A research team developed a model to help clinicians prescribe customized foot orthoses to patients with pes planus. The model can learn from and analyze clinical data based on a decision tree algorithm called a classification and regressing tree (CART). The model achieved an accuracy of 80.16 percent, which the researchers say suggests that it can provide adequate help to clinicians. A future study will refine the algorithm to compare and analyze the difference in foot shape and functional movement of patients with pes planus before and after the prescription of a foot orthosis to account for limitations found in the present model.
Eight parameters were selected based on the feature importance, and 15 rules for the prescription of foot orthoses were generated. The study used clinical data from 1,548 patients diagnosed with pes planus at the Department of Rehabilitation Medicine of Chungnam National University Hospital in Daejeon, Republic of Korea. Pes planus was diagnosed based on the results measured by a professional clinician with a goniometer (universal goniometer and gravity goniometer) and an inclinometer.
Nine variables affecting the prescription of foot orthosis were selected out of 20 independent variables: age; hip internal rotation; transmalleolar angle on the left side; inversion angle of the subtalar joint on the left side; eversion angle of the subtalar joint on the left side; eversion angle of the subtalar joint on the right side; forefoot to rearfoot angle on the right side; resting calcaneal stance position (RCSP) angle on the left side; and RCSP angle on the right side.
Two types of foot orthoses, gait plate and arch support orthoses with heel cups, were used as dependent variables. A gait plate limits in-toeing gait due to increased internal hip rotation and femoral anteversion with pes planus. An arch support orthosis with heel cups, designed to support the medial longitudinal arch and heel, is recommended to reduce rearfoot pronation, the collapse of the longitudinal arch, and foot instability. Each foot orthosis was customized for each patient’s foot with plaster casting in a resting calcaneal stance position.
The study’s authors noted several limitations to the study, which will direct their future work. There was insufficient quality training data for patients with pes planus, the types of pes planus (congenital or acquired/rigid or flexible), the time of onset, and other diseases related to pes planus were not considered, and there were no indicators to evaluate the clinical effectiveness of a prescribed foot orthosis.
The open-access study, “Decision tree-based foot orthosis prescription for patients with pes planus,” was published in the International Journal of Environmental Research and Public Health.
