Abstract
Vestibular impairments affect movement and can result in difficulties with daily life activities. The main aim of this study is to determine whether a short, simple test such as the Timed Up and Go test (TUG) can be an objective method of assessing balance dysfunction in patients with unilateral vestibular impairments. The TUG test was performed using six MediPost devices. The analysis was performed in three ways: (1) an analytical approach based only on data from one sensor; (2) an analytical approach based on data from six sensors; (3) an artificial neural network (ANN) approach based on data from six sensors. The best results were obtained using maximum angular velocities (MAV) of rotation and total time (TT) for approaches 1 and 2, and using 43 different features for approach 3. The following sensitivities and specificities were achieved: MAV 95% and 70%, TT 73% and 88% for approach 1; MAV 60% and 91% and TT 64% and 98% for approach 2; 88% and 92% for approach 3. The ANN-based six-sensor approach demonstrated the best sensitivity and specificity; however, the one-sensor approach might be used as a simple screening test.