Functional Independence Measure Motor Score Estimation Method Considering Instability of Movement

Abstract

In Japan, stroke is the second leading cause of long-term care. Therefore, patients with stroke need long-term rehabilitation. The Functional Independence Measure (FIM) is a measure of activities of daily living in stroke patients, which is a reliable physical therapy assessment that can be used in a multidisciplinary setting. However, the FIM scores are assessed by experienced nurses and difficult to assess accurately at home. In this study, we developed a system to estimate the FIM score easily at home using angular velocity from the target bodily movements using gyrosensors. Here, there are two types of target bodily movements: rising from a bed and sit-to-stand (STS) movement. To consider the instability of the two target bodily movements, the sum of vibrations was calculated from the acquired angular velocity time series data as features. We performed a Gaussian process regression analysis with the features as explanatory variables and the FIM motor score assessed by the nurse as an objective variable. Finally, we performed a series of experiments to evaluate the proposed method and calculated the root mean square error (RMSE) between the estimated FIM motor score and that assessed by the nurse. As a result, the RMSE with the lowest result was 10.42.