Skip to main content
Fig. 3 | Journal of NeuroEngineering and Rehabilitation

Fig. 3

From: Computational neurorehabilitation: modeling plasticity and learning to predict recovery

Fig. 3

Example of the predictive power of a prognostic regression model, the proportional recovery model [171] (see Eq. 2). The model accurately predicts the change in upper extremity Fugl-Meyer score from 2 days to 3 months post stroke for 70–80 % of the patients, who all received rehabilitation. The subgroup of patients who did not fit the model experienced less recovery than predicted. To our knowledge, there are no computational rehabilitation models that can predict which patients will fit this prognostic regression model, or explain the variance in those who do not. Modified from [173]; Used with permission

Back to article page