Sensor Abstracted Extremity Representation for Automatic Fugl-Meyer Assessment

Abstract

Summary. Given its virtually algorithmic process, the Fugl-Meyer Assessment (FMA) of motor recovery is prone to automatization reducing subjectivity, alleviating therapists' burden and collaterally reducing costs. Several attempts have been recently reported to achieve such automatization of the FMA. However, a cost-effective solution matching expert criteria is still unfulfilled, perhaps because these attempts are sensor-specific representation of the limb or have thus far rely on a trial and error strategy for building the underpinning computational model. Here, we propose a sensor abstracted representation. In particular, we improve previously reported results in the automatization of FMA by classifying a manifold embedded representation capitalizing on quaternions, and explore a wider range of classifiers. By enhancing the modeling, overall classification accuracy is boosted to 87% (mean: 82% ± 4.53: ) well over the maximum reported in literature thus far 51.03% (mean: 48.72 ± std: 2.10). The improved model brings automatic FMA closer to practical usage with implications for rehabilitation programs both in ward and at home.

Automation of motor dexterity assessment

“…The raw signals vary between the sensors and are not a good representation for classification purposes [28]. An abstract representation is obtained by transforming data to a common space as we have previously reported [22], [23].…”

Design of upper limb rehabilitation evaluation system based on deep learning

“…Angelica g. Thompson Butel et al employed three methods to assess limb function improvement in stroke patients and concluded that FMA is also appropriate for individuals with low motor function [4]. Patrick Heyer and Seunghee Lee utilized sensors for the research and development of full-automatic evaluation of FMA in their research on FMA automation applications at home and abroad [5][6]. Edwin Daniel Oña, E. D. used SPARC to measure the motion smoothness [7].…”