Automated Evaluation of Upper Limb Motor Impairment of Patient with Cerebellar Ataxia

© 2019 IEEE. Upper limb impairment with various symptoms including incoordination, tremors and prolonged motion are important factors of motor disturbance in Cerebellar ataxia (CA). Accurate assessment is a key element in the diagnosis and progress monitoring of conditions such as CA. Often such assessments are mostly based on the observations of the clinicians and hence, are inherently subjective. In this paper, we propose a system that consists of two automated assessment schemes which employ a depth camera and an inertial measurement unit (IMU) sensor for the quantification of upper limb ataxia in the treatment of CA. The assessment includes an automated finger chase in which the patients were asked to follow a target point on the screen using their index finger and another assessment in which the patients were asked to tap their finger continuously on a surface at a comfortable rate. The overall system was tested for 44 CA patients and 14 age matched healthy individuals. The combination of features of the two tests provided us with an objective measurement which identifies CA patients to a higher degree of accuracy (Quadratic Discriminant Analysis, 93.1%) in addition to providing a high correlation (r = 0.8, p < 0.001) with the the Scale for the Assessment and Rating of Ataxia (SARA) based severity evaluation of patients.