Computational formulation of orthodontic tooth-extraction decisions. Part II: which tooth should be extracted?

To develop a mathematical model that simulates optimum site(s) for tooth extraction and to examine what kinds of dentoskeletal traits, in the model, influence optimizing decisions for extraction site(s).

Conventional orthodontic records were obtained for 193 women who had received orthodontic tooth-extraction treatments judged as excellent treatment outcomes. The feature vector-elements that represented dentoskeletal traits, and weights of their contributions to achieving optimum simulation in the model, were determined.

The rate of coincidence between recommendations made by the optimized model and the actual judgments was found to be 86.0%. The elements that were sensitive to increasing the rate of coincidence and corresponding weights in judging the site(s) of tooth extraction were: protrusiveness of the upper and lower incisors (2.0), overjet and overbite (1.5), the membership grade for the skeletal Class II jaw relationship, molar relationship in the sagittal direction, the mandibular plane angle, and the severity of tooth crowding in the lower dentition (1.0). The remaining 10 feature vector-elements were also found to be indispensable for the model.

A mathematical model that simulates optimum site(s) for orthodontic tooth extraction, with a high agreement rate (86.0%) between the system's recommendations and the actual judgments given by orthodontists, was developed. The dentoskeletal structural traits that affected optimizing decisions for orthodontic tooth-extraction site(s) were formulated and subdivided into five major categories, ie, the sagittal dentoskeletal and soft tissue relationship, the vertical dentoskeletal relationship, the transverse dental relationship, the intra-arch conditions, and the pathological conditions.