A comprehensive approach for physical rehabilitation assessment in multiple sclerosis patients based on gait analysis

The assessment of gait features of subjects affected by Multiple Sclerosis supports physicians in defining customized rehabilitation treatment which, in turn, can lead to better clinical outcome. In the standard assessment protocol, an optoelectronic motion system, surface electromyography sensors, and a set of piezoelectric sensors on a force platform acquire large amount of data which is evaluated by physicians for defining treatment. In this paper, we introduce an automatic procedure based on Fuzzy-Granular Computing for evaluating gait metrics: three features extracted from each muscle involved in gait enable to summarize, quantify, and simplify the assessment protocol. Finally, we employ a Support Vector Machine to measure the relevance of the extracted features in classifying healthy subjects and patients using the simplified set of features.