Gross motor ability predicts response to upper extremity rehabilitation in chronic stroke.

摘要: The majority of rehabilitation research focuses on the comparative effectiveness different interventions in groups patients, while much less is currently known regarding individual factors that predict response to rehabilitation. In a recent article, authors presented prognostic model identify sensorimotor characteristics predictive extent motor recovery after Constraint-Induced Movement (CI) therapy amongst individuals with chronic mild-to-moderate deficit using enhanced probabilistic neural network (EPNN). This follow-up paper examines which participant are robust predictors irrespective training modality. To accomplish this, EPNN was first applied treatment who received virtual-reality gaming intervention (utilizing same enrollment criteria as prior study). combinations yield high validity for both therapies, their respective datasets, were then identified. High classification accuracy achieved (94.7%) and combined datasets (94.5%). Though CI employed primarily fine-motor tasks emphasized gross-motor practice, larger improvements gross function observed within datasets. Poorer ability at pre-treatment predicted better conclusion this upper extremity hemiparesis, residual deficits highly responsive restorative interventions, modality training.