Browsing by Author "Eckert, George"
Now showing 1 - 10 of 50
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 Accuracy of Orthodontic Soft Tissue Prediction Software between Different Ethnicities(2019) Stewart, Kelton; Patel, Pranali; Eckert, George; Rigsbee III, OH; Hughes, Jay; Utreja, AchintObjective: The objective of this study was to assess the accuracy of the soft tissue prediction module of Dolphin Imaging Software (DIS) in patients requiring extractions as part of the orthodontic treatment plan and compare its accuracy between different ethnicities. Materials and Methods: Initial and final records of 57 patients from three ethnic groups (African Americans, Caucasians, and Hispanics) who completed orthodontic treatment were included for assessment. The identified cases were managed non-surgically with dental extractions. A predictive profile was generated using DIS and compared to post-treatment lateral photographs. Actual and predictive profile photographs were compared using five designated parameters. The assessment parameters were evaluated using a manual protractor. ANOVA was used to compare differences between actual and predicted parameters between the specified groups and ICC was used to assess correlations between the data. Results: Neither ethnicity nor gender had a significant effect on the difference between predicted and final values. No significant difference was noted between the predicted and final images for the nasolabial angle. Significant differences were observed for the mentolabial fold, upper lip to E-line, and lower lip to E-line between predicted and actual images. Additionally, soft tissue convexity was significantly different (p=0.019). Additionally, a clinically significant difference was found for the mentolabial fold. Conclusion: Ethnicity and gender had no impact on the accuracy of predicted and actual image parameters. Overall, DIS demonstrated acceptable accuracy when simulating soft tissue changes after extraction therapy. Additional research on the accuracy of the software is warranted.Item Adiposity has unique influence on the renin-aldosterone axis and blood pressure in black children(Elsevier, 2013-11) Yu, Zhangsheng; Eckert, George; Liu, Hai; Pratt, J. Howard; Tu, Wanzhu; Medicine, School of MedicineOBJECTIVE: To comparatively examine the effects of adiposity on the levels of plasma renin activity (PRA), plasma aldosterone concentration (PAC), and aldosterone-renin ratio (ARR) in young black and white children. STUDY DESIGN: We prospectively assessed 248 black and 345 white children and adolescents. A novel analytical technique was used to assess the concurrent influences of age and body mass index (BMI) on PRA, PAC, and ARR. The estimated effects were depicted by colored contour plots. RESULTS: In contrast to whites, blacks had lower PRA (2.76 vs 3.36 ng/mL/h; P < .001) and lower PAC (9.01 vs 14.59 ng/dL; P < .001). In blacks, BMI was negatively associated with PRA (P = .001), consistent with an association with a more expanded plasma volume; there was no association with PAC. In whites, BMI was positively associated with PAC (P = .005); we did not detect a BMI-PRA association. The effects of BMI on ARR were directionally similar in the two race groups but more pronounced in blacks. Mean systolic blood pressure was greater in blacks with lower PRA (P < .01), higher PAC (P = .015), and higher ARR (P = .49). CONCLUSIONS: An increase in adiposity was associated with a suppressed PRA in blacks and an increase in PAC in whites. The unique relationship between adiposity and renin-aldosterone axis in blacks suggests the possible existence of a population-specific mechanism characterized by volume expansion, which could in turn enhance the influences of adiposity on blood pressure in black children and adolescents.Item The association of malocclusion and trumpet performance(2015) Kula, Katherine; Cilingir, H. Zeynep; Eckert, George; Dagg, Jack; Ghoniema, Ahmed; Department of Orthodontics and Oral Facial Genetics, School of DentistryObjective: To determine whether trumpet performance skills are associated with malocclusion. Materials and Methods: Following institutional review board approval, 70 university trumpet students (54 male, 16 female; aged 20–38.9 years) were consented. After completing a survey, the students were evaluated while playing a scripted performance skills test (flexibility, articulation, range, and endurance exercises) on their instrument in a soundproof music practice room. One investigator (trumpet teacher) used a computerized metronome and a decibel meter during evaluation. A three-dimensional (3D) cone-beam computerized tomography scan (CBCT) was taken of each student the same day as the skills test. Following reliability studies, multiple dental parameters were measured on the 3D CBCT. Nonparametric correlations (Spearman), accepting P < .05 as significant, were used to determine if there were significant associations between dental parameters and the performance skills. Results: Intrarater reliability was excellent (intraclass correlations; all r values > .94). Although associations were weak to moderate, significant negative associations (r ≤ −.32) were found between Little's irregularity index, interincisal inclination, maxillary central incisor rotation, and various flexibility and articulation performance skills, whereas significant positive associations (r ≤ .49) were found between arch widths and various skills. Conclusions: Specific malocclusions are associated with trumpet performance of experienced young musicians.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 Characteristics of Chemosensory Perception in Long COVID and COVID Reinfection(MDPI, 2023-05-22) Jaramillo, Mikki; Thyvalikakath, Thankam P.; Eckert, George; Srinivasan, Mythily; Oral Pathology, Medicine and Radiology, School of DentistryEmerging data suggest an increasing prevalence of persistent symptoms in individuals affected by coronavirus disease-19 (COVID-19). The objective of this study was to determine the relative frequency of altered taste and smell in COVID reinfection (multiple COVID positive tests) and long COVID (one COVID positive test). We sent an electronic survey to patients in the Indiana University Health COVID registry with positive COVID test results, querying if they were experiencing symptoms consistent with long COVID including altered chemosensory perceptions. Among the 225 respondents, a greater long COVID burden and COVID reinfection was observed in women. Joint pain was reported as the most common symptom experienced by 18% of individuals in the long COVID cohort. In the COVID reinfection cohort >20% of individuals reported headache, joint pain, and cough. Taste perception worse than pre-COVID was reported by 29% and 42% of individuals in the long COVID and COVID reinfection cohorts, respectively. Smell perception worse than pre-COVID was reported by 37% and 46% of individuals in long COVID and COVID reinfection cohorts, respectively. Further, Chi-square test suggested significant association between pre-COVID severity of taste/smell perception and headache in both cohorts. Our findings highlight the prevalence of persistent chemosensory dysfunction for two years and longer in long COVID and COVID reinfection.Item A CLINICAL AND HISTOMORPHOMETRIC STUDY OF CALCIUM SULFATE (DENTOGEN®), COMPARED TO FREEZE DRIED BONE ALLOGRAFT (FDBA) FOR ALVEOLAR RIDGE PRESERVATION(Office of the Vice Chancellor for Research, 2011-04-08) Toloue, Samira; Eckert, George; Blanchard, StevenThere is significant ridge resorption following tooth extraction. Freeze dried bone allograft (FDBA) is most widely used for ridge preservation and calcium sulfate has begun to show popularity. The objective of this study is to evaluate if DentoGen® (calcium sulfate) is as effective in preserving post extraction ridge dimensions compared to FDBA. Thirty consecutive single rooted extraction sites were selected that met the inclusion criteria for the study. Post extraction clinical measurements were made with a pre-fabricated stent and dental calipers. The sites were then divided randomly into the test group (calcium sulfate) or the control group (FDBA). Patients were recalled after 3 months, sites were reentered and clinical measurements were again made. A trephine bone core was harvested and sent for histomorphometric analysis. A total of 21 subjects with 41 potential sites were recruited to this study (IRB approval # 1003-56). Following extraction, 29 sites met the inclusion criteria. To date, no significant change in vertical ridge height pre to post surgery was noted within the test and control groups (0.53 + 1.63mm, 0.35 ± 1.13mm, respectively). There was a significant decrease in buccal-lingual ridge width within both groups, (-1.23 + 1.14mm test group. 0.93 + 0.94mm control group) There was no significant difference in the preservation performance between the two treatment groups for both ridge width and vertical height. Histological samples are currently being analyzed. Results suggest no statically significant differences between the use of calcium sulfate versus FDBA in preserving post extraction ridge dimensions.Item Combined Effects of Soda Drinks and Nicotine on Streptococcus Mutans Metabolic Activity and Biofilm Activity(2019) Mokeem, Lamia Sami; Gregory, Richard; Cook, Norman Blaine; Windsor, Jack; Eckert, GeorgeItem Combined effects of soft drinks and nicotine on Streptococcus mutans metabolic activity and biofilm formation(J-STAGE, 2021-01) Mokeem, Lamia S.; Willis, Lisa H.; Windsor, L. Jack; Cook, N. Blaine; Eckert, George; Gregory, Richard L.; Cariology, Operative Dentistry and Dental Public Health, School of DentistryThe purpose of this study was to explore the effects of nicotine on the activity of Streptococcus mutans (S. mutans) in soft drinks. Regular soft drinks contain large proportions of high-fructose corn syrup (HFCS), which increases the activity of S. mutans resulting in high-caries risk compared with sugar-free soft drinks. Nicotine use exhibits a strong correlation with increased S. mutans biofilm formation. The soft drinks chosen were (Coca-Cola Classic, Diet Coke, Coca-Cola Zero Sugar, Caffeine-Free Coca-Cola, Caffeine-Free Diet Coke, Caffeine-Free Coca-Cola Zero Sugar). S. mutans was grown overnight in tryptic soy broth; nicotine was diluted in tryptic soy broth supplemented with 1.0% sucrose followed by soft drinks in dilution of 1:3. Total growth absorbance and biofilm growth were determined by spectrophotometry, absorbance measured to determine biofilm formation, and metabolic activity quantified. One-way ANOVA showed a considerable effect for HFCS and caffeine in the presence of nicotine and their interaction in all measures. Results showed sugar-free caffeinated colas demonstrated significant effect in inhibiting S. mutans biofilm formation and metabolic activity with nicotine. Nicotine-induced S. mutans increased biofilm formation and metabolic activity in the presence of HFCS and caffeine in soft drinks. In conclusion, smokers should consider sugar-free caffeinated versions to minimize the chance of developing dental caries dut to the reduction of biofilm formation.