A Machine-Learning Model for Automatic Detection of Movement Compensations in Stroke Patients

Ronit Feingold Polak,Lior Rokach,Shelly Levy-Tzedek,Boaz Lerner,Shir Kashi

doi:10.1109/tetc.2020.2988945

Abstract

During the process of rehabilitation after stroke, it is important that patients know how well they perform their exercise, so they can improve their performance in future repetitions. Standard clinical rating conducted by human observation is the prevailing way today to monitor motor recovery of the patient. Therefore, patients cannot know whether they are performing a movement properly while exercising by themselves. Adhering to the exercise regime makes the rehabilitation process more effective and efficient, and thus a system that can give the patients feedback on their performance is of great value. Here, we built a machine-learning-based automated model that gives patients accurate information on the compensatory (undesirable) movements that they make. To construct the model, we recorded movements from 30 stroke patients, who each performed 18 movements, used to identify the presence of six types of compensatory movements in stroke patients’ movement trajectories. We used the random-forest algorithm for training this multi-label classification model. We achieved 85 percent average precision across the six movement compensations. This is the first study to automatically identify movement compensations based on stroke patients’ data. This model can be adapted for use in in-clinic and at-home exercise programs for patients after stroke.

Highlights

IntroductionPatients who are not able to coordinate their muscle-activation patterns to perform an RTG task as they did before they had a stroke, develop compensatory movement patterns—e.g., bending their trunk, rather than extending their elbow—to reach an object located at arm’s length
Feature Selection (Figure 1.3) was conducted in order to obtain an optimal set of features that will be the input to the random k-label sets (RAkEL) for multi-label classification algorithm (Figure 1.4), which is suitable for multi-label problems
The calculation of the macro-averaged precision metric as we explain in Section III.B.1) is done by computing the precision for each label, i.e, compensation, separately before averaging them

Summary

Introduction

Patients who are not able to coordinate their muscle-activation patterns to perform an RTG task as they did before they had a stroke, develop compensatory movement patterns—e.g., bending their trunk, rather than extending their elbow—to reach an object located at arm’s length. Several such compensatory characteristics of movement have been described in RTG tasks, both in the trajectory and in the interjoint coordination of the movement [6], [8]

Objectives

Methods

Results

Conclusion