Abstract
Standard upper-limb motor function impairment assessments, such as the Fugl-Meyer Assessment (FMA), are a critical aspect of rehabilitation after neurological disorders. These assessments typically take a long time (about 30 min for the FMA) for a clinician to perform on a patient, which is a severe burden in a clinical environment. In this paper, we propose a framework for automating upper-limb motor assessments that uses low-cost sensors to collect movement data. The sensor data is then processed through a machine learning algorithm to determine a score for a patient’s upper-limb functionality. To demonstrate the feasibility of the proposed approach, we implemented a system based on the proposed framework that can automate most of the FMA. Our experiment shows that the system provides similar FMA scores to clinician scores, and reduces the time spent evaluating each patient by 82%. Moreover, the proposed framework can be used to implement customized tests or tests specified in other existing standard assessment methods.
Highlights
The prevalence of neurological disorders, such as stroke, cerebral palsy, and multiple sclerosis, has been rapidly increasing
Upper-limb motor impairment assessment is a time consuming process that must be done in person
The Fugl-Meyer Assessment (FMA) [2], which is one of the most widely utilized clinical instruments for assessment, consists of 33 tests for the upper-limbs, where the clinician asks a patient to perform a series of pre-defined movements
Summary
The prevalence of neurological disorders, such as stroke, cerebral palsy, and multiple sclerosis, has been rapidly increasing. Patient assessment is essential to quantify the severity of motor impairment, but to perform effective intervention as part of the process of recovery. The Fugl-Meyer Assessment (FMA) [2], which is one of the most widely utilized clinical instruments for assessment, consists of 33 tests for the upper-limbs, where the clinician asks a patient to perform a series of pre-defined movements. It takes at least 30 min for a clinician to perform for each patient [2]. The Wolf Motor Function Test (WMFT) [3], Action Research Arm Test (ARAT) [4], and the NIH Stroke Scale (NIHSS) [5], and other assessment methods similar to the FMA consist of many tests that are each rated according to the patient’s upper-limb motor functionality
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
