Extraction of teeth is an important treatment decision in orthodontic practice. An expert system that is able to arrive at suitable treatment decisions can be valuable to clinicians for verifying treatment plans, minimizing human error, training orthodontists, and improving reliability. In this work, we train a number of machine learning models for this prediction task using data for 287 patients, evaluated independently by five different orthodontists. We demonstrate why ensemble methods are particularly suited for this task. We evaluate the performance of the machine learning models and interpret the training behavior. We show that the results for our model are close to the level of agreement between different orthodontists.

Objective: To compare the dentoskeletal effects and treatment efficiency of the Twin Force Bite Corrector (TFBC) appliance in Class II correction of patients treated before or after the pubertal growth spurt. Materials and Methods: Forty-one normodivergent Class II patients treated with the TFBC appliance were divided into two groups based on their cervical vertebral maturation stage (CVMS). Group 1 (G1) consisted of 23 patients (mean age 12.44 ± 1.59 years) where treatment was initiated before the pubertal growth spurt (CVMS I and II), while group 2 (G2) consisted of 18 patients (mean age 13.76 ± 1.44 years) where treatment was started after the pubertal growth spurt (CVMS III to V). Dentoskeletal measurements were made on lateral cephalograms taken before (T1) and after orthodontic treatment (T2). Results: During treatment, G1 had significantly greater skeletal correction than G2, with more dentoalveolar effects being observed in G2 than G1. However, on comparing both groups at the end of treatment (T2) when growth is complete, no differences in the parameters measured were observed. Overall, treatment time was significantly longer for G1 (3.67 ± 1.45 years) compared to G2 (2.75 ± 1.07 years). Conclusions: There is no difference in overall dentoskeletal effects obtained at the end of treatment by the TFBC appliance in normodivergent prepubertal vs postpubertal patients. However, treatment efficiency based on treatment timing is significantly greater for the postpubertal group.

The purpose of this twin case comparison was to assess the short- and long-term effects of nonsurgical treatment vs orthognathic surgical treatment for Class II correction. Two identical twins (age 13 years 3 months) were treated for Class II correction where one patient was treated nonsurgically using a fixed functional appliance, while the other was treated using orthognathic mandibular advancement surgery. The patients were recalled and evaluated 5 years in retention. Comparing changes in the short and long term, surgical treatment led to superior skeletal results compared to the nonsurgical twin. However, the soft tissue profile was remarkably similar for both patients suggesting that soft tissue profile changes may not necessarily follow similar changes in the bony skeletal structures.