It is important to predict outcome after spinal injury. 

     To improve clinicians'''' ability to predict outcome after spinal cord injury (SCI) and to help classify patients within clinical trials, we have created a novel prediction model relating acute clinical and imaging information to functional outcome at 1 year.

     Of 729 patients, 376 met the inclusion/exclusion criteria.

     Data were obtained from 2 large prospective datasets. The primary outcome was Functional Independence Measure (FIM) motor score at 1 year follow-up. Predictor variables were obtained within 3 days of injury and included: 1)ASIA grade; 2)neurological level; 3)age; and 4)MRI intra-medullary signal characteristics. A linear regression model was created and internally validated using bootstrap re-sampling, with model performance judged by R-squared values. FIM-motor score was dichotomized and logistic modeling was used to classify patients achieving functional independence (score ?6 for FIM-motor items). Model discrimination was judged by the area under receiver operator curves (AUC).

     The mean FIM-motor score at 1 year was 62.9(±28.6). The linear model demonstrated an R-square of 0.54 in the original dataset and 0.53 across the 200 bootstraps, with mean parameter estimates for each covariate across the bootstraps closely approximating estimates from the original dataset. Functional independence was achieved by 148 patients(39.4%).For the logistic model, the AUC was 0.92, indicating excellent predictive discrimination.

     This is a retrospective study.

     We present the first prediction model that uses acute clinical and imaging data to predict functional status at 1 year follow-up in patients with traumatic SCI.

     We anticipate that this model will have important clinical impact to guide decision making and to counsel patients and families.