We present a model, trained on synthetic data, to predict the extent of first peak KAM reduction after toe-in gait retraining.
About: Although foot progression angle gait retraining is overall beneficial as a conservative intervention for knee osteoarthritis, knee adduction moment (KAM) reductions are not consistent across patients. Moreover, customized gait interventions are time-consuming and require instrumentation not commonly available in the clinic. We present a model that uses minimal clinical data to predict the extent of first peak KAM reduction after toe-in gait retraining. Given the lack of large public datasets that contain different gaits for the same patient, we present a method to generate toe-in gait data synthetically, and share the resultant trained model.
Data are available under Downloads > Data Share
Code and trained models are available at our GitHub: https://github.com/CMU-MBL/predictKAMreduction