Browsing by Author "Turkkahraman, Hakan"
Now showing 1 - 10 of 19
Results Per Page
Sort Options
Item A machine learning model for orthodontic extraction/non-extraction decision in a racially and ethnically diverse patient population(Elsevier, 2023-09) Mason, Taylor; Kelly, Kynnedy M.; Eckert, George; Dean, Jeffrey A.; Dundar, M. Murat; Turkkahraman, Hakan; Orthodontics and Oral Facial Genetics, School of DentistryIntroduction The purpose of the present study was to create a machine learning (ML) algorithm with the ability to predict the extraction/non-extraction decision in a racially and ethnically diverse sample. Methods Data was gathered from the records of 393 patients (200 non-extraction and 193 extraction) from a racially and ethnically diverse population. Four ML models (logistic regression [LR], random forest [RF], support vector machine [SVM], and neural network [NN]) were trained on a training set (70% of samples) and then tested on the remaining samples (30%). The accuracy and precision of the ML model predictions were calculated using the area under the curve (AUC) of the receiver operating characteristics (ROC) curve. The proportion of correct extraction/non-extraction decisions was also calculated. Results The LR, SVM, and NN models performed best, with an AUC of the ROC of 91.0%, 92.5%, and 92.3%, respectively. The overall proportion of correct decisions was 82%, 76%, 83%, and 81% for the LR, RF, SVM, and NN models, respectively. The features found to be most helpful to the ML algorithms in making their decisions were maxillary crowding/spacing, L1-NB (mm), U1-NA (mm), PFH:AFH, and SN-MP(̊), although many other features contributed significantly. Conclusions ML models can predict the extraction decision in a racially and ethnically diverse patient population with a high degree of accuracy and precision. Crowding, sagittal, and vertical characteristics all featured prominently in the hierarchy of components most influential to the ML decision-making process.Item A Novel Machine Learning Model for Predicting Orthodontic Treatment Duration(MDPI, 2023-08-23) Volovic, James; Badirl, Sarkhan; Ahmad, Sunna; Leavit, Landon; Mason, Taylor; Bhamidipalli, Surya Sruthi; Eckert, George; Albright, David; Turkkahraman, Hakan; Orthodontics and Oral Facial Genetics, School of DentistryIn the field of orthodontics, providing patients with accurate treatment time estimates is of utmost importance. As orthodontic practices continue to evolve and embrace new advancements, incorporating machine learning (ML) methods becomes increasingly valuable in improving orthodontic diagnosis and treatment planning. This study aimed to develop a novel ML model capable of predicting the orthodontic treatment duration based on essential pre-treatment variables. Patients who completed comprehensive orthodontic treatment at the Indiana University School of Dentistry were included in this retrospective study. Fifty-seven pre-treatment variables were collected and used to train and test nine different ML models. The performance of each model was assessed using descriptive statistics, intraclass correlation coefficients, and one-way analysis of variance tests. Random Forest, Lasso, and Elastic Net were found to be the most accurate, with a mean absolute error of 7.27 months in predicting treatment duration. Extraction decision, COVID, intermaxillary relationship, lower incisor position, and additional appliances were identified as important predictors of treatment duration. Overall, this study demonstrates the potential of ML in predicting orthodontic treatment duration using pre-treatment variables.Item Can we predict orthodontic extraction patterns by using machine learning?(Wiley, 2023) Leavitt, Landon; Volovic, James; Steinhauer, Lily; Mason, Taylor; Eckert, George; Dean, Jeffrey A.; Dundar, M. Murat; Turkkahraman, Hakan; Orthodontics and Oral Facial Genetics, School of DentistryObjective To investigate the utility of machine learning (ML) in accurately predicting orthodontic extraction patterns in a heterogeneous population. Materials and Methods The material of this retrospective study consisted of records of 366 patients treated with orthodontic extractions. The dataset was randomly split into training (70%) and test sets (30%) and was stratified according to race/ethnicity and gender. Fifty-five cephalometric and demographic input data were used to train and test multiple ML algorithms. The extraction patterns were labelled according to the previous treatment plan. Random Forest (RF), Logistic Regression (LR), and Support Vector Machine (SVM) algorithms were used to predict the patient's extraction patterns. Results The highest class accuracy percentages were obtained for the upper and lower 1st premolars (U/L4s) (RF: 81.63%, LR: 63.27%, SVM: 63.27%) and upper 1st premolars only (U4s) extraction patterns (RF: 61.11%, LR: 72.22%, SVM: 72.22%). However, all methods revealed low class accuracy rates (<50%) for the upper 1st and lower 2nd premolars (U4/L5s), upper 2nd and lower 1st premolars (U5/L4s), and upper and lower 2nd premolars (U/L5s) extraction patterns. For the overall accuracy, RF yielded the highest percentage with 54.55%, followed by SVM with 52.73% and LR with 49.09%. Conclusion All tested supervised ML techniques yielded good accuracy in predicting U/L4s and U4s extraction patterns. However, they predicted poorly for the U4/L5s, U5/L4s, and U/L5s extraction patterns. Molar relationship, mandibular crowding, and overjet were found to be the most predictive indicators for determining extraction patterns.Item Effects of Rapid Maxillary Expansion and Facemask Therapy on the Soft Tissue Profiles of Class III Patients at Different Growth Stages(Thieme, 2019) Can, Fatma Selen Ozzeybek; Turkkahraman, Hakan; Orthodontics and Oral Facial Genetics, School of DentistryObjectives The aim of this study was to evaluate the effects of rapid maxillary expansion (RME) and facemask therapy on the soft tissue profiles of class III patients at different growth stages. Materials and Methods Forty-five subjects (23 females and 22 males) were divided into prepubertal, pubertal, and postpubertal groups. Bonded type RME appliances and Petit-type facemasks were fitted to each patient, and intraoral elastics were applied from the hooks of the RME appliance to the facemask. Statistical Analysis All measurements were statistically analyzed with SPSS version 18.0 (SPSS Inc., Chicago, IL, United States) for Windows. Repeated-measures of ANOVA and posthoc Tukey tests were used to compare the groups. Results The soft tissue nasion, pronasale, subnasale, soft tissue A point, and labrale superior landmarks were all displaced forward and downward, and the most dramatic changes were recorded in the pubertal group. The labrale inferior, soft tissue B point, soft tissue pogonion, and soft tissue menton landmarks moved backward and downward in all groups, and the greatest displacements were observed in the pubertal group. Conclusions The soft tissue profiles improved significantly and became more convex in all treatment groups. Although, the most favorable facial changes were observed in the pubertal growth stage, the treatments applied in the postpubertal stage also elicited significant changes and should thus be considered viable treatment options.Item Embracing the Unprecedented Pace of Change: Artificial Intelligence's Impact on Dentistry and Beyond(Thieme, 2023) Turkkahraman, Hakan; Orthodontics and Oral Facial Genetics, School of DentistryItem Histomorphometric and Histopathologic Evaluation of the Effects of Systemic Fluoride Intake on Orthodontic Tooth Movement(Thieme, 2019) Zorlu, Fatma Yalcin; Darici, Hakan; Turkkahraman, Hakan; Orthodontics and Oral Facial Genetics, School of DentistryObjectives The aim of this study was to determine the effects of systemic fluoride intake on orthodontic tooth movement with histomorphometric and histopathologic methods. Materials and Methods Forty-eight Wistar albino rats were randomly divided into four groups of 12 rats each. Group I received fluoridated water and underwent orthodontic tooth movement. Group II received fluoridated water and did not undergo orthodontic tooth movement. Group III received nonfluoridated water and underwent orthodontic tooth movement. Group IV received nonfluoridated water and did not undergo orthodontic tooth movement. At the beginning of the experiment (T1), impressions were taken from the maxilla of the rats in groups I and III under general anesthesia, and a NiTi closed coil spring appliance was ligated between the left maxillary central incisors and maxillary first molar. The orthodontic force applied was approximately 75 g, and the duration of the experimental period was 18 days. During the experimental period, appliances were controlled daily. At the end of the experimental period (T2), the rats were sacrificed with an overdose of a ketamine/xylasine combination, and their impressions were obtained. The upper first molars were subsequently dissected for histological examination. Incisor–molar distance, number of osteoblasts, number of osteoclasts and periodontal ligament (PDL) space widths on the compression and tension sides were measured. Statistical Analysis All measurements were statistically analyzed with SPSS for Windows version 18.0 (SPSS Inc., Chicago, IL, USA). Repeated measures ANOVA and posthoc Tukey tests were used to compare the groups. Results No statistically significant difference was found with respect to the amount of tooth movement between the fluoridated and nonfluoridated groups (p > 0.05). Orthodontic force application increased the number of osteoblasts at the tension sides and reduced it at the compression sides (p < 0.001). An increased number of osteoclasts was observed in the nonfluoridated group relative to the fluoridated group (p < 0.01). Conclusions No difference was observed with respect to the amount of tooth movement between the fluoridated and nonfluoridated groups. Fluoride significantly reduced the number of osteoclasts in the experimental groups.Item A novel hypothesis based on clinical, radiological, and histological data to explain the dentinogenesis imperfecta type II phenotype(Taylor & Francis, 2019) Turkkahraman, Hakan; Galindo, Fernando; Tulu, Ustun Serdar; Helms, Jill A.; Orthodontics and Oral Facial Genetics, School of DentistryPurpose/Aim: The aim of this study was to explore whether dentinogenesis imperfecta (DGI)-related aberrations are detectable in odontogenic tissues. Materials and Methods: Morphological and histological analyses were carried out on 3 teeth (two maxillary 1st molars, one maxillary central incisor) extracted from a patient with DGI Type II. A maxillary 2nd molar teeth extracted from a healthy patient was used as control. A micro-computed tomographic (μCT) data-acquisition system was used to scan and reconstruct samples. Pentachrome and picrosirius red histologic stains were used to analyze odontogenic tissues and their collagenous matrices. Results: Our findings corroborate DGI effects on molar and incisor root elongation, and the hypo-mineralized state of DGI dentin. In addition to these findings, we discovered changes to the DGI pulp cavity: Reactionary dentin formation, which we theorize is exacerbated by the early loss of enamel, nearly obliterated an acellular but still-vascularized DGI pulp cavity. We also discovered an accumulation of lamellated cellular cementum at the root apices, which we hypothesize compensates for the severe and rapid attrition of the DGI tooth. Conclusions: Based on imaging and histological data, we propose a novel hypothesis to explain the complex dental phenotypes observed in patients with DGI Type II.Item A novel machine learning model for class III surgery decision(Springer, 2022-08) Lee, Hunter; Ahmad, Sunna; Frazier, Michael; Dundar, Mehmet Murat; Turkkahraman, Hakan; Orthodontics and Oral Facial Genetics, School of DentistryPurpose The primary purpose of this study was to develop a new machine learning model for the surgery/non-surgery decision in class III patients and evaluate the validity and reliability of this model. Methods The sample consisted of 196 skeletal class III patients. All the cases were allocated randomly, 136 to the training set and the remaining 60 to the test set. Using the test set, the success rate of the artificial neural network model was estimated, along with a 95% confidence interval. To predict surgical cases, we trained a binary classifier using two different methods: random forest (RF) and logistic regression (LR). Results Both the RF and the LR model showed high separability when classifying each patient for surgical or non-surgical treatment. RF achieved an area under the curve (AUC) of 0.9395 on the test set. 95% confidence intervals were computed by bootstrap sampling as lower bound = 0.7908 and higher bound = 0.9799. On the other hand, LR achieved an AUC of 0.937 on the test set. 95% confidence intervals were computed by bootstrap sampling as lower bound = 0.8467 and higher bound = 0.9812. Conclusions RF and LR machine learning models can be used to generate accurate and reliable algorithms to successfully classify patients up to 90%. The features selected by the algorithms coincide with the clinical features that we as clinicians weigh heavily when determining a treatment plan. This study further supports that overjet, Wits appraisal, lower incisor angulation, and Holdaway H angle can be used as strong predictors in assessing a patient’s surgical needs.Item Precision and Accuracy Assessment of Cephalometric Analyses Performed by Deep Learning Artificial Intelligence with and without Human Augmentation(MDPI, 2023-06-08) Panesar, Sumer; Zhao , Alyssa; Hollensbe, Eric; Wong, Ariel; Bhamidipalli, Surya Sruthi; Eckert, George; Dutra, Vinicius; Turkkahraman, Hakan; Orthodontics and Oral Facial Genetics, School of DentistryThe aim was to assess the precision and accuracy of cephalometric analyses performed by artificial intelligence (AI) with and without human augmentation. Four dental professionals with varying experience levels identified 31 landmarks on 30 cephalometric radiographs twice. These landmarks were re-identified by all examiners with the aid of AI. Precision and accuracy were assessed by using intraclass correlation coefficients (ICCs) and mean absolute errors (MAEs). AI revealed the highest precision, with a mean ICC of 0.97, while the dental student had the lowest (mean ICC: 0.77). The AI/human augmentation method significantly improved the precision of the orthodontist, resident, dentist, and dental student by 3.26%, 2.17%, 19.75%, and 23.38%, respectively. The orthodontist demonstrated the highest accuracy with an MAE of 1.57 mm/°. The AI/human augmentation method improved the accuracy of the orthodontist, resident, dentist, and dental student by 12.74%, 19.10%, 35.69%, and 33.96%, respectively. AI demonstrated excellent precision and good accuracy in automated cephalometric analysis. The precision and accuracy of the examiners with the aid of AI improved by 10.47% and 27.27%, respectively. The AI/human augmentation method significantly improved the precision and accuracy of less experienced dental professionals to the level of an experienced orthodontist.Item Precision and accuracy assessment of single and multicamera three-dimensional photogrammetry compared with direct anthropometry(Allen Press, 2022) Staller, Sable; Anigbo, Justina; Stewart, Kelton; Dutra, Vinicius; Turkkahraman, Hakan; Orthodontics and Oral Facial Genetics, School of DentistryObjectives: To assess the precision and accuracy of single-camera photogrammetry (SCP) and multicamera photogrammetry (MCP) compared with direct anthropometry (DA). Materials and methods: A total of 30 participants were recruited, and 17 soft tissue landmarks were identified and used to complete a total of 16 measurements. Using SCP and MCP, two three-dimensional (3D) images were acquired from each participant. All 3D measurements and direct measurements were measured twice by the same operator to assess intraexaminer repeatability. Intraclass coefficients (ICCs) were used to evaluate intraexaminer repeatability and interexaminer agreement of the methods. Nonparametric bootstrap analyses were used to compare the means of the measurements among the three methods. Results: All three methods showed excellent intraexaminer repeatability (ICCs > 0.90), except interpupillary distance (ICC = 0.86) measured by SCP. Both SCP and MCP showed excellent interexaminer agreement (ICCs > 0.90), except interpupillary distance (ICC = 0.79), left gonion-pogonion (ICC = 0.74), and columella-subnasale-labrale superior angle (ICC = 0.86) measured by SCP. Overall, there was good agreement between methods, except for columella-subnasale-labrale superior angle (ICC = 0.40) between SCP and MCP. Conclusions: Both SCP and MCP techniques were found to be reliable and valid options for 3D facial imaging. SCP produced slightly larger mean values for several measurements, but the differences were within a clinically acceptable range. Because of the larger margin of errors, measurements including the gonial area and subnasale should be assessed with caution.