The recovery from stroke is frequently incomplete, leading to impairments in the function of the arms and hands. These impairments decrease the independence of patients and lead to poor quality of life. Clinical measures of motor impairments are crude and cannot distinguish between true recovery (return to pre-injury movement patterns) and improved functioning due to compensations. This distinction is important since it will allow better utilization of the recovery potential of patients after stroke. Using deep learning techniques, we have recently developed methods to perform marker-less 3D kinematic analysis to better quantify movements quality after stroke. We propose here to use these technological advancements to develop tools for assessing the quality of arm movements in subjects after stroke, and to use these assessments in order to better understand the connection between coordination impairments and weakness after stroke and motor impairments. This study will provide a validated, robust and clinically feasible tool for the assessment of upper extremity movement quality after stroke. Collecting information about movement quality will allow the assessment of the extent of true recovery and the efficacy of interventions after stroke.
|Effective start/end date||1/01/21 → …|
- United States-Israel Binational Science Foundation (BSF)