Researchers have built a statistical model to predict which of five orthosis designs-the solid ankle-foot orthosis (SAFO), posterior leaf spring (PLS), hinged ankle-foot orthosis (HAFO), supramalleolar orthosis (SMO), or foot orthosis (FO)-could optimize orthosis selection in children with diplegic cerebral palsy (CP) and provide the child with the greatest improvement in gait. Using the model’s recommendation, classification accuracy ranged from 67 to 82 percent. The research was published online July 3 in the journal Gait and Posture.
Development of the model used retrospective data from 476 individuals who wore one of the five orthosis designs bilaterally, and a Random Forest™ algorithm (RFA), a type of decorrelated decision tree. Gait outcome was defined as the change in Gait Deviation Index (ΔGDI) between walking while wearing an orthosis compared to barefoot (ΔGDI = GDIOrthosis – GDIBarefoot). The clinical benefit was estimated by predicting the optimal orthosis and ΔGDI for 1,016 individuals (average age: 12.6 years), 540 of whom did not have an existing orthosis prescription.
Among limbs with an orthosis, the model agreed with the prescription only 14 percent of the time, according the study’s authors. For 56 percent of limbs without an orthosis, the model agreed that no orthosis was expected to provide benefit. Using the current standard of care (existing orthosis prescriptions), ΔGDI is only +0.4 points on average. Using the orthosis prediction model, average ΔGDI for orthosis users was estimated to improve to +5.6 points. The researchers concluded that the results suggest that an orthosis selection model derived from the RFA can significantly improve outcomes from orthosis use for individuals with diplegic CP, and suggest further validation of the model using data from other centers and a prospective study.
