Easing Automatic Neurorehabilitation via Classification and Smoothness Analysis

TL;DR

This paper introduces an automatic neurorehabilitation assessment system that uses deep learning and movement smoothness measures to evaluate stroke patients' progress, aligning with clinical observations.

Contribution

It presents a novel pipeline combining shallow deep learning and jerk-based movement quality measures for stroke rehabilitation assessment.

Findings

Effective differentiation between healthy and patient movements based on smoothness.

The system's assessments align with clinicians' evaluations of patient progress.

Demonstrated potential for real-time, personalized neurorehabilitation monitoring.

Abstract

Assessing the quality of movements for post-stroke patients during the rehabilitation phase is vital given that there is no standard stroke rehabilitation plan for all the patients. In fact, it depends basically on the patient's functional independence and its progress along the rehabilitation sessions. To tackle this challenge and make neurorehabilitation more agile, we propose an automatic assessment pipeline that starts by recognizing patients' movements by means of a shallow deep learning architecture, then measuring the movement quality using jerk measure and related measures. A particularity of this work is that the dataset used is clinically relevant, since it represents movements inspired from Fugl-Meyer a well common upper-limb clinical stroke assessment scale for stroke patients. We show that it is possible to detect the contrast between healthy and patients movements in terms of smoothness, besides achieving conclusions about the patients' progress during the rehabilitation sessions that correspond to the clinicians' findings about each case.