Objective: To use the feature wrapping (FW) method to identify which cephalometric markers show the highest classification accuracy in prognosis prediction for Class III malocclusion and to compare the prediction accuracy between the FW method and conventional statistical methods such as discriminant analysis (DA). Materials and Methods: The sample set consisted of 38 patients (15 boys and 23 girls, mean age 8.53 ± 1.36 years) who were diagnosed with Class III malocclusion and received both first-phase (orthopedic) and second-phase (fixed orthodontic) treatments. Lateral cephalograms were taken before (T0) and after first-phase treatment (T1) and after second-phase treatment and retention (T2). Based on the measurements taken at the T2 stage, the patients were allocated into good (n = 20) or poor (n = 18) prognosis groups. Forty-six cephalometric variables on T0 lateral cephalograms were analyzed by the FW method to identify key determinants for discriminating between the two groups. Sequential forward search (SFS) algorism and support vector machine (SVM) were used in conjunction with the FW method to improve classification accuracy. To compare the prediction accuracy of the FW method with conventional statistical methods, DA was performed for the same data set. Results: AB to mandibular plane angle (°) and A to N-perpendicular (mm) were selected as the most accurate cephalometric predictors by both the FW and DA methods. However, classification accuracy was higher with the FW method (97.2%) compared with DA (92.1%), because the FW method with SFS and SVM has a more precise classification algorithm. Conclusions: The FW method, which uses a learning algorithm, might be an effective alternative to DA for prognosis prediction.
Objective: To determine the difference in the success rate for two types of oral installed mini-implants (OMIs): one type of initially installed OMI and a new implant of the same type that is reinstalled. Materials and Methods: The subjects consisted of 58 patients (19 male, 39 female; mean age = 21.78 ± 5.85 years) who had received at least one OMI (self-drilling type, conical shape with 2.0-mm upper diameter and 5-mm length) in the attached gingiva of the upper buccal posterior regions for maximum anchorage during en masse retraction. If an OMI failed, a new one was immediately installed in the same area after 4 to 6 weeks or in an adjacent area immediately. The total number of initially installed OMIs (II-OMI) was 109 and the total number of reinstalled OMIs (RI-OMI) was 34. Statistical analysis was performed using χ 2 test, Kaplan-Meier method, log-rank test, and Cox proportional hazards regression model. Results: The success rate and mean duration were 75.2% and 10.0 months, respectively, for II-OMI and 66.7% and 6.4 months, respectively, for RI-OMI. Age, vertical skeletal pattern, and site and side of implantation were not related to the success rates of II-OMI and RI-OMI. Log-rank test showed that II-OMI in males and Class III malocclusions were more prone to failure. The relative risk of II-OMI failure in Class III malocclusions as opposed to Class I malocclusions was 5.36 (95% confidence interval, 2.008 to 14.31, P = .001). Conclusion: The success rate of the II-OMI was not statistically different from that of the RI-OMI. Sex and ANB angle might be more important factors for better II-OMI results.