radiologists. These images were used to evaluate a DL-based semantic segmentation approach using an ED-CNN. Original and preprocessed CLAHE images were used to train and validate the models whose performances were compared. Original and CLAHE images acquired on 1 scanner had pixel values that were significantly darker and with lower contrast. The values of 3 metrics-the Dice similarity coefficient, sensitivity, and positive predictive value-were low when the original MR images were used for model training and validation. However, these metrics significantly improved when images were preprocessed with CLAHE. The robustness of the ED-CNN model trained on a dataset obtained from a single device is low but can be improved with CLAHE preprocessing. The proposed system provides promising results for a DL-based, fully automated segmentation method for TMJ articular disks on MRI.

Comparison of Self-Perception of Esthetics and Orthodontic Treatment Needs among Dental and Non-Dental Students with Assessment by Orthodontist

Objectives: The present study was conducted to compare the self-perception of esthetics and wish for seeking orthodontic treatment among dental and non-dental students. The realistic orthodontic treatment needs were confirmed by expert orthodontist. Methods: A cross-sectional study was conducted among 255 male students (Dental—75, Medical—93 and Pharmacy—87 students). The questionnaire included 20 items covering dental esthetics self-perception (10 questions), self-confidence and psychological impact (5 questions), and the need for seeking orthodontic treatment (5 questions) on a five-point Likert scale. The realistic orthodontic treatment needs were confirmed by photographs using aesthetic component of IOTN and clinical examination for the participants and analysis of jaw models using Dental aesthetic index (DAI). Kruskal-Wallis ANOVA was used to check the significant difference between groups. Results: The overall average esthetic self-perception score for total sample was 3.83. The overall average psychological impact score for the whole sample was 2.67. The total percentage of participants who either agree or strongly agree with the question related to their perception of need for seeking orthodontic treatment was 70%. According to the assessment of orthodontic needs using AC-IOTN, 19.8% required definitive treatment. According to the assessment of orthodontic treatment needs based on DAI, 20.3% and 9.9% needed highly desirable (DAI 31 - 35) and definite need of treatment (DAI ≥ 36) respectively. Conclusion: It can be concluded that there was no difference between the esthetic perception of dental and non-dental students. The self-perception for seeking orthodontic treatment was over-reported by participants compared to real requirement as assessed by orthodontic specialist. Dental esthetics has no psychological impact on academic performance and self-confidence as perceived by study participants.

Machine Learning Predictive Model as Clinical Decision Support System in Orthodontic Treatment Planning.

Diagnosis and treatment planning forms the crux of orthodontics, which orthodontists gain with years of expertise. Machine Learning (ML), having the ability to learn by pattern recognition, can gain this expertise in a very short duration, ensuring reduced error, inter-intra clinician variability and good accuracy. Thus, the aim of this study was to construct an ML predictive model to predict a broader outline of the orthodontic diagnosis and treatment plan. The sample consisted of 700 case records of orthodontically treated patients in the past ten years. The data were split into a training and a test set. There were 33 input variables and 11 output variables. Four ML predictive model layers with seven algorithms were created. The test set was used to check the efficacy of the ML-predicted treatment plan and compared with that of the decision made by the expert orthodontists. The model showed an overall average accuracy of 84%, with the Decision Tree, Random Forest and XGB classifier algorithms showing the highest accuracy ranging from 87-93%. Yet in their infancy stages, Machine Learning models could become a valuable Clinical Decision Support System in orthodontic diagnosis and treatment planning in the future.

Realistic high-resolution lateral cephalometric radiography generated by progressive growing generative adversarial network and quality evaluations

Realistic image generation is valuable in dental medicine, but still challenging for generative adversarial networks (GANs), which require large amounts of data to overcome the training instability. Thus, we generated lateral cephalogram X-ray images using a deep-learning-based progressive growing GAN (PGGAN). The quality of generated images was evaluated by three methods. First, signal-to-noise ratios of real/synthesized images, evaluated at the posterior arch region of the first cervical vertebra, showed no statistically significant difference (t-test, p = 0.211). Second, the results of an image Turing test, conducted by non-orthodontists and orthodontists for 100 randomly chosen images, indicated that they had difficulty in distinguishing whether the image was real or synthesized. Third, cephalometric tracing with 42 landmark points detection, performed on real and synthesized images by two expert orthodontists, showed consistency with mean difference of 2.08 ± 1.02 mm. Furthermore, convolutional neural network-based classification tasks were used to classify skeletal patterns using a real dataset with class imbalance and a dataset balanced with synthesized images. The classification accuracy for the latter case was increased by 1.5%/3.3% at internal/external test sets, respectively. Thus, the cephalometric images generated by PGGAN are sufficiently realistic and have potential to application in various fields of dental medicine.

Comparing intra-observer variation and external variations of a fully automated cephalometric analysis with a cascade convolutional neural net

The quality of cephalometric analysis depends on the accuracy of the delineating landmarks in orthodontic and maxillofacial surgery. Due to the extensive number of landmarks, each analysis costs orthodontists considerable time per patient, leading to fatigue and inter- and intra-observer variabilities. Therefore, we proposed a fully automated cephalometry analysis with a cascade convolutional neural net (CNN). One thousand cephalometric x-ray images (2 k × 3 k) pixel were used. The dataset was split into training, validation, and test sets as 8:1:1. The 43 landmarks from each image were identified by an expert orthodontist. To evaluate intra-observer variabilities, 28 images from the dataset were randomly selected and measured again by the same orthodontist. To improve accuracy, a cascade CNN consisting of two steps was used for transfer learning. In the first step, the regions of interest (ROIs) were predicted by RetinaNet. In the second step, U-Net detected the precise landmarks in the ROIs. The average error of ROI detection alone was 1.55 ± 2.17 mm. The model with the cascade CNN showed an average error of 0.79 ± 0.91 mm (paired t-test, p = 0.0015). The orthodontist’s average error of reproducibility was 0.80 ± 0.79 mm. An accurate and fully automated cephalometric analysis was successfully developed and evaluated.

Prototype of Augmented Reality Technology for Orthodontic Bracket Positioning: An In Vivo Study

To improve the accuracy of bracket placement in vivo, a protocol and device were introduced, which consisted of operative procedures for accurate control, a computer-aided design, and an augmented reality–assisted bracket navigation system. The present study evaluated the accuracy of this protocol. Methods: Thirty-one incisor teeth were tested from four participators. The teeth were bonded by novice and expert orthodontists. Compared with the control group by Boone gauge and the experiment group by augmented reality-assisted bracket navigation system, our study used for brackets measurement. To evaluate the accuracy, deviations of positions for bracket placement were measured. Results: The augmented reality-assisted bracket navigation system and control group were used in the same 31 cases. The priority of bonding brackets between control group or experiment group was decided by tossing coins, and then the teeth were debonded and the other technique was used. The medium vertical (incisogingival) position deviation in the control and AR groups by the novice orthodontist was 0.90 ± 0.06 mm and 0.51 ± 0.24 mm, respectively (p &lt; 0.05), and by the expert orthodontist was 0.40 ± 0.29 mm and 0.29 ± 0.08 mm, respectively (p &lt; 0.05). No significant changes in the horizontal position deviation were noted regardless of the orthodontist experience or use of the augmented reality–assisted bracket navigation system. Conclusion: The augmented reality–assisted bracket navigation system increased the accuracy rate by the expert orthodontist in the incisogingival direction and helped the novice orthodontist guide the bracket position within an acceptable clinical error of approximately 0.5 mm.

Fully automated estimation of arch forms in cone-beam CT with cubic B-spline approximation: Evaluation of digital dental models with missing teeth

Background and objectiveTo evaluate the automatic determination method for the arch form in cone-beam computed tomography (CBCT) images with cubic B-spline approximation on digital dental models using various types of missing teeth. MethodsThe maxilla and mandible from eight dental CBCT images with Class I occlusion and no missing teeth were used in this study. The dental arch determination algorithm using cubic B-spline approximation was modified by applying a smoothing function for reliable curve fitting to the digital dental models with various types of missing teeth. For evaluation, 31 scenarios with missing teeth were simulated, and cases with 1–8 missing teeth were divided into three groups: solitary, consecutive, and multiple (more than 4) missing teeth. The prediction accuracies of the dental arch forms were evaluated through comparisons with the gold standards for the digital dental models by two expert orthodontists. ResultsThe distance errors between the gold standards and the estimated results of the dental arch forms in all types of models were 0.237–1.740 mm. The mean distance errors of the solitary, consecutive, and multiple groups were 0.436 ± 0.124 mm (0.237–0.964 mm), 0.591 ± 0.250 mm (0.256–1.482 mm), and 0.679 ± 0.310 mm (0.254–1.740 mm), respectively. ConclusionsThe algorithm for predicting the arch form functioned reliably, even for digital dental models with various types of missing teeth, and could be applied to digital dentistry for applications such as orthodontic tooth setup, artificial tooth arrangement for denture fabrication, and implant guides.

Short-Term Effects of a Myofunctional Appliance on Atypical Swallowing and Lip Strength: A Prospective Study.

Atypical swallowing needs treatment in order to eliminate harmful interferences of the tongue, which prevent the harmonious growth of the stomatognathic system. The purpose of this study was to assess the effects of a functional appliance on the presence of atypical swallowing, analyzing the lip strength and the altered facial mimics. The effects of a myofunctional appliance (the Froggy Mouth) were evaluated on 40 children (6 males; 24 females; mean age 9.6 ± 2.17) with atypical swallowing—with tongue thrust diagnosed by an expert orthodontist—before and during a 6 month treatment. Data were analyzed over time with a paired samples t-test for normally distributed data. After 6 months of treatment, 33 children out of 40 achieved clinical correction of atypical swallowing due to their good compliance, even at an early stage. Seven children showed low compliance and did not obtain any result. Lip strength in compliant subjects went from 190.30 ± 86.04 cN to 489.39 ± 123.36 cN (t = p < 0.001). Facial mimics improved in 28 out of 33 compliant subjects, and four children with the initial diagnosis of labial incompetence achieved correction. This observational study demonstrates the short-term efficacy of this myofunctional appliance in the treatment of atypical swallowing, achieving correction of the facial mimics and labial incompetence with a significant improvement of the lip strength.

Unilateral sagittal split osteotomy: effect on mandibular symmetry in the treatment of class III with laterognathia

The bilateral sagittal split osteotomy is considered the standard surgery to correct facial asymmetries. More recently, unilateral sagittal split osteotomy (USSO) was used to treat such malocclusions.AimTo assess facial symmetry following USSO in the treatment of class III laterognathia.MethodsFrontal facial photographs of four groups of patients were assessed: (1) pre-surgical group (n = 30) with skeletal asymmetry, (2) postsurgical group assessing patients of the first group 2 years after USSO, (3) control group (n = 30) of patients judged to have harmonious facial norms, and (4) mirrored group (n = 30) in which the control photographs were altered by duplicating the right half side of the face to replace the left half, thus creating perfectly symmetrical faces. All 120 photographs were distributed to 40 expert orthodontists to evaluate and score facial symmetry using the visual analog scale. Skin sensitivity and temporomandibular joint (TMJ) disorders were also assessed clinically pre and postsurgically.ResultsStatistically significant differences were observed between the pre-surgical group and each of the postsurgical and control groups (p < 0.001). The control and postsurgical groups received similar scores of symmetry (p = 0.774). The mirrored group received statistically significantly higher symmetry scores than either of the control or the postsurgical groups (p < 0.001). A reduction in TMJ disorders was noted after USSO and all patients reported normal skin sensation 2 years post-surgery.ConclusionWhen indicated, USSO is a dependable and practical surgical approach to correct facial asymmetries associated with class III malocclusion.

Residents' journal review

Residents' journal review

Semi-automatic and robust determination of dental arch form in dental cone-beam CT with B-spline approximation

Background and objectiveThe dental arch form is generally used as a base for planning orthodontic treatments. It is, therefore, vital to determine the proper individual dental arch form for more accurate orthodontic treatment. We aimed to develop and validate a robust algorithm for semi-automatic determination of the dental arch form in dental cone-beam CT (CBCT) images with the cubic B-spline approximation. MethodsOur algorithm consists of tooth segmentation, determination of an occlusal plane, and generation of intersection points between the teeth and the offset plane from the occlusal plane in CBCT images. By fitting a curve to the intersection points using the cubic B-spline curve approximation, the dental arch form was finally determined. The accuracy of the dental arch forms was evaluated by comparison with gold standards determined by an expert orthodontist. ResultsThirteen dental CBCT scans from nine subjects were enrolled in this study. From the CBCT scans, 13 maxillary arch forms and 11 mandibular arch forms with Class I occlusion were determined by our proposed algorithm and evaluated for validation. The mean error between the dental arch forms of gold standards and our method using the cubic B-spline was 0.413 ± 0.092 mm (range, 0.264–0.587 mm). ConclusionsOur proposed method showed reliable accuracy of determining the dental arch forms for the maxilla and mandible. These results suggested that this method might be used for planning automatic tooth setup for individual patients.

A Comparative Study of the Examination Pattern of Panoramic Radiographs Using Eye-tracking Software

To analyze the differences between novice and expert orthodontists examining panoramic radiographs with incidental findings of varying difficulty. The null hypothesis states no difference in the examination pattern of panoramic radiographs between novice and expert orthodontists. Expert and novice orthodontic observers were asked to examine six panoramic radiographs with incidental findings of varying difficulty. The eye-tracking software recorded and analyzed their eye movements during the examination. After examining each radiograph, the observers were asked questions about the radiograph. All these collected data were analyzed to compare the performance of the two sets of observers. The total number of observers was 72 in the novice group and 64 in the expert group. There was only one statistically significant finding between the two groups of observers, which was the end time. Expert orthodontists recorded longer panoramic radiograph examination times. There is no significant difference in the abilities of expert and novice orthodontists to examine panoramic radiographs and identify incidental findings. Orthodontists might benefit from additional education and continued training in examining and reporting radiographs commonly utilized by this specific group of dental specialists, such as panoramic and cephalometric radiographs.

PROBLEM BASED LEARNING

Introduction: The research for finding the most effective teaching methodis still on. The aim of current study was to find out the perceptions of dental interns after aproblem based learning (PBL) sessions on a topic of orthodontic case planning. Study Design:Experimental, Quasi study. Setting: Orthodontic Dental Section, Faisalabad Medical University.Period: 15.8.2017 to 5.2.2018. Materials &amp; Methods: Thirty two dental interns were selectedat Orthodontic Dental Section, Faisalabad Medical University. On initial case planning sessions,baseline theoretical knowledge was provided on the topic of ‘Premolar extractions’. In betweenthe sessions dental interns were asked to answer five multiple choice questions relative to oneorthodontic case (OPG, Lateral cephalograms, Photographs) they were given. On a final caseplanning sessions, orthodontic case discussion case took place with an expert orthodontist,at the end of which dental interns were asked to rate their experiences about PBL sessionby filling questionnaire anonymously. Results: Results showed that dental interns perceivedPBL to stimulate their attentiveness, interest, and interactivity with fellow interns, motivation foradditional case study and learning efficacy. Conclusion: Perceptions of dental interns werepositive after a problem based learning attempt on a topic of orthodontic case planning.

Facial attractiveness of skeletal class I and class II malocclusion as perceived by laypeople, patients and clinicians.

Physical attractiveness is dependent on facial appearance. The facial profile plays a crucial role in facial attractiveness and can be improved with orthodontic treatment. The aesthetic assessment of facial appearance may be influenced by the cultural background and education of the assessor and dependent upon the experience level of dental professionals. This study aimed to evaluate how the sagittal jaw relationship in Class I and Class II individuals affects facial attractiveness, and whether the assessor's professional education and background affect the perception of facial attractiveness. Facial silhouettes simulating mandibular retrusion, maxillary protrusion, mandibular retrusion combined with maxillary protrusion, bimaxillary protrusion and severe bimaxillary protrusion in class I and class II patients were assessed by five groups of people with different backgrounds and education levels (i.e., 23 expert orthodontists, 21 orthodontists, 15 maxillofacial surgeons, 19 orthodontic patients and 28 laypeople). Straight facial profiles were judged to be more attractive than convex profiles due to severe mandibular retrusion and to mandibular retrusion combined with maxillary protrusion (all P<0.05). Convex profiles due to a slightly retruded position of the mandible were judged less attractive by clinicians than by patients and laypeople (all P<0.05). Convex facial profiles are less attractive than Class I profiles. The assessment of facial attractiveness is dependent on the assessor's education and background. Laypeople and patients are considerably less sensitive to abnormal sagittal jaw relationships than orthodontists.

Bayesian-Based Decision Support System for Assessing the Needs for Orthodontic Treatment.

ObjectivesIn this study, a clinical decision support system was developed to help general practitioners assess the need for orthodontic treatment in patients with permanent dentition.MethodsWe chose a Bayesian network (BN) as the underlying model for assessing the need for orthodontic treatment. One thousand permanent dentition patient data sets chosen from a hospital record system were prepared in which one data element represented one participant with information for all variables and their stated need for orthodontic treatment. To evaluate the system, we compared the assessment results based on the judgements of two orthodontists to those recommended by the decision support system.ResultsIn a BN decision support model, each variable is modelled as a node, and the causal relationship between two variables may be represented as a directed arc. For each node, a conditional probability table is supplied that represents the probabilities of each value of this node, given the conditions of its parents. There was a high degree of agreement between the two orthodontists (kappa value = 0.894) in their diagnoses and their judgements regarding the need for orthodontic treatment. Also, there was a high degree of agreement between the decision support system and orthodontists A (kappa value = 1.00) and B (kappa value = 0.894).ConclusionsThe study was the first testing phase in which the results generated by the proposed system were compared with those suggested by expert orthodontists. The system delivered promising results; it showed a high degree of accuracy in classifying patients into groups needing and not needing orthodontic treatment.