Machine learning approach to gait deviation prediction based on isokinetic data acquired from biometric sensors

Analyzing gait deviation is one of the crucial factors during the diagnosis and treatment of children with Cerebral Palsy (CP). The typical diagnostic procedure requires an expensive and complicated three-dimensional gait analysis system based on visual sensors. In this work, we focus on predicting well-known gait pathology scores using only information collected from the BS4P, the affordable isokinetic dynamometer. Using such equipment, it is possible to determine gait pathological indices such as the gait deviation index (GDI) or the Gillette gait index (GGI).

Are there correlations between the results of examining patients with CP on the Biodex Pro 4 device and the gait quality metrics (GDI and GGI)?

The isokinetic data acquired from biometric sensors (74 records) were analyzed using big data methods. We used several Machine Learning methods to find the correlation between gait deviation and isokinetic data: Adaptive Boosting Regression, K-nearest Neighbor, Decision Tree Regression, Random Forest Regression, and Gradient Boost Regression.

In this paper, we provided a detailed comparison of different machine learning regression models in predicting gait quality in patients with CP based only on the data gathered from affordable Biodex 4 Pro device. The best result was obtained using the gradient boosting regression model with Mean Absolute Percentage Error of 6%. However, it was not possible to precisely predict the GGI index using this method.

The results obtained showed promising results in the evaluation of gait index scores, which gives the possibility of diagnosing patients with CP without the use of expensive optometric systems. Evaluating gait metrics using the approach proposed in this paper could be very helpful for both physicians and physiotherapists in assessing the condition of patients with CP, as well as other diseases related to gait problems.