Browsing by Author "Orthodontics and Oral Facial Genetics, School of Dentistry"
Now showing 1 - 10 of 56
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 Associations between Oral Health and Cannabis Use among Adolescents and Young Adults: Implications for Orthodontists(MDPI, 2022-11-18) Le, Austin; Khoo, Edmund; Palamar, Joseph J.; Orthodontics and Oral Facial Genetics, School of DentistryCannabis use is prevalent among adolescents and young adults in the US. Virtually all modes of cannabis consumption involve the oral cavity, and previous studies have linked cannabis use with poorer oral health. We sought to identify associations between cannabis use and various oral health outcomes and behaviors among individuals 12–25 years of age, and to discuss implications for orthodontists who largely interact with this age group over an extended period of treatment time. We examined data from patient electronic health records (N = 14,657) obtained between 2015 and 2021. Associations between lifetime and current self-reported cannabis use and several oral health outcomes or related behaviors that reflect periodontal health, caries status, oral lesions, and physical integrity of tooth structure and restorations were examined in a bivariable and multivariable manner, controlling for patient age, sex, and self-reported tobacco and alcohol use. Reporting lifetime cannabis use was associated with higher risk for having oral lesions (aPR = 1.41, 95% CI: 1.07–1.85), bruxism (aPR = 1.31, 95% CI: 1.09–1.58), and frequent consumption of sugary beverages and snacks (aPR = 1.27, 95% CI: 1.12–1.41). Reporting current cannabis use was associated with higher risk for oral lesions (aPR = 1.45, 95% CI: 1.03–2.06) and frequent consumption of sugary beverages and snacks (aPR = 1.26, 95% CI: 1.07–1.48). Cannabis users aged 12–25 are at increased risk for bruxism, oral lesions, and frequent consumption of sugary beverages and snacks. Orthodontists and other dental professionals should probe for drug use and be cognizant of increased risk for oral health problems in patients that report actively using cannabis.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 CBCT of skeletal changes following rapid maxillary expansion to increase arch-length with a development-dependent bonded or banded appliance(Allen Press, 2013) Kanomi, Ryuzo; Deguchi, Toru; Kakuno, Eriko; Takano-Yamamoto, Teruko; Roberts, W. Eugene; Orthodontics and Oral Facial Genetics, School of DentistryObjective: To assess the three-dimensional (3D) skeletal response to a standardized 5 mm of rapid maxillary expansion (RME) in growing children (6-15 years) with maxillary width deficiency and crowding. Materials and methods: A bonded appliance was used prior to the eruption of the maxillary first premolars (Mx4s), and a banded appliance was used thereafter. A consecutive sample of 89 patients (29 boys and 60 girls) from a large pediatric dentistry and orthodontics practice was divided into four groups: 1) 6-8 years old (n = 26), 2) 9-11 years old with unerupted Mx4s (n = 21), 3) 9-11 years with erupted Mx4s (n = 23), and 4) 12-15 years (n = 19). For all patients, the 3D evaluation of dental and skeletal effects was performed with cone-beam computed tomography (CBCT). Results: For both appliances in all patients, CBCT confirmed a triangular pattern of expansion in both the frontal and sagittal planes. Overall, both appliances produced significant maxillary expansion (>80% of the 5-mm activation), but older children showed a progressively more dental (less skeletal) response. Comparison of the two types of expanders in the crossover sample, children aged 9-11 years, showed that the bonded RME produced the most efficient skeletal expansion in the preadolescent sample. Increased maxillary width at the level of the zygomaticomaxillary suture was the best indicator for development of maxillary arch circumference. Conclusion: Development-dependent appliances (bonded RPE before Mx4s erupt, and a banded device thereafter) provided optimal RME treatment for all children from age 6-15 years.Item Clinical Outcomes of 0.018-Inch and 0.022-Inch Bracket Slot Using the ABO Objective Grading System(E.H Angle Education and Research Foundation, 2010-05-01) Detterline, David A.; Isikbay, Serkis C.; Brizendine, Edward J.; Kula, Katherine S.; Orthodontics and Oral Facial Genetics, School of DentistryObjective: To determine if there is a significant difference in the clinical outcomes of cases treated with 0.018-inch brackets vs 0.022-inch brackets according to the American Board of Orthodontics (ABO) Objective Grading System (OGS). Materials and Methods: Treatment time and the ABO-OGS standards in alignment/rotations, marginal ridges, buccolingual inclination, overjet, occlusal relationships, occlusal contacts, interproximal contacts, and root angulations were used to compare clinical outcomes between a series of 828 consecutively completed orthodontic cases (2005–2008) treated in a university graduate orthodontic clinic with 0.018-inch- and 0.022-inch-slot brackets. Results: A two-sample t-test showed a significantly shorter treatment time and lower ABO-OGS score in four categories (alignment/rotations, marginal ridges, overjet, and root angulations), as well as lower total ABO-OGS total score, with the 0.018-inch brackets. The ANCOVA—adjusting for covariants of discrepancy index, age, gender, and treatment time—showed that the 0.018-inch brackets scored significantly lower than the 0.022-inch brackets in both the alignment/rotations category and total ABO-OGS score. Conclusions: There were statistically, but not clinically, significant differences in treatment times and in total ABO-OGS scores in favor of 0.018-inch brackets as compared with the 0.022-inch brackets in a university graduate orthodontic clinic (2005–2008).Item The combined effects of salivas and occlusal indicators on occlusal contact forces(Wiley, 2019) Beninati, Christopher J.; Katona, Thomas R.; Orthodontics and Oral Facial Genetics, School of DentistryBackground Some occlusal detection products are designed for use on dry teeth, but this is not always achieved. Others are suited for dry and wet applications. Objective The objective of this study is to assess the combined effects, on occlusal contact forces, of two previously studied affecting variables—occlusal detection products and saliva. Methods We used a full‐arch dentiform with three occlusal detection products (an articulating film, an articulation paper and T‐Scan) in combination with human (HS) and an artificial saliva. The maxillary arch assembly, weighing ~54 N (the maximum bite force), was lowered onto (occlusion) and lifted off (disclusion) of the mandibular arch through 10 cycles by a mechanical testing machine. The forces and moments acting on the mandibular arch were continuously recorded by a load cell that supported it. Results The maximum values of Flateral (the in‐occlusal plane component of the occlusal contact force) were analysed by occlusion/disclusion separately using one‐way ANOVA, with factor for group type to identify the significant effect of salivas on products, effect of products, effect of salivas with products, effect of human saliva. A difference in occlusion and/or in disclusion was considered different. Statistical differences (P < 0.0001) in Flateral were found in: dry product vs product + HS, dry product vs product + artificial saliva (with articulating film and T‐Scan) and HS vs product + HS (with articulation paper and T‐Scan). Conclusion All products were affected by the salivas, except articulation paper by artificial saliva.Item A comprehensive analysis of normal variation and disease-causing mutations in the human DSPP gene(Wiley, 2008-12) McKnight, Dianalee A.; Hart, P. Suzanne; Hart, Thomas C.; Hartsfield, James K.; Wilson, Anne; Wright, J. Timothy; Fisher, Larry W.; Orthodontics and Oral Facial Genetics, School of DentistryWithin nine dentin dysplasia (DD) (type II) and dentinogenesis imperfecta (type II and III) patient/families, seven have 1 of 4 net -1 deletions within the approximately 2-kb coding repeat domain of the DSPP gene while the remaining two patients have splice-site mutations. All frameshift mutations are predicted to change the highly soluble DSPP protein into proteins with long hydrophobic amino acid repeats that could interfere with processing of normal DSPP and/or other secreted matrix proteins. We propose that all previously reported missense, nonsense, and splice-site DSPP mutations (all associated with exons 2 and 3) result in dominant phenotypes due to disruption of signal peptide-processing and/or related biochemical events that also result in interference with protein processing. This would bring the currently known dominant forms of the human disease phenotype in agreement with the normal phenotype of the heterozygous null Dspp (-/+) mice. A study of 188 normal human chromosomes revealed a hypervariable DSPP repeat domain with extraordinary rates of change including 20 slip-replication indel events and 37 predominantly C-to-T transition SNPs. The most frequent transition in the primordial 9-basepair (bp) DNA repeat was a sense-strand CpG site while a CpNpG (CAG) transition was the second most frequent SNP. Bisulfite-sequencing of genomic DNA showed that the DSPP repeat can be methylated at both motifs. This suggests that, like plants and some animals, humans methylate some CpNpG sequences. Analysis of 37 haplotypes of the highly variable DSPP gene from geographically diverse people suggests it may be a useful autosomal marker in human migration studies.Item Correlation between Advanced Dental Admission Test performance and dental MATCH success(Wiley, 2021-04) Deek, Joseph; Albright, David A.; John, Vanchit; Tang, Qing; Stewart, Kelton T.; Orthodontics and Oral Facial Genetics, School of DentistryPurpose/Objectives The Advanced Dental Admissions Test was developed in 2016 to aid residency programs evaluate qualified applicants. Since its conception, however, there have been no studies seeking to evaluate the usefulness of the exam regarding an applicants’ ability to match with a residency program through the Postdoctoral Dental Matching Program (MATCH). The aim of this study was to evaluate the impact of the Advanced Dental Admission Test performance on student MATCH success into a post-doctoral pediatric residency program. Methods This retrospective study evaluated the academic records of pediatric residency applicants using the ADEA PASS and MATCH program between 2017 and 2019. Five scholastic and 7 demographic variables were extracted from student ADEA PASS applications. Applicant MATCH status and preference was obtained from the Postdoctoral Dental Matching Program. Descriptive statistics for each application cycle was calculated and used to evaluate applicant demographic and scholastic data. Correlation coefficients assessed for associations between scholastic/demographic factors and MATCH status/preference. Logistic regression models estimated the probability of MATCH status/preference. Significance was set at 5%. Results An association was found between ADAT scores and MATCH status, but the influence was minimal (odds ratio: 1.004, 95% confidence interval: 1.001-1.008). Applicant age (P < 0.0216) and dental schools that ranked students (P < 0.0002) were the most significant factors for MATCH status and preference, respectively. Conclusions ADAT scores played a minimal role in applicants matching to pediatric residency programs. Applicant age and schools that provide class ranks were found to be significant predictors when considering MATCH status and preference to pediatric residency programs.Item COVID-19: What do we know?(Elsevier, 2020-09-21) Marshall, Steve; Duryea, Michael; Huang, Greg; Kadioglu, Onur; Mah, James; Palomo, Juan Martin; Rossouw, Emile; Stappert, Dina; Stewart, Kelton; Tufekci, Eser; Orthodontics and Oral Facial Genetics, School of DentistryCoronavirus disease 2019 (COVID-19) is a global pandemic caused by the pathogen severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2).1 Preliminary assessments suggest the virus is highly transmittable and infectious,2, 3, 4, 5, 6, 7 with similarities in nosocomial and super-spreading events seen with severe acute respiratory syndrome coronavirus 1 (SARS-CoV-1) in 2003.8 Patients infected with SARS-CoV-2 display a wide range of host responses including no symptoms, mild nonrespiratory symptoms, severe respiratory illness, or organ dysfunction and death.1,5 The American Association of Orthodontists Council on Scientific Affairs was charged with examining the literature to determine the best evidence for questions pertaining to COVID-19 and its impact on the practice of orthodontics.