Objectives:
To evaluate the precision of the virtual occlusal record using the Carestream CS3600 Intraoral Scanner (Carestream Dental, Atlanta, Ga).
Materials and Methods:
A total of 20 participants were recruited for this prospective study using preestablished inclusion/exclusion criteria. A complete intraoral scan and two bite registrations were obtained. The participants were instructed to bite with normal pressure when bite registrations were acquired. Contact locations, size (circumference), and intensity were identified on the maxillary first molars and canines. Agreement between contact size and intensity was assessed with intraclass correlation coefficients. Kappa statistics evaluated agreement in contact locations. Statistical significance was set at P < .05.
Results:
All participant data were included for statistical analysis. Between the two bite registrations, nonstatistically significant differences were observed in the proportion of locations with contacts (P = .7681). A nonstatistically significant difference (−0.25 mm, P = .8416) in mean contact circumference size was observed. A statistically significant difference in mean contact intensity was observed (P = .0448). When evaluating agreement between the bite registrations, a weak correlation for size (intraclass correlation coefficient = 0.35) and intensity (intraclass correlation coefficient = 0.32) was observed as well as a moderate agreement for contact location (κ coefficient = 0.67).
Conclusions:
The findings suggest that the Carestream intraoral scanner software possesses adequate precision when acquiring the location and size of the contacts in bite registrations. The scanner failed to demonstrate adequate precision when acquiring contact intensities in bite registrations. Additional research is warranted to further investigate the precision of virtual occlusal records with currently available software systems.
Purpose
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.